The Border Gateway Protocol (BGP) provides crucial routing information for the Internet infrastructure. A problem with abnormal routing behavior affects the stability and connectivity of the global Internet. The biggest hurdles in detecting BGP attacks are extremely unbalanced data set category distribution and the dynamic nature of the network. This unbalanced class distribution and dynamic nature of the network results in the classifier's inferior performance. In this paper we proposed an efficient approach to properly managing these problems, the proposed approach tackles the unbalanced classification of datasets by turning the problem of binary classification into a problem of multiclass classification. This is achieved by splitting the majority-class samples evenly into multiple segments using Affinity Propagation, where the number of segments is chosen so that the number of samples in any segment closely matches the minority-class samples. Such sections of the dataset together with the minor class are then viewed as different classes and used to train the Extreme Learning Machine (ELM). The RIPE and BCNET datasets are used to evaluate the performance of the proposed technique. When no feature selection is used, the proposed technique improves the F1 score by 1.9% compared to state-of-the-art techniques. With the Fischer feature selection algorithm, the proposed algorithm achieved the highest F1 score of 76.3%, which was a 1.7% improvement over the compared ones. Additionally, the MIQ feature selection technique improves the accuracy by 3.5%. For the BCNET dataset, the proposed technique improves the F1 score by 1.8% for the Fisher feature selection technique. The experimental findings support the substantial improvement in performance from previous approaches by the new technique.
6RLR-ABC: 6LOWPAN ROUTING PROTOCOL WITH LOCAL REPAIR USING BIO INSPIRED ARTIF...IJCNCJournal
ย
The document presents a new routing protocol called 6RLR-ABC for 6LoWPAN networks that uses an artificial bee colony algorithm for local route repair. It compares the performance of 6RLR-ABC to the existing 6LoWPAN Ad-hoc On-Demand Distance Vector (LOAD) protocol through simulations. The results show that 6RLR-ABC achieves lower packet delay, higher packet delivery ratio, and higher throughput while using less energy than LOAD, especially with increasing network traffic loads.
Multipath Routing Protocol by Breadth First Search Algorithm in Wireless Mesh...IOSR Journals
ย
This document proposes a multipath routing protocol for wireless mesh networks that uses a parallel layer-based approach and breadth-first search algorithm to discover multiple paths between a source and destination. It organizes nodes into layers based on distance from the destination and performs iterative breadth-first searches to find partial paths connecting nodes in lower layers, storing the partial paths. This process repeats until reaching the destination to find all possible paths. The primary path is then elected using an Expected Forwarding Counter metric to select the most reliable path. The protocol was evaluated in NS-2 and showed improved throughput, delivery ratio, and reduced delay compared to other protocols.
Multimedia Streaming in Wireless Ad Hoc Networks According to Fuzzy Cross-lay...Editor IJCATR
ย
1) The document describes a fuzzy logic-based routing protocol for multimedia streaming in wireless ad hoc networks. It aims to select optimal routes taking into account factors like node mobility, available bandwidth, and battery energy levels.
2) The protocol uses fuzzy logic rules and membership functions to calculate a "stability rate" for network links based on their characteristics. This is used to select routes with minimum mobility and maximum bandwidth and energy.
3) Simulation results using the OPNET simulator show that the proposed fuzzy logic approach has fewer lost data packets compared to the standard AODV routing protocol, especially over time, indicating it selects more reliable routes for multimedia streaming in mobile ad hoc networks.
This document proposes a modified ant colony optimization (ACO) routing protocol for mobile ad hoc networks (MANETs). The key points are:
1) The protocol is based on swarm intelligence principles and uses mobile software agents like ants to intelligently route packets from node to node.
2) It modifies the standard ACO algorithm to make it power-balanced and achieve faster packet delivery rates by making the pheromone decay dependent on nodes' battery levels.
3) The routing process involves forward and backward ants establishing and maintaining routes between source and destination via probabilistic path selection based on accumulated pheromone levels.
EFFECTS OF MAC PARAMETERS ON THE PERFORMANCE OF IEEE 802.11 DCF IN NS-3ijwmn
ย
This paper presents the design procedure of the NS-3 script for WLAN that is organized according to the hierarchical manner of TCP/IP model. We configure all layers by using NS-3 model objects and set and modify the values used by objects to investigate the effects of MAC parameters (access mechanism, CWmin, CWmax and retry limit) on the performance metrics viz. packet delivery ratio, packet lost ratio, aggregated throughput, and average delay. The simulation results show that RTS/CTS access mechanism outperforms basic access mechanism in saturated state, whereas the MAC parameters have no significant impact on network performance in non-saturated state. A higher value of CWmin improves the aggregated throughput in expense of average delay. The tradeoff relationships among the performance metrics are also observed in results for the optimal values of MAC parameters. Our design procedure represents a good guideline for new NS-3 users to design and modify script and results greatly benefit the network design and management.
PERFORMANCE ANALYSIS OF OLSR PROTOCOL IN MANET CONSIDERING DIFFERENT MOBILITY...ijwmn
ย
A Mobile Ad Hoc Network (MANET) is created when an independent mobile node network is connected
dynamically via wireless links. MANET is a self-organizing network that does not rely on pre-existing
infrastructure such as wired or wireless network routers. Mobile nodes in this network move randomly,
thus, the topology is always changing. Routing protocols in MANET are critical in ensuring dependable
and consistent connectivity between the mobile nodes. They conclude logically based on the interaction
between mobile nodes in MANET routing and encourage them to choose the optimum path between source
and destination. Routing protocols are classified as proactive, reactive, or hybrid. The focus of this project
will be on Optimized Link State Routing (OLSR) protocol, a proactive routing technique. OLSR is known as
the optimized variant of link state routing in which packets are sent throughout the network using the
multipoint relay (MPR) mechanism. This article evaluates the performance of the OLSR routing protocol
under condition of changing mobility speed and network density. The study's performance indicators are
average packet throughput, packet delivery ratio (PDR), and average packet latency. Network Simulator 2
(NS-2) and an external patch UM-OLSR are used to simulate and evaluate the performance of such
protocol. As a result of research, the approach of implementing the MPR mechanism are able to minimise
redundant data transmission during the normal message broadcast. The MPRs enhance the link state
protocolsโ traditional diffusion mechanism by selecting the right MPRs. Hence, the number of undesired
broadcasts can be reduced and limited. Further research will focus on different scenario and environment
using different mobility model
This document summarizes a research paper that proposes a new routing algorithm for mobile ad hoc networks using fuzzy logic. The algorithm considers three input variables - signal power, mobility, and delay. It defines fuzzy sets and membership functions to map crisp normalized values of these variables to linguistic values. Rules are written to relate the input and output linguistic variables. The output represents the optimal route. The algorithm aims to address routing problems related to bandwidth, signal power, mobility, and delay in a distributed manner without relying on centralized control. It is designed to quickly adapt to changes in network topology.
The document reviews different secured routing protocols for mobile ad hoc networks and their vulnerabilities. It discusses three main categories of secured routing protocols:
1. Trust oriented protocols which use node trust values to determine routing, but are still vulnerable to malicious nodes gaining control.
2. Incentive oriented protocols which aim to discourage attacks through incentives like credits, but require online access or tamper-proof hardware.
3. Detection and isolation protocols which identify misbehaving nodes but have issues like high overhead, inability to detect certain attacks, and vulnerability to false accusations.
In conclusion, while existing protocols address some attacks, they remain vulnerable or impractical in many cases. A robust, lightweight approach is still needed to
6RLR-ABC: 6LOWPAN ROUTING PROTOCOL WITH LOCAL REPAIR USING BIO INSPIRED ARTIF...IJCNCJournal
ย
The document presents a new routing protocol called 6RLR-ABC for 6LoWPAN networks that uses an artificial bee colony algorithm for local route repair. It compares the performance of 6RLR-ABC to the existing 6LoWPAN Ad-hoc On-Demand Distance Vector (LOAD) protocol through simulations. The results show that 6RLR-ABC achieves lower packet delay, higher packet delivery ratio, and higher throughput while using less energy than LOAD, especially with increasing network traffic loads.
Multipath Routing Protocol by Breadth First Search Algorithm in Wireless Mesh...IOSR Journals
ย
This document proposes a multipath routing protocol for wireless mesh networks that uses a parallel layer-based approach and breadth-first search algorithm to discover multiple paths between a source and destination. It organizes nodes into layers based on distance from the destination and performs iterative breadth-first searches to find partial paths connecting nodes in lower layers, storing the partial paths. This process repeats until reaching the destination to find all possible paths. The primary path is then elected using an Expected Forwarding Counter metric to select the most reliable path. The protocol was evaluated in NS-2 and showed improved throughput, delivery ratio, and reduced delay compared to other protocols.
Multimedia Streaming in Wireless Ad Hoc Networks According to Fuzzy Cross-lay...Editor IJCATR
ย
1) The document describes a fuzzy logic-based routing protocol for multimedia streaming in wireless ad hoc networks. It aims to select optimal routes taking into account factors like node mobility, available bandwidth, and battery energy levels.
2) The protocol uses fuzzy logic rules and membership functions to calculate a "stability rate" for network links based on their characteristics. This is used to select routes with minimum mobility and maximum bandwidth and energy.
3) Simulation results using the OPNET simulator show that the proposed fuzzy logic approach has fewer lost data packets compared to the standard AODV routing protocol, especially over time, indicating it selects more reliable routes for multimedia streaming in mobile ad hoc networks.
This document proposes a modified ant colony optimization (ACO) routing protocol for mobile ad hoc networks (MANETs). The key points are:
1) The protocol is based on swarm intelligence principles and uses mobile software agents like ants to intelligently route packets from node to node.
2) It modifies the standard ACO algorithm to make it power-balanced and achieve faster packet delivery rates by making the pheromone decay dependent on nodes' battery levels.
3) The routing process involves forward and backward ants establishing and maintaining routes between source and destination via probabilistic path selection based on accumulated pheromone levels.
EFFECTS OF MAC PARAMETERS ON THE PERFORMANCE OF IEEE 802.11 DCF IN NS-3ijwmn
ย
This paper presents the design procedure of the NS-3 script for WLAN that is organized according to the hierarchical manner of TCP/IP model. We configure all layers by using NS-3 model objects and set and modify the values used by objects to investigate the effects of MAC parameters (access mechanism, CWmin, CWmax and retry limit) on the performance metrics viz. packet delivery ratio, packet lost ratio, aggregated throughput, and average delay. The simulation results show that RTS/CTS access mechanism outperforms basic access mechanism in saturated state, whereas the MAC parameters have no significant impact on network performance in non-saturated state. A higher value of CWmin improves the aggregated throughput in expense of average delay. The tradeoff relationships among the performance metrics are also observed in results for the optimal values of MAC parameters. Our design procedure represents a good guideline for new NS-3 users to design and modify script and results greatly benefit the network design and management.
PERFORMANCE ANALYSIS OF OLSR PROTOCOL IN MANET CONSIDERING DIFFERENT MOBILITY...ijwmn
ย
A Mobile Ad Hoc Network (MANET) is created when an independent mobile node network is connected
dynamically via wireless links. MANET is a self-organizing network that does not rely on pre-existing
infrastructure such as wired or wireless network routers. Mobile nodes in this network move randomly,
thus, the topology is always changing. Routing protocols in MANET are critical in ensuring dependable
and consistent connectivity between the mobile nodes. They conclude logically based on the interaction
between mobile nodes in MANET routing and encourage them to choose the optimum path between source
and destination. Routing protocols are classified as proactive, reactive, or hybrid. The focus of this project
will be on Optimized Link State Routing (OLSR) protocol, a proactive routing technique. OLSR is known as
the optimized variant of link state routing in which packets are sent throughout the network using the
multipoint relay (MPR) mechanism. This article evaluates the performance of the OLSR routing protocol
under condition of changing mobility speed and network density. The study's performance indicators are
average packet throughput, packet delivery ratio (PDR), and average packet latency. Network Simulator 2
(NS-2) and an external patch UM-OLSR are used to simulate and evaluate the performance of such
protocol. As a result of research, the approach of implementing the MPR mechanism are able to minimise
redundant data transmission during the normal message broadcast. The MPRs enhance the link state
protocolsโ traditional diffusion mechanism by selecting the right MPRs. Hence, the number of undesired
broadcasts can be reduced and limited. Further research will focus on different scenario and environment
using different mobility model
This document summarizes a research paper that proposes a new routing algorithm for mobile ad hoc networks using fuzzy logic. The algorithm considers three input variables - signal power, mobility, and delay. It defines fuzzy sets and membership functions to map crisp normalized values of these variables to linguistic values. Rules are written to relate the input and output linguistic variables. The output represents the optimal route. The algorithm aims to address routing problems related to bandwidth, signal power, mobility, and delay in a distributed manner without relying on centralized control. It is designed to quickly adapt to changes in network topology.
The document reviews different secured routing protocols for mobile ad hoc networks and their vulnerabilities. It discusses three main categories of secured routing protocols:
1. Trust oriented protocols which use node trust values to determine routing, but are still vulnerable to malicious nodes gaining control.
2. Incentive oriented protocols which aim to discourage attacks through incentives like credits, but require online access or tamper-proof hardware.
3. Detection and isolation protocols which identify misbehaving nodes but have issues like high overhead, inability to detect certain attacks, and vulnerability to false accusations.
In conclusion, while existing protocols address some attacks, they remain vulnerable or impractical in many cases. A robust, lightweight approach is still needed to
Efficient Routing Protocol in the Mobile Ad-hoc Network (MANET) by using Gene...IOSR Journals
ย
This document discusses using a genetic algorithm to improve routing in mobile ad hoc networks. It begins with background on mobile ad hoc networks and common routing protocols. It then introduces genetic algorithms and how they work by simulating natural evolution. The document proposes using a genetic algorithm with the AODV routing protocol to find optimal paths between source and destination nodes. It describes implementing this approach and comparing its performance to traditional AODV routing. The results showed the genetic algorithm approach performed better in terms of quality of service and throughput.
There are number of cluster based routing algorithms in mobile ad hoc networks. Since ad hoc networks are not accompanied by fixed access points, efficient routing is a must for such networks. Clustering approach is applied in mobile ad hoc network because clusters are more easily manageable and are more viable. It consists of segregating the given network into several reasonable clusters by using a clustering algorithm. By performing clustering we elect a worthy node from the cluster as the cluster head in such a way that we strive to reduce the management overheads and thus increasing the efficiency of routing. As for the fact that nodes in mobile ad hoc network have frequent host change and frequent topology change routing plays an important role for maintenance and backup mechanism to stabilize network performance. This paper aims to review the previous research papers and provide a survey on the various cluster based routing protocols in mobile ad hoc network. This paper presents analytical study of cluster based routing algorithms from literature. Index Termsโ Ad- hoc networks, Cluster head, Clustering, Protocol, Route selection.
Improved Routing Protocol in Mobile Ad Hoc Networks Using Fuzzy LogicTELKOMNIKA JOURNAL
ย
In mobile ad hoc networks, route selection is one of the most important issues that is studied in
these networks as a field of research. Many articles trying to provide solutions to choose the best path in
which the important parameters such as power consumption, bandwidth and mobility are used. In this
article, in order to improve the solutions presented in recent papers parameters such as power remaining,
mobility, degree node and available bandwidth are used by taking the factors for each parameter in
proportion to its influence in choosing the best path. Finally, we compare the proposed solution with the
three protocols IAOMDV-F, AODVFART and FLM-AODV with the help of OPNET simulation program
based on network throughput, routing discovery time, the average number of hops per route, network
delay.
Joint Routing and Congestion Control in Multipath Channel based on Signal to ...IJECEIAES
ย
Routing protocol and congestion control in Transmission Control Protocol (TCP) have important roles in wireless mobile network performance. In wireless communication, the stability of the path and successful data transmission will be influenced by the channel condition. This channel condition constraints come from path loss and the multipath channel fading. With these constraints, the algorithm in the routing protocol and congestion control is confronted with the uncertainty of connection quality and probability of successful packet transmission, respectively. It is important to investigate the reliability and robustness of routing protocol and congestion control algorithms in dealing with such situation. In this paper, we develop a detailed approach and analytical throughput performance with a cross layer scheme (CLS) between routing and congestion control mechanism based on signal to noise ratio (SNR) in Rician and Rayleigh as multipath fading channel. We proposed joint routing and congestion control TCP with a cross layer scheme model based on SNR (RTCP-SNR). We compare the performance of RTCP-SNR with conventional routing-TCP and routing-TCP that used CLS with routing aware (RTCP-RA) model. The analyses and the simulation results showed that RTCP-SNR in a multipath channel outperforms conventional routing-TCP and RTCP-RA.
INVESTIGATING MULTILAYER OMEGA-TYPE NETWORKS OPERATING WITH THE CUT-THROUGH T...IJCNCJournal
ย
The continuous increase in the complexity of data networks has motivated the development of more effective Multistage Interconnection Networks (MINs) as important factors in providing higher data transfer rates in various switching divisions. In this paper, semi-layer omega-class networks operating with a cut-through forwarding technique are chosen as test-bed subjects for detailed evaluation, and this network architecture is modelled, inspected, and simulated. The results are examined for relevant singlelayer omega networks operating with cut-through or โstore and forwardโ forwarding techniques. Two series of experiments are carried out: one concerns the case of uniform traffic, while the other is related to hotspot traffic. The results quantify the way in which this network outperforms the corresponding singlelayer network architectures for the same network size and buffer size. Furthermore, the effects of the dimensions of the switch elements and their corresponding reliability on the overall interconnection system are investigated, and the complexity and the relevant cost are examined. The data yielded by this investigation can be valuable to MIN engineers and can allow them to achieve more productive networks with lower overall implementation costs.
ANALYSIS AND STUDY OF MATHEMATICAL MODELS FOR RWA PROBLEM IN OPTICAL NETWORKSIJEEE
ย
Blocking probability has been one of the key performance to solve Routing and Wavelength Assignment problem (RWA) indexes in the design of wavelength-routed all-optical WDM networks. To evaluate blocking probability different analytical model are introduced.
Performance Analysis of Ad-hoc on Demand Distance Vector Routing (AODV) and D...ijceronline
ย
International Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
Dynamic cluster based adaptive gateway discovery mechanisms in an integrated ...IAEME Publication
ย
This document discusses dynamic cluster-based adaptive gateway discovery mechanisms for integrating mobile ad hoc networks (MANETs) with the Internet. It begins by introducing the problem and outlines existing solutions. It then proposes a new architecture using dynamic clusters and mobile gateways. Key points of the proposed approach include dynamically adjusting the TTL value and periodicity of gateway advertisements based on network characteristics. The paper evaluates the approach through simulations in NS-2, finding it increases reliability and performance metrics like delivery ratio and delay. In conclusion, dynamic cluster-based gateways help provide reliable Internet access for MANET nodes with varying mobility.
This document summarizes a research paper that proposes a new Position Based Opportunistic Routing Protocol (POR) to improve reliable data delivery in mobile ad hoc networks. Existing geographic routing protocols have issues with route failures and delays in discovering new routes when nodes move. The proposed POR protocol selects multiple forwarding candidate nodes to opportunistically forward packets. If the primary forwarder fails, backup candidates can forward packets to avoid transmission interruptions. Simulation results show the POR protocol has lower delay and higher packet delivery ratio compared to existing protocols.
An Efficient and Stable Routing Algorithm in Mobile Ad Hoc NetworkIJCNCJournal
ย
Mobile Ad hoc Network (MANET) is mainly designed to set up communication among devices in infrastructure-less wireless communication network. Routing in this kind of communication network is highly affected by its restricted characteristics such as frequent topological changes and limited battery power. Several research works have been carried out to improve routing performance in MANET. However, the overall performance enhancement in terms of packet delivery, delay and control message overhead is still not come into the wrapping up. In order to overcome the addressed issues, an Efficient and Stable-AODV (EFST-AODV) routing scheme has been proposed which is an improvement over AODV to establish a better quality route between source and destination. In this method, we have modified the route request and route reply phase. During the route request phase, cost metric of a route is calculated on the basis of parameters such as residual energy, delay and distance. In a route reply phase, average residual energy and average delay of overall path is calculated and the data forwarding decision is taken at the source node accordingly. Simulation outcomes reveal that the proposed approach gives better results in terms of packet delivery ratio, delay, throughput, normalized routing load and control message overhead as compared to AODV.
Traffic Congestion Prediction using Deep Reinforcement Learning in Vehicular ...IJCNCJournal
ย
In recent years, a new wireless network called vehicular ad-hoc network (VANET), has become a popular research topic. VANET allows communication among vehicles and with roadside units by providing information to each other, such as vehicle velocity, location and direction. In general, when many vehicles likely to use the common route to proceed to the same destination, it can lead to a congested route that should be avoided. It may be better if vehicles are able to predict accurately the traffic congestion and then avoid it. Therefore, in this work, the deep reinforcement learning in VANET to enhance the ability to predict traffic congestion on the roads is proposed. Furthermore, different types of neural networks namely Convolutional Neural Network (CNN), Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) are investigated and compared in this deep reinforcement learning model to discover the most effective one. Our proposed method is tested by simulation. The traffic scenarios are created using traffic simulator called Simulation of Urban Mobility (SUMO) before integrating with deep reinforcement learning model. The simulation procedures, as well as the programming used, are described in detail. The performance of our proposed method is evaluated using two metrics; the average travelling time delay and average waiting time delay of vehicles. According to the simulation results, the average travelling time delay and average waiting time delay are gradually improved over the multiple runs, since our proposed method receives feedback from the environment. In addition, the results without and with three different deep learning algorithms, i.e., CNN, MLP and LSTM are compared. It is obvious that the deep reinforcement learning model works effectively when traffic density is neither too high nor too low. In addition, it can be concluded that the effective algorithms for traffic congestion prediction models in descending order are MLP, CNN, and LSTM, respectively.
The document proposes a Crosslayered and Power Conserved Routing Topology (CPCRT) for congestion control in mobile ad hoc networks. CPCRT aims to distinguish between packet loss due to link failure versus other causes like congestion. It takes a cross-layer approach using information from the physical, MAC, and application layers. The proposed method also aims to conserve power during packet transmission by adjusting transmission power levels based on received signal strength. Simulation results show that CPCRT can better utilize resources and conserve power during congestion control compared to other approaches.
Review on design of advanced opportunistics routing in manetyatin1988
ย
This document discusses mobile ad hoc networks and opportunistic routing. It provides background on MANETs, including their definition as temporary networks formed without infrastructure between wireless mobile nodes. It also covers applications of MANETs and challenges like mobility and link quality. The document introduces opportunistic routing as a forwarding technique for unpredictable MANET topologies. It reviews related work analyzing opportunistic routing and discusses using fuzzy logic to improve routing stability and availability in MANETs. The proposed work is to implement a fuzzy routing mechanism on the AODV protocol to optimize link availability and evaluate performance metrics like throughput and delay.
Performance Evaluation of a Layered WSN Using AODV and MCF Protocols in NS-2csandit
ย
This document summarizes a study that compares the performance of two routing protocols, AODV and MCF, in a layered wireless sensor network (WSN) using the network simulator NS-2. It first provides background on AODV, describing how it establishes and maintains routes. It then describes the MCF protocol, which formulates lightpath routing as an integer linear program to minimize the impact of fiber failures. The document outlines how both protocols were implemented in NS-2 and compares their performance based on metrics like throughput, packet loss, and end-to-end delay. The simulation results show that MCF generally has better throughput and reliability than AODV in the scenario of a 80-node WSN.
ERROR PERFORMANCE ANALYSIS USING COOPERATIVE CONTENTION-BASED ROUTING IN WIRE...IJCSEIT Journal
ย
In Wireless Ad hoc network, cooperation of nodes can be achieved by more interactions at higher protocol
layers, particularly the MAC (Medium Access Control) and network layers play vital role. MAC facilitates
a routing protocol based on position location of nodes at network layer specially known as Beacon-less
geographic routing (BLGR) using Contention-based selection process. This paper proposes two levels of
cross-layer framework -a MAC network cross-layer design for forwarder selection (or routing) and a
MAC-PHY for relay selection. Wireless networks suffers huge number of communication at the same time
leads to increase in collision and energy consumption; hence focused on new Contention access method
that uses a dynamical change of channel access probability which can reduce the number of contention
times and collisions. Simulation result demonstrates the best Relay selection and the comparative of direct
mode with the cooperative networks. And also demonstrates the Performance evaluation of contention
probability with Collision avoidance.
Efficient routing mechanism using cycle based network and k hop security in a...ijait
ย
In a multi-domain network, Topology Aggregation (TA) may be adopted to provide limited information
regarding intra cluster connectivity without revealing detailed topology information. Nodes are grouped
into the cluster. Every cluster has border nodes, which is used for data transmission between source and
destination. The K-hop security can be used for the purpose of securing the data communication. The
topologies are spanning tree and balanced tree that can be used to reduce bandwidth overhead, delivery
delay and to increase throughput and packet delivery ratio. The shortest path can be found using
Bhandariโs algorithm and Cycle-Based Minimum-Cost Domain-Disjoint Paths (CMCDP) Algorithm for
establish the second path in the network . These topologies are compared to demonstrate the advantage of
finding shortest path using Bhandariโs algorithm.
A SURVEY OF ENHANCED ROUTING PROTOCOLS FOR MANETspijans
ย
This document summarizes and surveys several enhanced routing protocols that have been developed for mobile ad hoc networks (MANETs). It begins by providing background on routing challenges in MANETs and classifications of routing protocols. It then describes several traditional and widely used routing protocols, including DSDV, OLSR, TORA, DSR, and AODV. The document focuses on summarizing several new routing protocols that have been proposed to improve upon existing protocols. It discusses protocols such as BAWB-DSR, CCSR, RAMP, AODV-SBA, CBRP-R, and CBTRP - noting techniques, advantages, and disadvantages of each. The overall purpose is to review
MACHINE LEARNING FOR QOE PREDICTION AND ANOMALY DETECTION IN SELF-ORGANIZING ...ijwmn
ย
Existing mobile networking systems lack the level of intelligence, scalability, and autonomous adaptability
required to optimally enable next-generation networks like 5G and beyond, which are expected to be Self -
Organizing Networks (SONs). It is anticipated that machine learning (ML) will be instrumental in designing
future โxโG SON networks with their demanding Quality of Experience (QoE) requirements. This paper
evaluates a methodology that uses supervised machine learning to predict the QoE level of the end user
experiences and uses this information to detect anomalous behavior of dysfunctional network nodes
(eNodeBs/base stations) in self-organizing mobile networks. An end-to-end network scenario is created using
the network simulator ns-3, where end users interact with a remote host that is accessed over the Internet to
run the most commonly used applications like file downloads and uploads and the resulting output is used as
a dataset to implement ML algorithms for QoE prediction and eNodeB (eNB) anomaly detection. Three ML
algorithms were implemented and compared to study their effectiveness and the scalability of the
methodology. In the test network, an accuracy score greater than 99% is achieved using the ML algorithms.
As suggested by the ns-3 simulation the use of ML for QoE prediction will help network operators understand
end-user needs and identify network elements that are failing and need attention and recovery.
ISSUES RELATED TO SAMPLING TECHNIQUES FOR NETWORK TRAFFIC DATASETijmnct
ย
The document discusses issues related to sampling techniques for network traffic datasets. It analyzes various sampling techniques for their ability to capture information while sampling imbalanced network traffic data. The key points are:
1) Network traffic data is huge, varying, and imbalanced with some classes distributed unequally. Sampling is needed to reduce training time for machine learning algorithms used to analyze the data, but sampling can lose important information.
2) The document evaluates random sampling, systematic sampling, stratified sampling, and re-sampling techniques using a dataset collected from Panjab University's network. It finds that random sampling can miss some protocol classes entirely, losing important information.
3) Careful sampling is needed to handle the
S3 INFOTECH +91 988 48 48 198
# 10/1, Jones Road, Saidapet, Chennai โ 15. Ph: 044-3201 7467, 9884848198.
www.s3computers.com E-Mail: info@s3computers.com
The document lists 10 project titles from IEEE 2015 related to wireless networks and security. The projects address topics such as detecting malicious nodes in mobile ad hoc networks, enhancing security and caching in MANETs, providing multicast connectivity in flexgrid optical networks, and optimizing resource allocation and base station selection in heterogeneous networks.
Efficient Routing Protocol in the Mobile Ad-hoc Network (MANET) by using Gene...IOSR Journals
ย
This document discusses using a genetic algorithm to improve routing in mobile ad hoc networks. It begins with background on mobile ad hoc networks and common routing protocols. It then introduces genetic algorithms and how they work by simulating natural evolution. The document proposes using a genetic algorithm with the AODV routing protocol to find optimal paths between source and destination nodes. It describes implementing this approach and comparing its performance to traditional AODV routing. The results showed the genetic algorithm approach performed better in terms of quality of service and throughput.
There are number of cluster based routing algorithms in mobile ad hoc networks. Since ad hoc networks are not accompanied by fixed access points, efficient routing is a must for such networks. Clustering approach is applied in mobile ad hoc network because clusters are more easily manageable and are more viable. It consists of segregating the given network into several reasonable clusters by using a clustering algorithm. By performing clustering we elect a worthy node from the cluster as the cluster head in such a way that we strive to reduce the management overheads and thus increasing the efficiency of routing. As for the fact that nodes in mobile ad hoc network have frequent host change and frequent topology change routing plays an important role for maintenance and backup mechanism to stabilize network performance. This paper aims to review the previous research papers and provide a survey on the various cluster based routing protocols in mobile ad hoc network. This paper presents analytical study of cluster based routing algorithms from literature. Index Termsโ Ad- hoc networks, Cluster head, Clustering, Protocol, Route selection.
Improved Routing Protocol in Mobile Ad Hoc Networks Using Fuzzy LogicTELKOMNIKA JOURNAL
ย
In mobile ad hoc networks, route selection is one of the most important issues that is studied in
these networks as a field of research. Many articles trying to provide solutions to choose the best path in
which the important parameters such as power consumption, bandwidth and mobility are used. In this
article, in order to improve the solutions presented in recent papers parameters such as power remaining,
mobility, degree node and available bandwidth are used by taking the factors for each parameter in
proportion to its influence in choosing the best path. Finally, we compare the proposed solution with the
three protocols IAOMDV-F, AODVFART and FLM-AODV with the help of OPNET simulation program
based on network throughput, routing discovery time, the average number of hops per route, network
delay.
Joint Routing and Congestion Control in Multipath Channel based on Signal to ...IJECEIAES
ย
Routing protocol and congestion control in Transmission Control Protocol (TCP) have important roles in wireless mobile network performance. In wireless communication, the stability of the path and successful data transmission will be influenced by the channel condition. This channel condition constraints come from path loss and the multipath channel fading. With these constraints, the algorithm in the routing protocol and congestion control is confronted with the uncertainty of connection quality and probability of successful packet transmission, respectively. It is important to investigate the reliability and robustness of routing protocol and congestion control algorithms in dealing with such situation. In this paper, we develop a detailed approach and analytical throughput performance with a cross layer scheme (CLS) between routing and congestion control mechanism based on signal to noise ratio (SNR) in Rician and Rayleigh as multipath fading channel. We proposed joint routing and congestion control TCP with a cross layer scheme model based on SNR (RTCP-SNR). We compare the performance of RTCP-SNR with conventional routing-TCP and routing-TCP that used CLS with routing aware (RTCP-RA) model. The analyses and the simulation results showed that RTCP-SNR in a multipath channel outperforms conventional routing-TCP and RTCP-RA.
INVESTIGATING MULTILAYER OMEGA-TYPE NETWORKS OPERATING WITH THE CUT-THROUGH T...IJCNCJournal
ย
The continuous increase in the complexity of data networks has motivated the development of more effective Multistage Interconnection Networks (MINs) as important factors in providing higher data transfer rates in various switching divisions. In this paper, semi-layer omega-class networks operating with a cut-through forwarding technique are chosen as test-bed subjects for detailed evaluation, and this network architecture is modelled, inspected, and simulated. The results are examined for relevant singlelayer omega networks operating with cut-through or โstore and forwardโ forwarding techniques. Two series of experiments are carried out: one concerns the case of uniform traffic, while the other is related to hotspot traffic. The results quantify the way in which this network outperforms the corresponding singlelayer network architectures for the same network size and buffer size. Furthermore, the effects of the dimensions of the switch elements and their corresponding reliability on the overall interconnection system are investigated, and the complexity and the relevant cost are examined. The data yielded by this investigation can be valuable to MIN engineers and can allow them to achieve more productive networks with lower overall implementation costs.
ANALYSIS AND STUDY OF MATHEMATICAL MODELS FOR RWA PROBLEM IN OPTICAL NETWORKSIJEEE
ย
Blocking probability has been one of the key performance to solve Routing and Wavelength Assignment problem (RWA) indexes in the design of wavelength-routed all-optical WDM networks. To evaluate blocking probability different analytical model are introduced.
Performance Analysis of Ad-hoc on Demand Distance Vector Routing (AODV) and D...ijceronline
ย
International Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
Dynamic cluster based adaptive gateway discovery mechanisms in an integrated ...IAEME Publication
ย
This document discusses dynamic cluster-based adaptive gateway discovery mechanisms for integrating mobile ad hoc networks (MANETs) with the Internet. It begins by introducing the problem and outlines existing solutions. It then proposes a new architecture using dynamic clusters and mobile gateways. Key points of the proposed approach include dynamically adjusting the TTL value and periodicity of gateway advertisements based on network characteristics. The paper evaluates the approach through simulations in NS-2, finding it increases reliability and performance metrics like delivery ratio and delay. In conclusion, dynamic cluster-based gateways help provide reliable Internet access for MANET nodes with varying mobility.
This document summarizes a research paper that proposes a new Position Based Opportunistic Routing Protocol (POR) to improve reliable data delivery in mobile ad hoc networks. Existing geographic routing protocols have issues with route failures and delays in discovering new routes when nodes move. The proposed POR protocol selects multiple forwarding candidate nodes to opportunistically forward packets. If the primary forwarder fails, backup candidates can forward packets to avoid transmission interruptions. Simulation results show the POR protocol has lower delay and higher packet delivery ratio compared to existing protocols.
An Efficient and Stable Routing Algorithm in Mobile Ad Hoc NetworkIJCNCJournal
ย
Mobile Ad hoc Network (MANET) is mainly designed to set up communication among devices in infrastructure-less wireless communication network. Routing in this kind of communication network is highly affected by its restricted characteristics such as frequent topological changes and limited battery power. Several research works have been carried out to improve routing performance in MANET. However, the overall performance enhancement in terms of packet delivery, delay and control message overhead is still not come into the wrapping up. In order to overcome the addressed issues, an Efficient and Stable-AODV (EFST-AODV) routing scheme has been proposed which is an improvement over AODV to establish a better quality route between source and destination. In this method, we have modified the route request and route reply phase. During the route request phase, cost metric of a route is calculated on the basis of parameters such as residual energy, delay and distance. In a route reply phase, average residual energy and average delay of overall path is calculated and the data forwarding decision is taken at the source node accordingly. Simulation outcomes reveal that the proposed approach gives better results in terms of packet delivery ratio, delay, throughput, normalized routing load and control message overhead as compared to AODV.
Traffic Congestion Prediction using Deep Reinforcement Learning in Vehicular ...IJCNCJournal
ย
In recent years, a new wireless network called vehicular ad-hoc network (VANET), has become a popular research topic. VANET allows communication among vehicles and with roadside units by providing information to each other, such as vehicle velocity, location and direction. In general, when many vehicles likely to use the common route to proceed to the same destination, it can lead to a congested route that should be avoided. It may be better if vehicles are able to predict accurately the traffic congestion and then avoid it. Therefore, in this work, the deep reinforcement learning in VANET to enhance the ability to predict traffic congestion on the roads is proposed. Furthermore, different types of neural networks namely Convolutional Neural Network (CNN), Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) are investigated and compared in this deep reinforcement learning model to discover the most effective one. Our proposed method is tested by simulation. The traffic scenarios are created using traffic simulator called Simulation of Urban Mobility (SUMO) before integrating with deep reinforcement learning model. The simulation procedures, as well as the programming used, are described in detail. The performance of our proposed method is evaluated using two metrics; the average travelling time delay and average waiting time delay of vehicles. According to the simulation results, the average travelling time delay and average waiting time delay are gradually improved over the multiple runs, since our proposed method receives feedback from the environment. In addition, the results without and with three different deep learning algorithms, i.e., CNN, MLP and LSTM are compared. It is obvious that the deep reinforcement learning model works effectively when traffic density is neither too high nor too low. In addition, it can be concluded that the effective algorithms for traffic congestion prediction models in descending order are MLP, CNN, and LSTM, respectively.
The document proposes a Crosslayered and Power Conserved Routing Topology (CPCRT) for congestion control in mobile ad hoc networks. CPCRT aims to distinguish between packet loss due to link failure versus other causes like congestion. It takes a cross-layer approach using information from the physical, MAC, and application layers. The proposed method also aims to conserve power during packet transmission by adjusting transmission power levels based on received signal strength. Simulation results show that CPCRT can better utilize resources and conserve power during congestion control compared to other approaches.
Review on design of advanced opportunistics routing in manetyatin1988
ย
This document discusses mobile ad hoc networks and opportunistic routing. It provides background on MANETs, including their definition as temporary networks formed without infrastructure between wireless mobile nodes. It also covers applications of MANETs and challenges like mobility and link quality. The document introduces opportunistic routing as a forwarding technique for unpredictable MANET topologies. It reviews related work analyzing opportunistic routing and discusses using fuzzy logic to improve routing stability and availability in MANETs. The proposed work is to implement a fuzzy routing mechanism on the AODV protocol to optimize link availability and evaluate performance metrics like throughput and delay.
Performance Evaluation of a Layered WSN Using AODV and MCF Protocols in NS-2csandit
ย
This document summarizes a study that compares the performance of two routing protocols, AODV and MCF, in a layered wireless sensor network (WSN) using the network simulator NS-2. It first provides background on AODV, describing how it establishes and maintains routes. It then describes the MCF protocol, which formulates lightpath routing as an integer linear program to minimize the impact of fiber failures. The document outlines how both protocols were implemented in NS-2 and compares their performance based on metrics like throughput, packet loss, and end-to-end delay. The simulation results show that MCF generally has better throughput and reliability than AODV in the scenario of a 80-node WSN.
ERROR PERFORMANCE ANALYSIS USING COOPERATIVE CONTENTION-BASED ROUTING IN WIRE...IJCSEIT Journal
ย
In Wireless Ad hoc network, cooperation of nodes can be achieved by more interactions at higher protocol
layers, particularly the MAC (Medium Access Control) and network layers play vital role. MAC facilitates
a routing protocol based on position location of nodes at network layer specially known as Beacon-less
geographic routing (BLGR) using Contention-based selection process. This paper proposes two levels of
cross-layer framework -a MAC network cross-layer design for forwarder selection (or routing) and a
MAC-PHY for relay selection. Wireless networks suffers huge number of communication at the same time
leads to increase in collision and energy consumption; hence focused on new Contention access method
that uses a dynamical change of channel access probability which can reduce the number of contention
times and collisions. Simulation result demonstrates the best Relay selection and the comparative of direct
mode with the cooperative networks. And also demonstrates the Performance evaluation of contention
probability with Collision avoidance.
Efficient routing mechanism using cycle based network and k hop security in a...ijait
ย
In a multi-domain network, Topology Aggregation (TA) may be adopted to provide limited information
regarding intra cluster connectivity without revealing detailed topology information. Nodes are grouped
into the cluster. Every cluster has border nodes, which is used for data transmission between source and
destination. The K-hop security can be used for the purpose of securing the data communication. The
topologies are spanning tree and balanced tree that can be used to reduce bandwidth overhead, delivery
delay and to increase throughput and packet delivery ratio. The shortest path can be found using
Bhandariโs algorithm and Cycle-Based Minimum-Cost Domain-Disjoint Paths (CMCDP) Algorithm for
establish the second path in the network . These topologies are compared to demonstrate the advantage of
finding shortest path using Bhandariโs algorithm.
A SURVEY OF ENHANCED ROUTING PROTOCOLS FOR MANETspijans
ย
This document summarizes and surveys several enhanced routing protocols that have been developed for mobile ad hoc networks (MANETs). It begins by providing background on routing challenges in MANETs and classifications of routing protocols. It then describes several traditional and widely used routing protocols, including DSDV, OLSR, TORA, DSR, and AODV. The document focuses on summarizing several new routing protocols that have been proposed to improve upon existing protocols. It discusses protocols such as BAWB-DSR, CCSR, RAMP, AODV-SBA, CBRP-R, and CBTRP - noting techniques, advantages, and disadvantages of each. The overall purpose is to review
MACHINE LEARNING FOR QOE PREDICTION AND ANOMALY DETECTION IN SELF-ORGANIZING ...ijwmn
ย
Existing mobile networking systems lack the level of intelligence, scalability, and autonomous adaptability
required to optimally enable next-generation networks like 5G and beyond, which are expected to be Self -
Organizing Networks (SONs). It is anticipated that machine learning (ML) will be instrumental in designing
future โxโG SON networks with their demanding Quality of Experience (QoE) requirements. This paper
evaluates a methodology that uses supervised machine learning to predict the QoE level of the end user
experiences and uses this information to detect anomalous behavior of dysfunctional network nodes
(eNodeBs/base stations) in self-organizing mobile networks. An end-to-end network scenario is created using
the network simulator ns-3, where end users interact with a remote host that is accessed over the Internet to
run the most commonly used applications like file downloads and uploads and the resulting output is used as
a dataset to implement ML algorithms for QoE prediction and eNodeB (eNB) anomaly detection. Three ML
algorithms were implemented and compared to study their effectiveness and the scalability of the
methodology. In the test network, an accuracy score greater than 99% is achieved using the ML algorithms.
As suggested by the ns-3 simulation the use of ML for QoE prediction will help network operators understand
end-user needs and identify network elements that are failing and need attention and recovery.
ISSUES RELATED TO SAMPLING TECHNIQUES FOR NETWORK TRAFFIC DATASETijmnct
ย
The document discusses issues related to sampling techniques for network traffic datasets. It analyzes various sampling techniques for their ability to capture information while sampling imbalanced network traffic data. The key points are:
1) Network traffic data is huge, varying, and imbalanced with some classes distributed unequally. Sampling is needed to reduce training time for machine learning algorithms used to analyze the data, but sampling can lose important information.
2) The document evaluates random sampling, systematic sampling, stratified sampling, and re-sampling techniques using a dataset collected from Panjab University's network. It finds that random sampling can miss some protocol classes entirely, losing important information.
3) Careful sampling is needed to handle the
S3 INFOTECH +91 988 48 48 198
# 10/1, Jones Road, Saidapet, Chennai โ 15. Ph: 044-3201 7467, 9884848198.
www.s3computers.com E-Mail: info@s3computers.com
The document lists 10 project titles from IEEE 2015 related to wireless networks and security. The projects address topics such as detecting malicious nodes in mobile ad hoc networks, enhancing security and caching in MANETs, providing multicast connectivity in flexgrid optical networks, and optimizing resource allocation and base station selection in heterogeneous networks.
An efficient vertical handoff mechanism for future mobile networkBasil John
ย
This document proposes a novel fuzzy logic based vertical handoff decision algorithm for heterogeneous wireless networks. It introduces a speed-adaptive system discovery scheme to improve the update rate of candidate networks based on the mobile terminal's speed. It also includes a pre-handoff decision method to quickly filter candidate networks and reduce unnecessary handoffs. The key aspects of the proposed algorithm are: 1) It uses a speed-adaptive scheme to dynamically adjust the discovery of candidate networks. 2) It employs a pre-handoff decision method to filter networks and reduce ping-pong effects. 3) It applies fuzzy logic to evaluate multiple parameters like bandwidth, RSS, and cost to select the best network. Simulations show it outperforms traditional RSS-based
Genetic Algorithm for Vertical Handover (GAfVH)in a Heterogeneous networksIJECEIAES
ย
The fifth generation (5G) wireless system will deal with the growing demand of new multimedia and broadband application. The 5G network architecture is based on heterogeneous Radio Access Technologies (RATs). In such implementation the Vertical handover is a key issue. Up till now, systems are using simple mechanisms to make handover decision, based on the evaluation of the Received Signal Strength (RSS). In some cases these mechanisms are not Efficient.This paper presents a new vertical handover algorithm based on Genetic Algorithm (GAfVH). It aims to reduce the number of unnecessary handovers, and optimizes the system performance. We compare our simulation results to the Received Signal Strength (RSS) based method. The results show that the number of handovers decreases. Moreover, we demonstrate that the network selection result can differ from an application to another.
Congestion Control in Wireless Sensor Networks Using Genetic AlgorithmEditor IJCATR
ย
Sensor network consists of a large number of small nods, strongly interacting with the physical environment, takes
environmental data through sensors, and reacts after processing on information. Wireless network technologies are widely used in most
applications. As wireless sensor networks have many activities in the field of information transmission, network congestion cannot be
thus avoided. So it seems necessary that some new methods can control congestion and use existing resources for providing better traffic
demands. Congestion increases packet loss and retransmission of removed packets and also wastes of energy. In this paper, a novel
method is presented for congestion control in wireless sensor networks using genetic algorithm. The results of simulation show that the
proposed method, in comparison with the algorithm LEACH, can significantly improve congestion control at high speeds.
Cao nicolau-mc dermott-learning-neural-cybernetics-2018-preprintNam Le
ย
This paper proposes using latent representation models, specifically autoencoders (AEs) and variational autoencoders (VAEs), to improve network anomaly detection. The models are trained on only normal data and introduce regularizers that compress normal data into a tight region around the origin in the latent space, while anomalies will have representations further away. This new latent feature space is then used as input to one-class classifiers to detect anomalies. The goal is for the models to perform well even with limited training data and be insensitive to hyperparameter settings, in order to address challenges of network anomaly detection like lack of labeled anomaly data and high dimensionality.
Online stream mining approach for clustering network trafficeSAT Journals
ย
Abstract A large number of research have been proposed on intrusion detection system, which leads to the implementation of agent based intelligent IDS (IIDS), Non โ intelligent IDS (NIDS), signature based IDS etc. While building such IDS models, learning algorithms from flow of network traffic plays crucial role in accuracy of IDS systems. The proposed work focuses on implementing the novel method to cluster network traffic which eliminates the limitations in existing online clustering algorithms and prove the robustness and accuracy over large stream of network traffic arriving at extremely high rate. We compare the existing algorithm with novel methods to analyse the accuracy and complexity. Keywordsโ NIDS, Data Stream Mining, Online Clustering, RAH algorithm, Online Efficient Incremental Clustering algorithm
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
APPLICATION OF GENETIC ALGORITHM IN DESIGNING A SECURITY MODEL FOR MOBILE ADH...cscpconf
ย
In recent years, the static shortest path (SP) problem has been well addressed using intelligent
optimization techniques, e.g., artificial neural networks, genetic algorithms (GAs), particle
swarm optimization, etc. However, with the advancement in wireless communications, more and
more mobile wireless networks appear, e.g., mobile networks [mobile ad hoc networks
(MANETs)], wireless sensor networks, etc. One of the most important characteristics in mobile
wireless networks is the topology dynamics, i.e., the network topology changes over time due to
energy conservation or node mobility. Therefore, the SP routing problem in MANETs turns out to
be a dynamic optimization problem. GA's are able to find, if not the shortest, at least an optimal
path between source and destination in mobile ad-hoc network nodes. And we obtain the alternative path or backup path to avoid reroute discovery in the case of link failure or nodeex
IGeekS Technologies is a company located in Bangalore, India. We have being recognized as a quality provider of hardware and software solutions for the studentโs in order carry out their academic Projects. We offer academic projects at various academic levels ranging from graduates to masters (Diploma, BCA, BE, M. Tech, MCA, M. Sc (CS/IT)). As a part of the development training, we offer Projects in Embedded Systems & Software to the Engineering College students in all major disciplines.
Approximation of regression-based fault minimization for network trafficTELKOMNIKA JOURNAL
ย
This research associates three distinct approaches for computer network traffic prediction. They are the traditional stochastic gradient descent (SGD) using a few random samplings instead of the complete dataset for each iterative calculation, the gradient descent algorithm (GDA) which is a well-known optimization approach in deep learning, and the proposed method. The network traffic is computed from the traffic load (data and multimedia) of the computer network nodes via the Internet. It is apparent that the SGD is a modest iteration but can conclude suboptimal solutions. The GDA is a complicated one, can function more accurate than the SGD but difficult to manipulate parameters, such as the learning rate, the dataset granularity, and the loss function. Network traffic estimation helps improve performance and lower costs for various applications, such as an adaptive rate control, load balancing, the quality of service (QoS), fair bandwidth allocation, and anomaly detection. The proposed method confirms optimal values out of parameters using simulation to compute the minimum figure of specified loss function in each iteration.
SAMPLING BASED APPROACHES TO HANDLE IMBALANCES IN NETWORK TRAFFIC DATASET FOR...cscpconf
ย
Network traffic data is huge, varying and imbalanced because various classes are not equally distributed. Machine learning (ML) algorithms for traffic analysis uses the samples from this
data to recommend the actions to be taken by the network administrators as well as training. Due to imbalances in dataset, it is difficult to train machine learning algorithms for traffic
analysis and these may give biased or false results leading to serious degradation in performance of these algorithms. Various techniques can be applied during sampling to minimize the effect of imbalanced instances. In this paper various sampling techniques have been analysed in order to compare the decrease in variation in imbalances of network traffic
datasets sampled for these algorithms. Various parameters like missing classes in samples probability of sampling of the different instances have been considered for comparison
Web server load prediction and anomaly detection from hypertext transfer prot...IJECEIAES
ย
As network traffic increases and new intrusions occur, anomaly detection solutions based on machine learning are necessary to detect previously unknown intrusion patterns. Most of the developed models require a labelled dataset, which can be challenging owing to a shortage of publicly available datasets. These datasets are often too small to effectively train machine learning models, which further motivates the use of real unlabeled traffic. By using real traffic, it is possible to more accurately simulate the types of anomalies that might occur in a real-world network and improve the performance of the detection model. We present a method able to predict and categorize anomalies without the aid of a labelled dataset, demonstrating the modelโs usability while also gathering a dataset from real noisy network traffic. The proposed long short-term memory (LTSM) based intrusion detection system was tested in a real-world setting of an antivirus company and was successful in detecting various intrusions using 5-minute windowing over both the predicted and real update curves thereby demonstrating its usefulness. Our contribution was the development of a robust model generally applicable to any hypertext transfer protocol (HTTP) traffic with almost real-time anomaly detection, while also outperforming earlier studies in terms of prediction accuracy.
DYNAMIC NETWORK ANOMALY INTRUSION DETECTION USING MODIFIED SOMcscpconf
ย
This document presents a modified Self-Organizing Map (SOM) algorithm for network anomaly intrusion detection. The proposed algorithm allows the neural network to grow dynamically based on a distance threshold, rather than having a fixed architecture. It also uses connection strength to identify neighborhood nodes for weight vector updating. The algorithm was tested on standard intrusion detection datasets and achieved a detection rate of 98% and a false alarm rate of 2%, outperforming a basic SOM approach. The modified SOM addresses limitations of fixed network architecture and random weight initialization in the standard SOM method.
Implementation of energy efficient coverage aware routing protocol for wirele...ijfcstjournal
ย
In recent years, wireless sensor network have been used in many application such as disaster reservation,
agriculture, environmental observation and forecasting .Coverage preservation and energy consumption
are two most important issues in wireless sensor networks. To increase the network lifetime, we propose an
energy efficient coverage aware routing protocol for wireless sensor network for randomly deployed sensor
nodes. Some of the routing protocol is based on energy efficiency and some are based on coverage aware.
The proposed routing protocol is based on both the issues i.e. coverage and energy, in which we first find
the k-mean i.e. the degree of coverage, so that we can use this in the selection of cluster heads in wireless
sensor network by using Genetic Algorithm for increasing network lifetime and coverage. For cluster head
selection each node evaluates its k-mean and energy by internal function which used as fitness function in
genetic algorithm. The proposed algorithm โImplementation of energy efficient coverage aware routing
protocol for Wireless Sensor Networkโ is designed for homogeneous wireless sensor network. Simulations
results show that proposed algorithm increases the network lifetime by reduce the energy consumption and
preserve coverage. Simulation is done with MATLAB and a comparison of algorithm with benchmark
algorithms is also performed.
Fuzzy Logic-based Efficient Message Route Selection Method to Prolong the Net...IJCNCJournal
ย
Recently, sensor networks have been used in a wide range of applications, and interest in sensor node performance has increased. A sensor network is composed of tiny nodes with limited resources. The sensor network communicates between nodes in a configured network through self-organization. An energyefficient security protocol with a hierarchy structure with various advantages has been proposed to prolong the network lifetime of sensor networks. But due to structural problems in traditional protocols, nodes located upstream tend to consume relatively high energy compared to other nodes. A network protocol should be considered to provide minimal security and efficient allocation of energy consumption by nodes to increase the network lifetime. In this paper, we introduce a solution to solve the bottleneck problem through an efficient message route selection method. The proposed method selects an efficient messaging path using GA and fuzzy logic composed of multiple rules. Message route selection plays an important role in controlling the load balancing of nodes. A principal benefit of the proposed scheme is the potential portability of the clustering-based protocol. In addition, the proposed method is updated to find the optimal path through the genetic algorithm to respond to various environments. We demonstrated the effectiveness of the proposed method through an experiment in which the proposed method is applied to a probabilistic voting-based filtering scheme that is one of the cluster-based security schemes.
FUZZY LOGIC-BASED EFFICIENT MESSAGE ROUTE SELECTION METHOD TO PROLONG THE NET...IJCNCJournal
ย
- The document discusses a fuzzy logic-based method for efficient message routing in wireless sensor networks to prolong the network lifetime. It aims to balance energy load across nodes by selectively tagging nodes at risk of energy exhaustion and rerouting messages around them.
- It proposes using fuzzy logic to evaluate nodes based on their potential importance, energy level, and event occurrence frequency to determine tagging. Tagged nodes avoid routing traffic but still detect and generate reports.
- The method was tested by applying it to a probabilistic voting-based filtering security scheme and was shown to improve energy efficiency, node survival rate, and report transmission success compared to not tagging nodes.
Similar to Securing BGP by Handling Dynamic Network Behavior and Unbalanced Datasets (20)
Rendezvous Sequence Generation Algorithm for Cognitive Radio Networks in Post...IJCNCJournal
ย
Recent natural disasters have inflicted tremendous damage on humanity, with their scale progressively increasing and leading to numerous casualties. Events such as earthquakes can trigger secondary disasters, such as tsunamis, further complicating the situation by destroying communication infrastructures. This destruction impedes the dissemination of information about secondary disasters and complicates post-disaster rescue efforts. Consequently, there is an urgent demand for technologies capable of substituting for these destroyed communication infrastructures. This paper proposes a technique for generating rendezvous sequences to swiftly reconnect communication infrastructures in post-disaster scenarios. We compare the time required for rendezvous using the proposed technique against existing methods and analyze the average time taken to establish links with the rendezvous technique, discussing its significance. This research presents a novel approach enabling rapid recovery of destroyed communication infrastructures in disaster environments through Cognitive Radio Network (CRN) technology, showcasing the potential to significantly improve disaster response and recovery efforts. The proposed method reduces the time for the rendezvous compared to existing methods, suggesting that it can enhance the efficiency of rescue operations in post-disaster scenarios and contribute to life-saving efforts.
Blockchain Enforced Attribute based Access Control with ZKP for Healthcare Se...IJCNCJournal
ย
The relationship between doctors and patients is reinforced through the expanded communication channels provided by remote healthcare services, resulting in heightened patient satisfaction and loyalty. Nonetheless, the growth of these services is hampered by security and privacy challenges they confront. Additionally, patient electronic health records (EHR) information is dispersed across multiple hospitals in different formats, undermining data sovereignty. It allows any service to assert authority over their EHR, effectively controlling its usage. This paper proposes a blockchain enforced attribute-based access control in healthcare service. To enhance the privacy and data-sovereignty, the proposed system employs attribute-based access control, zero-knowledge proof (ZKP) and blockchain. The role of data within our system is pivotal in defining attributes. These attributes, in turn, form the fundamental basis for access control criteria. Blockchain is used to keep hospital information in public chain but EHR related data in private chain. Furthermore, EHR provides access control by using the attributed based cryptosystem before they are stored in the blockchain. Analysis shows that the proposed system provides data sovereignty with privacy provision based on the attributed based access control.
EECRPSID: Energy-Efficient Cluster-Based Routing Protocol with a Secure Intru...IJCNCJournal
ย
A revolutionary idea that has gained significance in technology for Internet of Things (IoT) networks backed by WSNs is the " Energy-Efficient Cluster-Based Routing Protocol with a Secure Intrusion Detection" (EECRPSID). A WSN-powered IoT infrastructure's hardware foundation is hardware with autonomous sensing capabilities. The significant features of the proposed technology are intelligent environment sensing, independent data collection, and information transfer to connected devices. However, hardware flaws and issues with energy consumption may be to blame for device failures in WSN-assisted IoT networks. This can potentially obstruct the transfer of data. A reliable route significantly reduces data retransmissions, which reduces traffic and conserves energy. The sensor hardware is often widely dispersed by IoT networks that enable WSNs. Data duplication could occur if numerous sensor devices are used to monitor a location. Finding a solution to this issue by using clustering. Clustering lessens network traffic while retaining path dependability compared to the multipath technique. To relieve duplicate data in EECRPSID, we applied the clustering technique. The multipath strategy might make the provided protocol more dependable. Using the EECRPSID algorithm, will reduce the overall energy consumption, minimize the End-to-end delay to 0.14s, achieve a 99.8% Packet Delivery Ratio, and the network's lifespan will be increased. The NS2 simulator is used to run the whole set of simulations. The EECRPSID method has been implemented in NS2, and simulated results indicate that comparing the other three technologies improves the performance measures.
Analysis and Evolution of SHA-1 Algorithm - Analytical TechniqueIJCNCJournal
ย
A 160-bit (20-byte) hash value, sometimes called a message digest, is generated using the SHA-1 (Secure Hash Algorithm 1) hash function in cryptography. This value is commonly represented as 40 hexadecimal digits. It is a Federal Information Processing Standard in the United States and was developed by the National Security Agency. Although it has been cryptographically cracked, the technique is still in widespread usage. In this work, we conduct a detailed and practical analysis of the SHA-1 algorithm's theoretical elements and show how they have been implemented through the use of several different hash configurations.
Optimizing CNN-BiGRU Performance: Mish Activation and Comparative AnalysisIJCNCJournal
ย
Deep learning is currently extensively employed across a range of research domains. The continuous advancements in deep learning techniques contribute to solving intricate challenges. Activation functions (AF) are fundamental components within neural networks, enabling them to capture complex patterns and relationships in the data. By introducing non-linearities, AF empowers neural networks to model and adapt to the diverse and nuanced nature of real-world data, enhancing their ability to make accurate predictions across various tasks. In the context of intrusion detection, the Mish, a recent AF, was implemented in the CNN-BiGRU model, using three datasets: ASNM-TUN, ASNM-CDX, and HOGZILLA. The comparison with Rectified Linear Unit (ReLU), a widely used AF, revealed that Mish outperforms ReLU, showcasing superior performance across the evaluated datasets. This study illuminates the effectiveness of AF in elevating the performance of intrusion detection systems.
An Hybrid Framework OTFS-OFDM Based on Mobile Speed EstimationIJCNCJournal
ย
The Future wireless communication systems face the challenging task of simultaneously providing high-quality service (QoS) and broadband data transmission, while also minimizing power consumption, latency, and system complexity. Although Orthogonal Frequency Division Multiplexing (OFDM) has been widely adopted in 4G and 5G systems, it struggles to cope with a significant delay and Doppler spread in high mobility scenarios. To address these challenges, a novel waveform named Orthogonal Time Frequency Space (OTFS). Designers aim to outperform OFDM by closely aligning signals with the channel behaviour. In this paper, we propose a switching strategy that empowers operators to select the most appropriate waveform based on an estimated speed of the mobile user. This strategy enables the base station to dynamically choose the waveform that best suits the mobile userโs speed. Additionally, we suggest retaining an Integrated Sensing and Communication (ISAC) radar approach for accurate Doppler estimation. This provides precise information to facilitate the waveform selection procedure. By leveraging the switching strategy and harnessing the Doppler estimation capabilities of an ISAC radar.Our proposed approach aims to enhance the performance of wireless communication systems in high mobility cases. Considering the complexity of waveform processing, we introduce an optimized hybrid system that combines OTFS and OFDM, resulting in reduced complexity while still retaining performance benefits.This hybrid system presents a promising solution for improving the performance of wireless communication systems in higher mobility.The simulation results validate the effectiveness of our approach, demonstrating its potential advantages for future wireless communication systems. The effectiveness of the proposed approach is validated by simulation results as it will be illustrated.
Enhanced Traffic Congestion Management with Fog Computing - A Simulation-Base...IJCNCJournal
ย
Accurate latency computation is essential for the Internet of Things (IoT) since the connected devices generate a vast amount of data that is processed on cloud infrastructure. However, the cloud is not an optimal solution. To overcome this issue, fog computing is used to enable processing at the edge while still allowing communication with the cloud. Many applications rely on fog computing, including traffic management. In this paper, an Intelligent Traffic Congestion Mitigation System (ITCMS) is proposed to address traffic congestion in heavily populated smart cities. The proposed system is implemented using fog computing and tested in a crowdedCairo city. The results obtained indicate that the execution time of the simulation is 4,538 seconds, and the delay in the application loop is 49.67 seconds. The paper addresses various issues, including CPU usage, heap memory usage, throughput, and the total average delay, which are essential for evaluating the performance of the ITCMS. Our system model is also compared with other models to assess its performance. A comparison is made using two parameters, namely throughput and the total average delay, between the ITCMS, IOV (Internet of Vehicle), and STL (Seasonal-Trend Decomposition Procedure based on LOESS). Consequently, the results confirm that the proposed system outperforms the others in terms of higher accuracy, lower latency, and improved traffic efficiency.
Rendezvous Sequence Generation Algorithm for Cognitive Radio Networks in Post...IJCNCJournal
ย
Recent natural disasters have inflicted tremendous damage on humanity, with their scale progressively increasing and leading to numerous casualties. Events such as earthquakes can trigger secondary disasters, such as tsunamis, further complicating the situation by destroying communication infrastructures. This destruction impedes the dissemination of information about secondary disasters and complicates post-disaster rescue efforts. Consequently, there is an urgent demand for technologies capable of substituting for these destroyed communication infrastructures. This paper proposes a technique for generating rendezvous sequences to swiftly reconnect communication infrastructures in post-disaster scenarios. We compare the time required for rendezvous using the proposed technique against existing methods and analyze the average time taken to establish links with the rendezvous technique, discussing its significance. This research presents a novel approach enabling rapid recovery of destroyed communication infrastructures in disaster environments through Cognitive Radio Network (CRN) technology, showcasing the potential to significantly improve disaster response and recovery efforts. The proposed method reduces the time for the rendezvous compared to existing methods, suggesting that it can enhance the efficiency of rescue operations in post-disaster scenarios and contribute to life-saving efforts.
Vehicle Ad Hoc Networks (VANETs) have become a viable technology to improve traffic flow and safety on the roads. Due to its effectiveness and scalability, the Wingsuit Search-based Optimised Link State Routing Protocol (WS-OLSR) is frequently used for data distribution in VANETs. However, the selection of MultiPoint Relays (MPRs) plays a pivotal role in WS-OLSR's performance. This paper presents an improved MPR selection algorithm tailored to WS-OLSR, designed to enhance the overall routing efficiency and reduce overhead. The analysis found that the current OLSR protocol has problems such as redundancy of HELLO and TC message packets or failure to update routing information in time, so a WS-OLSR routing protocol based on improved-MPR selection algorithm was proposed. Firstly, factors such as node mobility and link changes are comprehensively considered to reflect network topology changes, and the broadcast cycle of node HELLO messages is controlled through topology changes. Secondly, a new MPR selection algorithm is proposed, considering link stability issues and nodes. Finally, evaluate its effectiveness in terms of packet delivery ratio, end-to-end delay, and control message overhead. Simulation results demonstrate the superior performance of our improved MR selection algorithm when compared to traditional approaches.
May 2024, Volume 16, Number 3 - The International Journal of Computer Network...IJCNCJournal
ย
The International Journal of Computer Networks & Communications (IJCNC) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Networks & Communications. The journal focuses on all technical and practical aspects of Computer Networks & data Communications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.
Vehicle Ad Hoc Networks (VANETs) have become a viable technology to improve traffic flow and safety on the roads. Due to its effectiveness and scalability, the Wingsuit Search-based Optimised Link State Routing Protocol (WS-OLSR) is frequently used for data distribution in VANETs. However, the selection of MultiPoint Relays (MPRs) plays a pivotal role in WS-OLSR's performance. This paper presents an improved MPR selection algorithm tailored to WS-OLSR, designed to enhance the overall routing efficiency and reduce overhead. The analysis found that the current OLSR protocol has problems such as redundancy of HELLO and TC message packets or failure to update routing information in time, so a WS-OLSR routing protocol based on improved-MPR selection algorithm was proposed. Firstly, factors such as node mobility and link changes are comprehensively considered to reflect network topology changes, and the broadcast cycle of node HELLO messages is controlled through topology changes. Secondly, a new MPR selection algorithm is proposed, considering link stability issues and nodes. Finally, evaluate its effectiveness in terms of packet delivery ratio, end-to-end delay, and control message overhead. Simulation results demonstrate the superior performance of our improved MR selection algorithm when compared to traditional approaches.
A Novel Medium Access Control Strategy for Heterogeneous Traffic in Wireless ...IJCNCJournal
ย
So far, Wireless Body Area Networks (WBANs) have played a pivotal role in driving the development of intelligent healthcare systems with broad applicability across various domains. Each WBAN consists of one or more types of sensors that can be embedded in clothing, attached directly to the body, or even implanted beneath an individual's skin. These sensors typically serve asingle application. However, the traffic generated by each sensor may have distinct requirements. This diversity necessitates a dual approach: tailored treatment based on the specific needs of each traffic typeand the fulfillment of application requirements, such asreliability and timeliness. Never the less, the presence of energy constraints and the unreliable nature of wireless communications make QoS provisioning under such networks a non-trivial task. In this context, the current paper introduces a novel Medium AccessControl (MAC) strategy for the regular traffic applications of WBANs, designed to significantly enhance efficiency when compared to the established MAC protocols IEEE 802.15.4 and IEEE 802.15.6, with a particular focus on improving reliability, timeliness, and energy efficiency.
May_2024 Top 10 Read Articles in Computer Networks & Communications.pdfIJCNCJournal
ย
The International Journal of Computer Networks & Communications (IJCNC) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Networks & Communications. The journal focuses on all technical and practical aspects of Computer Networks & data Communications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.
A Topology Control Algorithm Taking into Account Energy and Quality of Transm...IJCNCJournal
ย
The efficient use of energy in wireless sensor networks is critical for extending node lifetime. The network topology is one of the factors that have a significant impact on the energy usage at the nodes and the quality of transmission (QoT) in the network. We propose a topology control algorithm for software-defined wireless sensor networks (SDWSNs) in this paper. Our method is to formulate topology control algorithm as a nonlinear programming (NP) problem with the objective to optimizing two metrics, maximum communication range, and desired degree. This NP problem is solved at the SDWSN controller by employing the genetic algorithm (GA) to determine the best topology. The simulation results show that the proposed algorithm outperforms the MaxPower algorithm in terms of average node degree and energy expansion ratio.
Multi-Server user Authentication Scheme for Privacy Preservation with Fuzzy C...IJCNCJournal
ย
The integration of artificial intelligence technology with a scalable Internet of Things (IoT) platform facilitates diverse smart communication services, allowing remote users to access services from anywhere at any time. The multi-server environment within IoT introduces a flexible security service model, enabling users to interact with any server through a single registration. To ensure secure and privacy preservation services for resources, an authentication scheme is essential. Zhao et al. recently introduced a user authentication scheme for the multi-server environment, utilizing passwords and smart cards, claiming resilience against well-known attacks. This paper conducts cryptanalysis on Zhao et al.'s scheme, focusing on denial of service and privacy attacks, revealing a lack of user-friendliness. Subsequently, we propose a new multi-server user authentication scheme for privacy preservation with fuzzy commitment over the IoT environment, addressing the shortcomings of Zhao et al.'s scheme. Formal security verification of the proposed scheme is conducted using the ProVerif simulation tool. Through both formal and informal security analyses, we demonstrate that the proposed scheme is resilient against various known attacks and those identified in Zhao et al.'s scheme.
Advanced Privacy Scheme to Improve Road Safety in Smart Transportation SystemsIJCNCJournal
ย
In -Vehicle Ad-Hoc Network (VANET), vehicles continuously transmit and receive spatiotemporal data with neighboring vehicles, thereby establishing a comprehensive 360-degree traffic awareness system. Vehicular Network safety applications facilitate the transmission of messages between vehicles that are near each other, at regular intervals, enhancing drivers' contextual understanding of the driving environment and significantly improving traffic safety. Privacy schemes in VANETs are vital to safeguard vehiclesโ identities and their associated owners or drivers. Privacy schemes prevent unauthorized parties from linking the vehicle's communications to a specific real-world identity by employing techniques such as pseudonyms, randomization, or cryptographic protocols. Nevertheless, these communications frequently contain important vehicle information that malevolent groups could use to Monitor the vehicle over a long period. The acquisition of this shared data has the potential to facilitate the reconstruction of vehicle trajectories, thereby posing a potential risk to the privacy of the driver. Addressing the critical challenge of developing effective and scalable privacy-preserving protocols for communication in vehicle networks is of the highest priority. These protocols aim to reduce the transmission of confidential data while ensuring the required level of communication. This paper aims to propose an Advanced Privacy Vehicle Scheme (APV) that periodically changes pseudonyms to protect vehicle identities and improve privacy. The APV scheme utilizes a concept called the silent period, which involves changing the pseudonym of a vehicle periodically based on the tracking of neighboring vehicles. The pseudonym is a temporary identifier that vehicles use to communicate with each other in a VANET. By changing the pseudonym regularly, the APV scheme makes it difficult for unauthorized entities to link a vehicle's communications to its real-world identity. The proposed APV is compared to the SLOW, RSP, CAPS, and CPN techniques. The data indicates that the efficiency of APV is a better improvement in privacy metrics. It is evident that the AVP offers enhanced safety for vehicles during transportation in the smart city.
April 2024 - Top 10 Read Articles in Computer Networks & CommunicationsIJCNCJournal
ย
The International Journal of Computer Networks & Communications (IJCNC) is a bi monthly open access peer-reviewed journal that publishes articles which contribute new results in all areas of Computer Networks & Communications. The journal focuses on all technical and practical aspects of Computer Networks & data Communications. The goal of this journal is to bring together researchers and practitioners from academia and industry to focus on advanced networking concepts and establishing new collaborations in these areas.
DEF: Deep Ensemble Neural Network Classifier for Android Malware DetectionIJCNCJournal
ย
Malware is one of the threats to security of computer networks and information systems. Since malware instances are available sufficiently, there is increased interest among researchers on usage of Artificial Intelligence (AI). Of late AI-enabled methods such as machine learning (ML) and deep learning paved way for solving many real-world problems. As it is a learning-based approach, accumulated training samples help in improving thequality of training and thus leveraging malware detection accuracy. Existing deep learning methods are focusing on learning-based malware detection systems. However, there is need for improving the state of the art through ensemble approach. Towards this end, in this paper we proposed a framework known as Deep Ensemble Framework (DEF) for automatic malware detection. The framework obtains features from training samples. From given malware instance a grayscale image is generated. There is another process to extract the opcode sequences. Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) techniques are used to obtain grayscale image and opcode sequence respectively. Afterwards, a stacking ensemble is employed in order to achieve efficient malware detection and classification. Malware samples collected fromthe Internet sources and Microsoft are used for theempirical study. An algorithm known as Ensemble Learning for Automatic Malware Detection (EL-AML) is proposed to realize our framework. Another algorithm named Pre-Process is proposed to assist the EL-AML algorithm for obtaining intermediate features required by CNN and LSTM.Empirical study reveals that our framework outperforms many existing methods in terms of speed-up and accuracy.
High Performance NMF Based Intrusion Detection System for Big Data IOT TrafficIJCNCJournal
ย
With the emergence of smart devices and the Internet of Things (IoT), millions of users connected to the network produce massive network traffic datasets. These vast datasets of network traffic, Big Data are challenging to store, deal with and analyse using a single computer. In this paper we developed parallel implementation using a High Performance Computer (HPC) for the Non-Negative Matrix Factorization technique as an engine for an Intrusion Detection System (HPC-NMF-IDS). The large IoT traffic datasets of order of millions samples are distributed evenly on all the computing cores for both storage and speedup purpose. The distribution of computing tasks involved in the Matrix Factorization takes into account the reduction of the communication cost between the computing cores. The experiments we conducted on the proposed HPC-IDS-NMF give better results than the traditional ML-based intrusion detection systems. We could train the HPC model with datasets of one million samples in only 31 seconds instead of the 40 minutes using one processor), that is a speed up of 87 times. Moreover, we have got an excellent detection accuracy rate of 98% for KDD dataset.
A Novel Medium Access Control Strategy for Heterogeneous Traffic in Wireless ...IJCNCJournal
ย
So far, Wireless Body Area Networks (WBANs) have played a pivotal role in driving the development of intelligent healthcare systems with broad applicability across various domains. Each WBAN consists of one or more types of sensors that can be embedded in clothing, attached directly to the body, or even implanted beneath an individual's skin. These sensors typically serve asingle application. However, the traffic generated by each sensor may have distinct requirements. This diversity necessitates a dual approach: tailored treatment based on the specific needs of each traffic typeand the fulfillment of application requirements, such asreliability and timeliness. Never the less, the presence of energy constraints and the unreliable nature of wireless communications make QoS provisioning under such networks a non-trivial task. In this context, the current paper introduces a novel Medium AccessControl (MAC) strategy for the regular traffic applications of WBANs, designed to significantly enhance efficiency when compared to the established MAC protocols IEEE 802.15.4 and IEEE 802.15.6, with a particular focus on improving reliability, timeliness, and energy efficiency.
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesChristina Lin
ย
Traditionally, dealing with real-time data pipelines has involved significant overhead, even for straightforward tasks like data transformation or masking. However, in this talk, weโll venture into the dynamic realm of WebAssembly (WASM) and discover how it can revolutionize the creation of stateless streaming pipelines within a Kafka (Redpanda) broker. These pipelines are adept at managing low-latency, high-data-volume scenarios.
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
ย
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
ACEP Magazine edition 4th launched on 05.06.2024Rahul
ย
This document provides information about the third edition of the magazine "Sthapatya" published by the Association of Civil Engineers (Practicing) Aurangabad. It includes messages from current and past presidents of ACEP, memories and photos from past ACEP events, information on life time achievement awards given by ACEP, and a technical article on concrete maintenance, repairs and strengthening. The document highlights activities of ACEP and provides a technical educational article for members.
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
ย
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
ย
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Introduction- e - waste โ definition - sources of e-wasteโ hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste managementโ e-waste handling rules - waste minimization techniques for managing e-waste โ recycling of e-waste - disposal treatment methods of e- waste โ mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste โ E-waste in India- case studies.
We have compiled the most important slides from each speaker's presentation. This yearโs compilation, available for free, captures the key insights and contributions shared during the DfMAy 2024 conference.
6th International Conference on Machine Learning & Applications (CMLA 2024)ClaraZara1
ย
6th International Conference on Machine Learning & Applications (CMLA 2024) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications.
Securing BGP by Handling Dynamic Network Behavior and Unbalanced Datasets
1. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
DOI: 10.5121/ijcnc.2021.13603 41
SECURING BGP BY HANDLING
DYNAMIC NETWORK BEHAVIOR AND
UNBALANCED DATASETS
Rahul Deo Verma1
, Shefalika Ghosh Samaddar2
and A. B. Samaddar2
1
Ph.D. Scholar, Department of Computer Science and Engineering,
National Institute of Technology Sikkim, India
2
Department of Computer Science and Engineering,
National Institute of Technology Sikkim, India
ABSTRACT
The Border Gateway Protocol (BGP) provides crucial routing information for the Internet
infrastructure. A problem with abnormal routing behavior affects the stability and connectivity of
the global Internet. The biggest hurdles in detecting BGP attacks are extremely unbalanced data
set category distribution and the dynamic nature of the network. This unbalanced class
distribution and dynamic nature of the network results in the classifier's inferior performance. In
this paper we proposed an efficient approach to properly managing these problems, the proposed
approach tackles the unbalanced classification of datasets by turning the problem of binary
classification into a problem of multiclass classification. This is achieved by splitting the
majority-class samples evenly into multiple segments using Affinity Propagation, where the
number of segments is chosen so that the number of samples in any segment closely matches the
minority-class samples. Such sections of the dataset together with the minor class are then
viewed as different classes and used to train the Extreme Learning Machine (ELM). The RIPE
and BCNET datasets are used to evaluate the performance of the proposed technique. When no
feature selection is used, the proposed technique improves the F1 score by 1.9% compared to
state-of-the-art techniques. With the Fischer feature selection algorithm, the proposed algorithm
achieved the highest F1 score of 76.3%, which was a 1.7% improvement over the compared ones.
Additionally, the MIQ feature selection technique improves the accuracy by 3.5%. For the
BCNET dataset, the proposed technique improves the F1 score by 1.8% for the Fisher feature
selection technique. The experimental findings support the substantial improvement in
performance from previous approaches by the new technique.
KEYWORDS
Border Gateway Protocol (BGP), Extreme Learning Machine (ELM), Anomaly Detection.
1. INTRODUCTION
The Internet is a network without a center that is interconnected. It consists of thousands of
autonomous (AS) systems. Border Gateway Protocol (BGP) is designed and implemented for the
transmission of packets across the ASes. In BGP, the prefixes owned by each autonomous system
will be announced and routing information learned from its neighbors will be propagated
according to policy. The ASes must follow a path to the source of the prefix while propagating
the prefix and will be able to choose between different paths. However, even being a core
2. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
42
component of the Internet infrastructure, BGP consists of several serious security vulnerabilities
[1].
There are four types of messages sent over BGP: open, update, keep alive, and notification,
which is defined by metrics such as the shortest path to the nearest next-hop router, and routing
policies.While peer-to-peer messages are exchanged, a variety of events such as router
misconfigurations, session resets, and link failures can trigger BGP anomalies. Any upgrade
which does not represent a shift in the underlying BGP network or routing policy is the simplest
concept of BGP anomalies. Such irregularities undermine the efficiency and performance of the
network.
There have been numerous techniques used to detect BGP anomalies [2]. Unfortunately, these
existing anomaly detection approaches perform poorly with highly unbalanced traffic
characteristics (as malicious traffic amounts are very small compared to normal traffic), also,
these approaches do not account for the network's dynamic nature. The unbalanced distribution of
class and the dynamic nature of the network contribute to the classifier's inferior efficiency. We,
therefore, need a technique to deal with the above-mentioned issue that not only learns from such
unbalanced datasets but also preserves a margin between training samples and classifier
boundaries so that we can deal with the network's dynamic behavior. To achieve this, a classifier
based on Affinity Propagation and ELM is proposed in this work.
The proposed approach addresses the unbalanced classification of datasets by converting the
issue of binary classification into a problem of multi-class classification. Using Affinity
Propagation, the majority of class samples are clustered into multiple groups. With this, we
divide the data samples of the majority of class into multiple classes each of which contains
samples approximately equal to minority classes. Together with the minor class, these dataset
clusters are used to train the classifier Extreme Learning Machine (ELM) to handle the problem
of multiclass classification.
2. LITERATURE REVIEW
Several methods have been suggested by analyzing traffic patterns to detect anomalies. One of
the early and common methods is to develop traffic behavior models based on statistical
techniques [3, 4], identifying the anomalies as correlated abrupt changes that occur in the
underlying distribution. The downside, however, is that with all possible cases, it is difficult to
estimate the dimensional distributions. Clustering techniques [5, 6, 7] have also been suggested to
identify all regular traffic data points belonging to one cluster while anomalous data points that
belong to multiple clusters. Clustering techniques have the main disadvantage of being optimized
to detect regular traffic, which is not the goal of detection methods. An alternative widely used
approach is the rule-based technique [8, 9, 10], which builds classifiers based on specific rules.
The downside is that a priori knowledge and a high degree of computations are required. Several
machine learning techniques have been used to create traffic classification models [11, 12, 13, 14,
15, 16] to identify anomalies for both unsupervised and supervised machine learning models.
Despite the ability of neural networks to detect the complex relationship between features, they
have many disadvantages such as high computational complexity and high probability of
overfitting. Support vector machine (SVM) techniques use nonlinear classification functions to
identify anomaly patterns in data and classify that data point based on the value obtained by the
classifier function. SVMs build a classification model that maximizes the difference between
each class's data points. Several variants of SVM detection techniques are introduced and
evaluated [17], but due to the quadratic optimization problem that needs to be solved, they have
high computational complexity. Finally, due to their low time complexity, Bayesian networks
(BN) techniques [18] are used in many real-time classification systems. BNs rely on two
3. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
43
hypotheses: features are conditionally independent given a target category and the resulting
likelihood is the criterion for classification between any two data points. Variants of BNs have
been introduced by several anomaly detection schemes [19, 20]. Most of the models described
here are not intended for sequence classification and are not appropriate for time series anomaly
detection, where only input instances are handled separately without taking into account the
sequenced existence of traffic data. In fact, traffic data are multivariate time series and the
patterns of the anomaly are gradually varying with time information. In [21], an ELM-based
intrusion detection approach is presented that addresses the class imbalance problem. The results
of the experiments show that the ELM outperforms the SVM. Knowing that, an ELM has the
advantage of faster computation for both training and testing, the ELM emerges as a promising
technique for classification problems. However, selecting the correct number of hidden nodes in
an ELM is still a difficult task.
3. APPROACH
In the section, the details of Affinity Propagation and Extreme Learning Machine (ELM) are
presented. Clustering algorithms such as affinity propagation are often used for unsupervised
learning, while feedforward neural networks such as ELM use multiple layers of hidden nodes
with no need to tune their parameters.
3.1. Affinity Propagation (AP)
The propagation of affinity (AP) has been suggested as a new and powerful exemplary learning
technique. In short, the user must provide a complete matrix of similarities between the input data
points as the initial input to the algorithm (for the selected metric(s)). First of all, all data points
are seen as potential examples. As soon as information messages (i.e. responsibility and
availability) are transmitted along the network edge (each data point acts as a node), identifying
possible examples and clusters [23].
In the following sections, we explain the AP mathematical model in brief. AP starts with a set of
real-valued similarities between data points as input. Given a ๐ data pointโs dataset, ๐ฅ๐ and ๐ฅ๐
are two objects in it. The similarity ๐ (๐, ๐) indicates how well ๐ฅ๐ is suited to be the exemplar
for๐ฅ๐. For instance, it can be initialized to ๐ (๐, ๐) = โโ๐ฅ๐ โ ๐ฅ๐โ
2
, ๐ โ ๐. In [22], if no heuristic
knowledge is present, self-similarities are referred to as preferences and are often inferred as
constants. For instance, they could be set as:
๐ (๐, ๐) =
โ ๐ (๐, ๐)
๐
๐,๐=1;๐โ๐
๐ ร (๐ โ 1)
, 1 โค ๐ โค ๐ (1)
Then, the AP method computes two types of messages which are then exchanged between data
points. The first one identifies a "responsibility" ๐(๐, ๐) that is sent from the ๐ to the ๐, a good
indication of whether point ๐ serves as a suitable exemplar for ๐. In the second message, called
"availability" ๐(๐, ๐), candidate exemplar point ๐ transmits his or her availability to point ๐ and
tells point ๐ the accumulated evidence to determine whether or not point ๐ should accept point ๐ as
its exemplar. The availabilities are initially set to zero, ๐(๐, ๐) = 0. The update equations for
๐(๐, ๐) and ๐(๐, ๐) are written as:
๐ ๐(๐, ๐) = ๐ (๐, ๐) โ ๐๐๐ฅ
๐โ ๐
{๐(๐, ๐โฒ
) + ๐ (๐, ๐โฒ
)} (2)
4. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
44
{
๐๐๐ {0, ๐(๐, ๐) + โ max{0, ๐(๐, ๐)}
๐โ ๐,๐
} ๐ โ ๐
โ max{0, ๐(๐, ๐)}
๐โ ๐
๐ = ๐
(3)
To prevent numerical oscillations due to the exchange of messages between data points, a
damping factor of ๐ = [0,1 ] is also applied:
๐ ๐ก+1 = (1 โ ๐)๐ ๐ก + ๐๐ ๐กโ1
๐ด๐ก+1 = (1 โ ๐)๐ด๐ก + ๐๐ด๐กโ1
(4)
Where, ๐ = ๐(๐, ๐) and ๐ด = (๐, ๐) represent the matrix of responsibility and the matrix of
availability respectively; ๐ก indicates the time of iteration. For several iterations, the above two
messages will be modified iteratively until they exceed certain specified values or the local
decisions remain constant. At this point, it is then possible to combine availabilities and
responsibilities to define exemplars:
๐๐ โ arg ๐๐๐ฅ
1โค๐โค๐
[๐(๐, ๐) + ๐(๐, ๐)] (5)
Affinity Propagation Algorithm
Input: a set of pairwise similarities, {๐ (๐, ๐)}(๐,๐)โ{1,2,โฆ,๐}2,๐โ ๐where ๐ (๐, ๐) โ โ indicates the suitability of data point ๐ as an
exemplar for data point ๐, and is calculated as:
๐ (๐, ๐) = โโ๐ฅ๐ โ ๐ฅ๐โ2
, ๐ โ ๐,
There is a real number s (k, k) for each point; this real number indicates that this point is preferred a priori (a cluster is a small cost
to add).
๐ (๐, ๐) = ๐ โ๐ โ {1, โฆ , ๐}
Initialization: set availabilities to zero โ๐, ๐: ๐(๐, ๐) = 0.
Repeat: update๐ (๐, ๐), and ๐(๐, ๐) until convergence achieved
โ๐, ๐: ๐(๐, ๐) = ๐ (๐, ๐) โ max
๐โฒ,๐โฒโ ๐
[๐ (๐, ๐โฒ) + ๐(๐, ๐โฒ
)]
โ๐, ๐: ๐(๐, ๐) =
{
โ max[0, ๐(๐โฒ
, ๐)]
๐โฒ,๐โฒโ ๐
,๐๐๐ ๐ = ๐
min [0, ๐(๐, ๐) + โ ๐๐๐ฅ[0, ๐(๐โฒ
, ๐)]
๐โฒ,๐โฒโ ๐
] ,๐๐๐ ๐ โ ๐
Output: assignments๐ฬ = (๐ฬ1, ๐ฬ2, โฆ , ๐ฬ๐), where ๐ฬ๐ = ๐๐๐๐๐๐ฅ๐ [๐(๐, ๐) + ๐(๐, ๐)] and ๐ฬ๐ indexes the clusterโs exemplar to which
point ๐ is assigned.
Several comprehensive analyzes of the AP method are performed ([23], [24]) for different scale
datasets. A comparison of Affinity Propagation clustering with standard approaches (like p-
median analysis and vertex heuristic substitution) shows that there are only minor differences for
both precision and speed on small datasets. For large datasets, however, AP offers notable
benefits over existing methods [22, 24].
3.2. Extreme Learning Machine
An emerging algorithm in machine learning is called the Extreme Learning Machine (ELM) [25].
It is based on a single hidden layer feedforward neural network (SLFN), which trains quickly and
provides performance similar to support vector machines (SVMs) [26]. ELM is a standard three-
5. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
45
layer feedforward design that was introduced in 2006 [27]. The model contains two layers: an
input layer and a hidden layer (the sigmoid nonlinear neurons) projecting the input layer onto
higher dimensions. The final layer serves as the output and is made up of linear input-output
neurons. Fig. 1 shows the ELM structure.
๐ฆ(๐) = โ ๐ฝ๐๐ (โ ๐ค๐,๐๐ฅ๐ + ๐๐
๐
๐=1
)
๐
๐=1
(6)
Here, ๐ฝ๐ and ๐ฝ๐ represents the weights between the hidden layer and the input layer, and the
output layer and the hidden layer respectively. The hidden layer neuron threshold value ๐๐ and its
activation function ๐(. ). Weights of the same input layer (๐ค๐,๐) and bias (๐๐) are assigned
randomly. In the beginning, the network is initialized by allocating the input layer neuron number
(๐) and hidden layer neuron number (๐), and the activation function (๐(. )). Now, based on this
information, by combining and rearranging the parameters known in equilibrium, the output layer
becomes as in equation (8) [28].
๐ป(๐ค๐,๐, ๐๐, ๐ฅ๐) = [
๐(๐ค1,1๐ฅ1 + ๐1) โฏ ๐(๐ค1,๐๐ฅ๐ + ๐๐)
โฎ โฑ โฎ
๐(๐ค๐,1๐ฅ๐ + ๐1) โฏ ๐(๐ค๐,๐๐ฅ๐ + ๐๐)
]
(7)
๐ฆ = ๐ป๐ฝ (8)
Like all training algorithm models, the objective should be to minimize errors as much as
possible. The output ๐ฆ๐ error function obtained from the real output value ๐ฆ๐ in ELM is โ (๐ฆ๐ โ
๐
๐
๐ฆ๐)(with "s": training data number) and โโ (๐ฆ๐ โ ๐ฆ๐)
2
๐
๐ โ can be minimized. The output ๐ฆ๐
obtained from the actual output value ๐ฆ๐ must be equal to ๐ฆ๐ for both of these functions. If this
occurs, the unknown parameter in equation (8) will be a very low probability matrix (๐ป). It
Figure 1. Feed-forward neural network with a single hidden layer in an ELM structure.
6. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
46
means that there will never be the same number of samples in the training set as there are features
in each sample.Therefore, it will be a challenge to take the inverse of ๐ป and to find weights (๐).
To overcome this situation, the pseudo-inverse of the matrix ๐ป can be taken by using Moore-
Penrose Inverse. The output weights can therefore be found through ๐ฝ = ๐ฆ ร ๐๐๐ผ(๐ป).
3.3. Experimental Datasets
BGP raw data are collected from AS513 (RIPE RIS, rcc04, CIXP, Geneva) during worm attacks
like Slammer [29], Nimda [30], and Code Red I [31]. for the same duration, we downloaded the
standard BGP datasets from RIPE NCC [32] and the BCNET Network Operations Center [33]
from Vancouver, Canada. To convert MRT [34] to ASCII format, the libBGPdump tool [35] is
used. Based on the tools written in C #, we parse the ASCII file and extract 37 features sampled
in five days each minute, generating 7,200 samples for each anomaly case.
Filtered collected traffic data for BGP update messages during the intervals when the internet
experienced BGP anomalies is provided in [36]. Three anomalous traffic events and two regular
traffic events, described in this paper, are listed in Table 1.
Table 1. Details of BGP datasets [36]
Dataset Class Date Duration
(h)
Training set
data points
Testing set
data points
Slammer Anomaly January 25, 2003 16 3212:4080 1:3211,
4081:7200
Nimda Anomaly September 18, 2001 59 3680:7200 1:3679
Code Red I Anomaly July 19, 2001 10 3681:4280 1:3680,
4281:7200
RIPE Regular July 14, 2001 24 None 1:1440
BCNET Regular December 20, 2011 24 None 1:1440
3.4. Features Analysis
Information and characteristics influence the model's classification output and determine the
machine learning upper limit. The BGP raw data is used to generate 37 features set with obvious
physical or statistical meaning. The feature set is obtained through the extraction process
described in [37], and their values are calculated in one-minute intervals, which produces 7200
samples for each anomaly condition. The details of these features are presented in [36], these
features are divided into three types (Continuous, Categorical, and Binary), and grouped into two
categories named volume (how many BGP announcements are made) and AS-path (the
maximum edit distance between the two ASs). For the complete details of the features set please
refer to [36], as in this work the similar features set properties are adopted.
3.5. Feature selection
The feature vectorโs high dimensionality due to non-informative features is considered
unnecessary because it increases computational complexity and the use of memory [38]. It also
leads to poor accuracy in classification. To decrease dimensionality, it is appropriate to choose
the most relevant subset of the original set of features. A Fisher [39, 40] and a minimal
Redundancy Maximum Relevance (mRMR) [41] algorithm were used to identify the most
significant features.
7. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
47
Table 2. Top 10 selected features by different algorithms
Fisher MID MIQ MIBASE
Selected
features
highest
score
(top)
to
lowest
score
(bottom) 11 34 34 34
6 32 2 36
25 33 8 2
9 2 24 8
2 31 9 9
36 24 14 3
37 8 1 1
24 14 36 6
8 30 3 12
14 22 25 11
To select the top ten features, we use three variants of the mRMR algorithm: Mutual Information
Difference (MID), Mutual Information Quotient (MIQ), and Mutual Information Base
(MIBASE). These selected features according to the feature selection algorithm are presented in
Table 2.
3.6. Proposed Methodology
The proposed BGP anomaly detection model is shown in Fig. 2. Classification involves
categorizing test labels into predefined categories. In this work, four different classes Slammer,
Nimda, Code Red, and Regular are defined as presented in Table 1. The steps of the classification
process for the proposed model are shown in Fig. 2. Initially, raw data is processed to extract
features and labels. The datasets are sorted by affinity propagation clustering into multiple groups
and divided into two sets of training data and testing data, as shown in Fig. 2. In the training
stage, the training set which consists set of predefined features and respective labels is used to
train the extreme learning machine (ELM). The trained ELM is used as an anomaly detector on
the test dataset. In the testing stage, the testing dataset is applied to the trained ELM model to
generate classification labels. At the end of the process, a set of labels generated from the testing
step is compared with the original labels from the testing step to evaluate the performance of the
proposed model.
Figure 2. Proposed Classification Process
8. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
48
4. PERFORMANCE EVALUATION METRICS
The classifier is evaluated based on four common measures known as accuracy (Eq. 10),
precision (Eq. 11), recall (Eq. 12), and F1 (Eq. 9) to estimate the efficiency of the methods.
Accuracy determines the predictive ability of the classifier for normal and anomaly assessments.
Accuracy defines the predicted accuracy of the label. Recall determines the completeness of the
category. F1 is a dimensionless measure of precision and recall that can be used to balance
accuracy and recall.
๐น = 2 โ
๐๐๐๐๐๐ ๐๐๐ โ ๐ ๐๐๐๐๐
๐๐๐๐๐๐ ๐๐๐ + ๐ ๐๐๐๐๐
(9)
๐ด๐๐๐ข๐๐๐๐ฆ =
|๐๐ + ๐๐|
|๐๐ + ๐๐ + ๐น๐ + ๐น๐ |
(10)
๐๐๐๐๐๐ ๐๐๐ =
|๐๐|
|๐๐ + ๐น๐ |
(11)
๐ ๐๐๐๐๐ =
|๐๐|
|๐๐ + ๐น๐|
(12)
Where, ๐๐, ๐๐, are denoting the true positive, true negative, while ๐น๐, ๐น๐ are denoting the false
positive and false negative. These terms can be defined as:
๏ท TP: The number of anomalous instances classifier correctly identified as an anomaly.
๏ท TN: The number of normal instances classifier correctly identified as normal.
๏ท FP: The number of normal instances classifier incorrectly identified as an anomaly.
๏ท FN: The number of anomalous instances classifier incorrectly identified as normal.
These can also be defined by the confusion matrix.
Table 3. Confusion Matrix
Known Labels
True (Anomaly) False (Normal)
Classifierโs identification
result
Positive (Anomaly) TP FP
Negative (Normal) FN TN
5. RESULTS ANALYSIS
Table 4 shows the performance comparison of previous methods (SVM (Support Vector
Machine), HMM (Hidden Markov Model) and, NB (Naรฏve Bayes)) with the proposed method.
For the RIPE dataset when compared to previous methods, the proposed approach delivers better
accuracy for MID and MIQ-based features. For MID-based features, it provides 75.3% accuracy
which is 0.4% higher than the 74.9 the previous best provided by HMM. For MIQ-based features,
we get 74.8% which is 3.5% higher than the previous best 71.3% provided by SVM. When
comparing in terms of F1 score the proposed classifier works better for all features set except for
the MIBASE. Since the F1 score presents the combined information of Precision and Recall the
higher value of it even when the Accuracy measure is lesser shows the better classifier
performance.
9. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
49
For the BCNET dataset when compared to previous methods, the proposed approach delivers
better accuracy for MID-based features and gives 80.6% accuracy which is 1.7% higher than the
78.9 the previous best provided by HMM. When comparing in terms of F1 score the proposed
classifier works better for the Fisher and MID feature set.
Table 4. Performance Comparison
Dataset
Feature
Set
Accuracy (%) F1 (%)
SVM HMM NB Proposed SVM HMM NB Proposed
RIPE 1-37 77.1 81.3 74.3 79.1 71.2 70.7 64.3 73.1
RIPE Fisher 82.8 79.2 24.7 81.7 74.6 69.3 24.1 76.3
RIPE MID 67.8 60.6 74.9 75.3 56.3 50.5 65.3 70.6
RIPE MIQ 71.3 68.2 24.6 74.8 55.1 48.2 22.7 69.5
RIPE MIBASE 72.8 74.8 75.4 71.2 68.9 67.7 60.5 63.4
BCNET 1-37 91.4 86.6 67.6 85.5 74.4 75.1 56.8 71.8
BCNET Fisher 85.7 81.3 34.3 84.2 73.8 74.8 25.1 76.6
BCNET MID 78.7 78.9 33.1 80.6 71.3 73.3 22.1 73.3
BCNET MIQ 89.1 81.1 34.8 86.3 75.6 72.8 24.9 76.7
BCNET MIBASE 90.2 81.4 33.1 87.8 75.4 71.5 21.8 75.1
The proposed algorithm gives an average 80.65% accuracy for all datasets with a standard
deviation of 5.52%, whereas SVM provides 80.69% accuracy however with an 8.42% standard
deviation. When analyzed for the F1 scores the proposed method gives a higher average F1 score
of 72.64% with only 4.11% of standard deviation in comparison to the second-best SVM which
provides 69.66% average accuracy with a 7.66% standard deviation. This validates that the
proposed method gives much uniform performance for all the five features set in terms of
accuracy and F1 score.
Looking at the performance of different feature selection algorithms Fisher provides better
average accuracy of 77.95% with a 2.9% of standard deviation for the RIPE dataset however for
the BCNET dataset MIBASE gives better accuracy of 73.12% with 26.94% of standard deviation
for the BCNET dataset. For the F1 score, the Fisher feature selection algorithm gives better
performance for both the datasets and achieves an average of 69.82% and 62.57% respectively.
(a)
(b)
10. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
50
Figure 3. Mean and standard deviation of (a) Accuracy, and (b) F1 Score, of different classification
techniques for the RIPE+BCNET dataset
(a) (b)
Figure 4. Mean and standard deviation in (a) Accuracy, and (b) F1 Score, of different feature selection
techniques for only the RIPE dataset
(a) (b)
Figure 5. Mean and standard deviation in (a) Accuracy, and (b) F1 Score, of different feature selection
techniques for only the BCNET dataset
6. CONCLUSION
In this paper, we presented an Affinity Propagation and Extreme Learning Machine (ELM) based
approach for anomaly detection in the BGP network. Affinity Propagation-based clustering used
the datasets processing phase, while ELM during the classification phase. Finally, the
performance of the proposed algorithm is evaluated with two different datasets named RIPE and
BCNET with four different feature selection algorithms. The experimental results reveal that the
proposed algorithm performs better than SVM, HMM, and NB algorithms and provides much
stable performance throughout the datasets and feature selection algorithms. The experimental
results show that for both datasets and balanced and non-balanced class distributions, the
proposed algorithm provides significantly improved performance over previous algorithms.
Although the proposed algorithm performs better than compared algorithms, the algorithm may
require several repetitions to get the best solution. This happens because with AP it is difficult to
get the optimal parameter values, also AP may involve oscillations. In the future, these
limitations may be addressed using enhanced versions of the AP algorithm.
CONFLICTS OF INTEREST
The authors declare no conflict of interest.
11. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
51
REFERENCES
[1] S. Murphy, โBGP security vulnerabilities analysis,โ Tech. Rep., 2005.
[2] Al-Musawi B, Branch P, Armitage G. BGP anomaly detection techniques: a survey. IEEE
CommunSurv Tut 2017; 19: 377-396.
[3] Chandola V, Banerjee A, Kumar V. Anomaly detection: a survey. ACM ComputSurv 2009; 41: 1-58.
[4] Hajji H. Statistical analysis of network traffic for adaptive faults detection. IEEE T Neural Networ
2005; 16: 1053-1063.
[5] Thottan M, Liu G. Anomaly detection approaches for communication networks. In: Cormode G,
Thottan M, editors. Algorithms for Next Generation Networks. London, UK: Springer, 2010. pp. 239-
261.
[6] Wang, Bingming, Shi Ying, Guoli Cheng, Rui Wang, Zhe Yang, and Bo Dong. "Log-based anomaly
detection with the improved K-nearest neighbor." International Journal of Software Engineering and
Knowledge Engineering 30, no. 02 (2020): 239-262.
[7] Putina, Andrian, and Dario Rossi. "Online anomaly detection leveraging stream-based clustering and
real-time telemetry." IEEE Transactions on Network and Service Management (2020).
[8] Tan P, Steinbach M, Kumar V. Introduction to Data Mining. 1st ed. Boston, MA, USA: Addison-
Wesley, 2005.
[9] Protogerou, Aikaterini, Stavros Papadopoulos, Anastasios Drosou, Dimitrios Tzovaras, and Ioannis
Refanidis. "A graph neural network method for distributed anomaly detection in IoT." Evolving
Systems (2020): 1-18.
[10] Li, Huichun, Chengli Zhao, Yangyang Liu, and Xue Zhang. "Anomaly detection by discovering
bipartite structure on complex networks." Computer Networks (2021): 107899.
[11] Augusteijn M, Folkert B. Neural network classification and novelty detection. Int J Remote Sens
2002; 23: 2891-2902.
[12] Diaz I, Hollmen J. Residual generation and visualization for understanding novel process conditions.
In: IEEE IJCNNโ02 Neural Networks Conference; 12โ17 May 2002; Honolulu, HI, USA. New York,
NY, USA: IEEE. pp. 2070-2075.
[13] Xu, Mengying, and Xing Li. "BGP Anomaly Detection Based on Automatic Feature Extraction by
Neural Network." In 2020 IEEE 5th Information Technology and Mechatronics Engineering
Conference (ITOEC), pp. 46-50. IEEE, 2020.
[14] Takhar, Hardeep Kaur. "Machine Learning Techniques for Detecting BGP Anomalies." PhD diss.,
SIMON FRASER UNIVERSITY, 2020.
[15] Al-Akhras, Mousa, Mohammed Alawairdhi, Ali Alkoudari, and Samer Atawneh. "Using machine
learning to build a classification model for iot networks to detect attack signatures."
(2020).International journal of Computer Networks & Communications. 12. 99-116. 10.5121.
[16] Hai, Tran Hoang, and Eui nam Huh. "Network Anomaly Detection Based On Late Fusion Of Several
Machine Learning Algorithms." International Journal of Computer Networks and
Communications 12, no. 6 (2020): 117-131.
[17] Sharma O, Girolami M, Sventek J. Detecting worm variants using machine learning. In: Proceedings
of CoNEXT Conference; 10โ13 December 2007; New York, NY, USA. New York, NY, USA: ACM.
pp. 1-12.
[18] Gray, Caitlin, Clemens Mosig, Randy Bush, Cristel Pelsser, Matthew Roughan, Thomas C. Schmidt,
and Matthias Wahlisch. "BGP Beacons, Network Tomography, and Bayesian Computation to Locate
Route Flap Damping." In Proceedings of the ACM Internet Measurement Conference, pp. 492-505.
2020.
[19] Moore A, Zuev D. Internet traffic classification using Bayesian analysis techniques. In: Proceedings
Conference on Measurement and Modeling of Computer Systems; 6โ10 June 2005; Alberta, Canada.
New York, NY, USA: ACM. pp. 50-60.
[20] El-Arini K, Killourhy K. Bayesian detection of router configuration anomalies. In: Proceedings of
Workshop on Mining Network Data; 26 August 2005; Philadelphia, PA, USA. New York, NY, USA:
ACM. pp.221-222.
[21] Awad, Mohammed, and AlaeddinAlabdallah. "Addressing Imbalanced Classes Problem of Intrusion
Detection System Using Weighted Extreme Learning Machine." International Journal of Computer
Networks & Communications (IJCNC) Vol 11 (2019).
[22] Dueck, Delbert. Affinity propagation: clustering data by passing messages. Toronto: University of
Toronto, 2009.
12. International Journal of Computer Networks & Communications (IJCNC) Vol.13, No.6, November 2021
52
[23] Taneja, Shweta, Bhawna Suri, Himanshu Narwal, Anchit Jain, Akshay Kathuria, and Sachin Gupta.
"A new approach for data classification using Fuzzy logic." In Cloud System and Big Data
Engineering (Confluence), 2016 6th International Conference, pp. 22-27. IEEE, 2016.
[24] Song, Qinbao, Jingjie Ni, and Guangtao Wang. "A fast clustering-based feature subset selection
algorithm for high-dimensional data." IEEE transactions on knowledge and data engineering 25, no. 1
(2013): 1-14.
[25] Huang, G.-B., Wang, D.H., Lan, Y.: Extreme Learning Machines: A Survey. International Journal of
Machine Learning and Cybernetics 2, 107โ122 (2011).
[26] Tapson, J., van Schaik, A.: Learning the pseudoinverse solution to network weights. Neural Networks
45, 94โ100 (2013).
[27] Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme Learning Machine: Theory and applications.
Neurocomputing 70, 489โ501 (2006).
[28] Toprak, Abdullah. "Extreme Learning Machine (ELM)-Based Classification of Benign and Malignant
Cells in Breast Cancer." Medical science monitor: international medical journal of experimental and
clinical research 24 (2018): 6537.
[29] D. Moore, V. Paxson, and S. Savage. Inside the slammer worm [J]. IEEE Security & Privacy, 2003,
99(4): 33-39.
[30] A. Machie, J. Roculan, and R. Russellu. Nimda worm analysis[R]. Tech. Rep., Incident Analysis,
Security Focus, 2001.
[31] D. Moore, and C. Shannon. Code-Red: a case study on the spread and victims of an Internet
worm[C]//Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurement. ACM,
2002: 273-284.
[32] RIPE NCC [Online]. Available: http://www.routeviews.org/. Accessed: Feb. 28, 2018
[33] S. Lally, T. Farah, and R. Gill. Collection and characterization of BCNET BGP traffic.
Communications, Computers and Signal Processing (PacRim), 2011 IEEE Pacific Rim Conference
on. IEEE, 2011: 830-835.
[34] libBGPdump.[Online]. Available: http://bitbucket.org/ripencc wiki/Home. Accessed: Sep. 17, 2018
[35] T. Manderson. Multi-threaded routing toolkit (MRT) border gateway protocol (BGP) routing
information export format with geo-location extensions. RFC 6397, IETF, Oct. 2011 [Online].
Available: https://tools.ietf.org/html/rfc6397.txt
[36] Al-Rousan, Nabil M., and Ljiljana Trajkoviฤ. "Machine learning models for classification of BGP
anomalies." In 2012 IEEE 13th International Conference on High Performance Switching and
Routing, pp. 103-108. IEEE, 2012.
[37] N. Al-Rousan, and Lj. Trajkovic. Machine learning models for classification of BGP anomalies.
IEEE, International Conference on High Performance Switching and Routing. IEEE, 2013:103-108.
[38] P. Winter, E. Hermann, and M. Zeilinger, Inductive intrusion detection in flow-based network data
using one-class support vector machines," in New Technologies, Mobility and Security (NTMS),
2011 4th IFIP Int. Conf., Paris, France, Feb. 2011, pp. 1-5.
[39] Y.-W. Chen and C.-J. Lin, Combining SVMs with various feature selection strategies," in Feature
Extraction: Foundations and Applications, London, Springer, June 2006, pp. 317-328.
[40] Q. Gu, Z. Li, and J. Han, Generalized fisher score for feature selection," in Proc. Conf. on
Uncertainty in Artificial Intelligence, Barcelona, Spain, July 2011, pp. 266-273.
[41] H. Peng, F. Long, and C. Ding, Feature selection based on mutual information criteria of max-
dependency, max-relevance, and min-redundancy," IEEE Trans. Pattern Analysis and Machine
Intelligence, vol. 27, no. 8, pp. 1226{1238, Aug. 2005.