A neural filtering technique is proposed in this paper for restoring the images extremely corrupted with random valued impulse noise. The proposed intelligent filter is carried out in two stages. In first stage the corrupted image is filtered by applying an asymmetric trimmed median filter. An asymmetric trimmed median filtered output image is suitably combined with a feed forward neural network in the second stage. The internal parameters of the feed forward neural network are adaptively optimized by training of three well known images. This is quite effective in eliminating random valued impulse noise. Simulation results show that the proposed filter is superior in terms of eliminating impulse noise as well as preserving edges and fine details of digital images and results are compared with other existing nonlinear filters.
Comparison of Learning Algorithms for Handwritten Digit RecognitionSafaa Alnabulsi
A 20 minutes seminar where I explained the performance of different classifiers in the Handwritten Digit Recognition problem.
The paper: http://yann.lecun.com/exdb/publis/pdf/lecun-95b.pdf
This is a presentation on Handwritten Digit Recognition using Convolutional Neural Networks. Convolutional Neural Networks give better results as compared to conventional Artificial Neural Networks.
The main objective of this paper is to recognize and predict handwritten digits from 0 to 9 where data set of 5000 examples of MNIST was given as input. As we know as every person has different style of writing digits humans can recognize easily but for computers it is comparatively a difficult task so here we have used neural network approach where in the machine will learn on itself by gaining experiences and the accuracy will increase based upon the experience it gains. The dataset was trained using feed forward neural network algorithm. The overall system accuracy obtained was 95.7% Jyoti Shinde | Chaitali Rajput | Prof. Mrunal Shidore | Prof. Milind Rane"Handwritten Digit Recognition" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-2 , February 2018, URL: http://www.ijtsrd.com/papers/ijtsrd8384.pdf http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/8384/handwritten-digit-recognition/jyoti-shinde
Comparison of Learning Algorithms for Handwritten Digit RecognitionSafaa Alnabulsi
A 20 minutes seminar where I explained the performance of different classifiers in the Handwritten Digit Recognition problem.
The paper: http://yann.lecun.com/exdb/publis/pdf/lecun-95b.pdf
This is a presentation on Handwritten Digit Recognition using Convolutional Neural Networks. Convolutional Neural Networks give better results as compared to conventional Artificial Neural Networks.
The main objective of this paper is to recognize and predict handwritten digits from 0 to 9 where data set of 5000 examples of MNIST was given as input. As we know as every person has different style of writing digits humans can recognize easily but for computers it is comparatively a difficult task so here we have used neural network approach where in the machine will learn on itself by gaining experiences and the accuracy will increase based upon the experience it gains. The dataset was trained using feed forward neural network algorithm. The overall system accuracy obtained was 95.7% Jyoti Shinde | Chaitali Rajput | Prof. Mrunal Shidore | Prof. Milind Rane"Handwritten Digit Recognition" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-2 , February 2018, URL: http://www.ijtsrd.com/papers/ijtsrd8384.pdf http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/8384/handwritten-digit-recognition/jyoti-shinde
final Year Projects, Final Year Projects in Chennai, Software Projects, Embedded Projects, Microcontrollers Projects, DSP Projects, VLSI Projects, Matlab Projects, Java Projects, .NET Projects, IEEE Projects, IEEE 2009 Projects, IEEE 2009 Projects, Software, IEEE 2009 Projects, Embedded, Software IEEE 2009 Projects, Embedded IEEE 2009 Projects, Final Year Project Titles, Final Year Project Reports, Final Year Project Review, Robotics Projects, Mechanical Projects, Electrical Projects, Power Electronics Projects, Power System Projects, Model Projects, Java Projects, J2EE Projects, Engineering Projects, Student Projects, Engineering College Projects, MCA Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, Wireless Networks Projects, Network Security Projects, Networking Projects, final year projects, ieee projects, student projects, college projects, ieee projects in chennai, java projects, software ieee projects, embedded ieee projects, "ieee2009projects", "final year projects", "ieee projects", "Engineering Projects", "Final Year Projects in Chennai", "Final year Projects at Chennai", Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, Final Year Java Projects, Final Year ASP.NET Projects, Final Year VB.NET Projects, Final Year C# Projects, Final Year Visual C++ Projects, Final Year Matlab Projects, Final Year NS2 Projects, Final Year C Projects, Final Year Microcontroller Projects, Final Year ATMEL Projects, Final Year PIC Projects, Final Year ARM Projects, Final Year DSP Projects, Final Year VLSI Projects, Final Year FPGA Projects, Final Year CPLD Projects, Final Year Power Electronics Projects, Final Year Electrical Projects, Final Year Robotics Projects, Final Year Solor Projects, Final Year MEMS Projects, Final Year J2EE Projects, Final Year J2ME Projects, Final Year AJAX Projects, Final Year Structs Projects, Final Year EJB Projects, Final Year Real Time Projects, Final Year Live Projects, Final Year Student Projects, Final Year Engineering Projects, Final Year MCA Projects, Final Year MBA Projects, Final Year College Projects, Final Year BE Projects, Final Year BTech Projects, Final Year ME Projects, Final Year MTech Projects, Final Year M.Sc Projects, IEEE Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, IEEE 2009 Java Projects, IEEE 2009 ASP.NET Projects, IEEE 2009 VB.NET Projects, IEEE 2009 C# Projects, IEEE 2009 Visual C++ Projects, IEEE 2009 Matlab Projects, IEEE 2009 NS2 Projects, IEEE 2009 C Projects, IEEE 2009 Microcontroller Projects, IEEE 2009 ATMEL Projects, IEEE 2009 PIC Projects, IEEE 2009 ARM Projects, IEEE 2009 DSP Projects, IEEE 2009 VLSI Projects, IEEE 2009 FPGA Projects, IEEE 2009 CPLD Projects, IEEE 2009 Power Electronics Projects, IEEE 2009 Electrical Projects, IEEE 2009 Robotics Projects, IEEE 2009 Solor Projects, IEEE 2009 MEMS Projects, IEEE 2009 J2EE P
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESVikash Kumar
IMAGE CLASSIFICATION USING KNN, RANDOM FOREST AND SVM ALGORITHM ON GLAUCOMA DATASETS AND EXPLAIN THE ACCURACY, SENSITIVITY, AND SPECIFICITY OF EACH AND EVERY ALGORITHMS
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
With the increase in Internet users the number of malicious users are also growing day-by-day posing a
serious problem in distinguishing between normal and abnormal behavior of users in the network. This
has led to the research area of intrusion detection which essentially analyzes the network traffic and tries
to determine normal and abnormal patterns of behavior.In this paper, we have analyzed the standard
NSL-KDD intrusion dataset using some neural network based techniques for predicting possible
intrusions. Four most effective classification methods, namely, Radial Basis Function Network, Self-
Organizing Map, Sequential Minimal Optimization, and Projective Adaptive Resonance Theory have been
applied. In order to enhance the performance of the classifiers, three entropy based feature selection
methods have been applied as preprocessing of data. Performances of different combinations of classifiers
and attribute reduction methods have also been compared.
Artificial neural network for machine learninggrinu
An Artificial Neurol Network (ANN) is a computational model. It is based on the structure and functions of biological neural networks. It works like the way human brain processes information. ANN includes a large number of connected processing units that work together to process information. They also generate meaningful results from it.
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...Jinwon Lee
TensorFlow Korea 논문읽기모임 PR12 258번째 논문 review입니다.
이번 논문은 MIT에서 나온 From ImageNet to Image Classification: Contextualizing Progress on Benchmarks입니다.
Deep Learning 하시는 분들이면 ImageNet 모르시는 분들이 없을텐데요, 이 논문은 ImageNet의 labeling 방법의 한계와 문제점에 대해서 얘기하고 top-1 accuracy 기반의 평가 방법에도 문제가 있을 수 있음을 지적하고 있습니다.
ImageNet data의 20% 이상이 multi object를 포함하고 있지만 그 중에 하나만 정답으로 인정되는 문제가 있고, annotation 방법의 한계로 인하여 실제로 사람이 생각하는 것과 다른 class가 정답으로 labeling되어 있는 경우도 많았습니다. 또한 terrier만 20종이 넘는 등 전문가가 아니면 판단하기 어려운 label도 많다는 문제도 있었구요. 이 밖에도 다양한 실험을 통해서 정량적인 분석과 함께 human-in-the-loop을 이용한 평가로 현재 model들의 성능이 어디까지 와있는지, 그리고 앞으로 더 높은 성능을 내기 위해서 data labeling 측면에서 해결해야할 과제는 무엇인지에 대해서 이야기하고 있습니다. 논문이 양이 좀 많긴 하지만 기술적인 내용이 별로 없어서 쉽게 읽으실 수 있는데요, 자세한 내용이 궁금하신 분들은 영상을 참고해주세요!
논문링크: https://arxiv.org/abs/2005.11295
발표영상링크: https://youtu.be/CPMgX5ikL_8
Intrusion Detection Model using Self Organizing Maps.Tushar Shinde
Proposed Model:
[I] Pre-processing of server logs:
Our web-site server log file analyser performs the following steps when provided with a log file:
1) It scans the entries in the log files to help identify unique visitor’s sessions.
2) For each identified sessions, the analyser has to examine its key matching features to generate the session’s dimensional feature-vector representation.
[II] Session identification:
In this process of dividing a web-site server access log enters into sessions. Session identification is performed by:
1) Grouping all HTTP requests on web-sites that originate from the same IP address that matches the visitor and also are described by the same user-agent strings.
2) By applying a timeout approach to divide into unique sessions to avoid any mishaps.
[III] Dataset labelling:
labels each feature-vector as belonging to one of the following four categories:
1. Human visitor’s normal Known.
2. well-behaved web-site attackers.
3. malicious attackers.
4. unknown visitors unidentified.
Thus, allow a better understanding of the cluster’s nature and significance results can be generated.
Techniques:
SOM Algorithm, NNtool, MATLAB, WEKA toolkit, KDD Data-set.
Data Mining is an analytic process designed to explore data in search of consistent patterns and systematic relationships between variables, and then to validate the results by applying the patterns found to a new subset of data. Data mining is often described as the process of discovering patterns, correlations, trends or relationships by searching through a large amount of data stored in repositories, databases, and data warehouses. Diabetes, often referred to by doctors as diabetes mellitus, describes a group of metabolic diseases in which the person has high blood [3] glucose (blood sugar), either because insulin production is insufficient, or because the body's cells do not respond properly to insulin, or both. This project helps in identifying whether a person has diabetes or not, if predicted diabetic[4] the project suggest measures for maintaining normal health and if not diabetic it predicts the risk of getting diabetic. In this project Classification algorithm was used to classify the Pima Indian diabetes dataset. Results have been obtained using Android Application.
Image enhancement plays an important role in vision applications. Recently a lot of work has been performed in the field of image enhancement. Many techniques have already been proposed till now for enhancing the digital images. This paper has presented a comparative analysis of various image enhancement techniques. This paper has shown that the fuzzy logic and histogram based techniques have quite effective results over the available techniques. This paper ends up with suitable future directions to enhance fuzzy based image enhancement technique further. In the proposed technique, an approach is made to enhance the images other than low-contrast images as well by balancing the stretching parameter (K) according to the color contrast. Proposed technique is designed to restore the degraded edges resulted due to contrast enhancement as well.
final Year Projects, Final Year Projects in Chennai, Software Projects, Embedded Projects, Microcontrollers Projects, DSP Projects, VLSI Projects, Matlab Projects, Java Projects, .NET Projects, IEEE Projects, IEEE 2009 Projects, IEEE 2009 Projects, Software, IEEE 2009 Projects, Embedded, Software IEEE 2009 Projects, Embedded IEEE 2009 Projects, Final Year Project Titles, Final Year Project Reports, Final Year Project Review, Robotics Projects, Mechanical Projects, Electrical Projects, Power Electronics Projects, Power System Projects, Model Projects, Java Projects, J2EE Projects, Engineering Projects, Student Projects, Engineering College Projects, MCA Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, Wireless Networks Projects, Network Security Projects, Networking Projects, final year projects, ieee projects, student projects, college projects, ieee projects in chennai, java projects, software ieee projects, embedded ieee projects, "ieee2009projects", "final year projects", "ieee projects", "Engineering Projects", "Final Year Projects in Chennai", "Final year Projects at Chennai", Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, Final Year Java Projects, Final Year ASP.NET Projects, Final Year VB.NET Projects, Final Year C# Projects, Final Year Visual C++ Projects, Final Year Matlab Projects, Final Year NS2 Projects, Final Year C Projects, Final Year Microcontroller Projects, Final Year ATMEL Projects, Final Year PIC Projects, Final Year ARM Projects, Final Year DSP Projects, Final Year VLSI Projects, Final Year FPGA Projects, Final Year CPLD Projects, Final Year Power Electronics Projects, Final Year Electrical Projects, Final Year Robotics Projects, Final Year Solor Projects, Final Year MEMS Projects, Final Year J2EE Projects, Final Year J2ME Projects, Final Year AJAX Projects, Final Year Structs Projects, Final Year EJB Projects, Final Year Real Time Projects, Final Year Live Projects, Final Year Student Projects, Final Year Engineering Projects, Final Year MCA Projects, Final Year MBA Projects, Final Year College Projects, Final Year BE Projects, Final Year BTech Projects, Final Year ME Projects, Final Year MTech Projects, Final Year M.Sc Projects, IEEE Java Projects, ASP.NET Projects, VB.NET Projects, C# Projects, Visual C++ Projects, Matlab Projects, NS2 Projects, C Projects, Microcontroller Projects, ATMEL Projects, PIC Projects, ARM Projects, DSP Projects, VLSI Projects, FPGA Projects, CPLD Projects, Power Electronics Projects, Electrical Projects, Robotics Projects, Solor Projects, MEMS Projects, J2EE Projects, J2ME Projects, AJAX Projects, Structs Projects, EJB Projects, Real Time Projects, Live Projects, Student Projects, Engineering Projects, MCA Projects, MBA Projects, College Projects, BE Projects, BTech Projects, ME Projects, MTech Projects, M.Sc Projects, IEEE 2009 Java Projects, IEEE 2009 ASP.NET Projects, IEEE 2009 VB.NET Projects, IEEE 2009 C# Projects, IEEE 2009 Visual C++ Projects, IEEE 2009 Matlab Projects, IEEE 2009 NS2 Projects, IEEE 2009 C Projects, IEEE 2009 Microcontroller Projects, IEEE 2009 ATMEL Projects, IEEE 2009 PIC Projects, IEEE 2009 ARM Projects, IEEE 2009 DSP Projects, IEEE 2009 VLSI Projects, IEEE 2009 FPGA Projects, IEEE 2009 CPLD Projects, IEEE 2009 Power Electronics Projects, IEEE 2009 Electrical Projects, IEEE 2009 Robotics Projects, IEEE 2009 Solor Projects, IEEE 2009 MEMS Projects, IEEE 2009 J2EE P
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESVikash Kumar
IMAGE CLASSIFICATION USING KNN, RANDOM FOREST AND SVM ALGORITHM ON GLAUCOMA DATASETS AND EXPLAIN THE ACCURACY, SENSITIVITY, AND SPECIFICITY OF EACH AND EVERY ALGORITHMS
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
With the increase in Internet users the number of malicious users are also growing day-by-day posing a
serious problem in distinguishing between normal and abnormal behavior of users in the network. This
has led to the research area of intrusion detection which essentially analyzes the network traffic and tries
to determine normal and abnormal patterns of behavior.In this paper, we have analyzed the standard
NSL-KDD intrusion dataset using some neural network based techniques for predicting possible
intrusions. Four most effective classification methods, namely, Radial Basis Function Network, Self-
Organizing Map, Sequential Minimal Optimization, and Projective Adaptive Resonance Theory have been
applied. In order to enhance the performance of the classifiers, three entropy based feature selection
methods have been applied as preprocessing of data. Performances of different combinations of classifiers
and attribute reduction methods have also been compared.
Artificial neural network for machine learninggrinu
An Artificial Neurol Network (ANN) is a computational model. It is based on the structure and functions of biological neural networks. It works like the way human brain processes information. ANN includes a large number of connected processing units that work together to process information. They also generate meaningful results from it.
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...Jinwon Lee
TensorFlow Korea 논문읽기모임 PR12 258번째 논문 review입니다.
이번 논문은 MIT에서 나온 From ImageNet to Image Classification: Contextualizing Progress on Benchmarks입니다.
Deep Learning 하시는 분들이면 ImageNet 모르시는 분들이 없을텐데요, 이 논문은 ImageNet의 labeling 방법의 한계와 문제점에 대해서 얘기하고 top-1 accuracy 기반의 평가 방법에도 문제가 있을 수 있음을 지적하고 있습니다.
ImageNet data의 20% 이상이 multi object를 포함하고 있지만 그 중에 하나만 정답으로 인정되는 문제가 있고, annotation 방법의 한계로 인하여 실제로 사람이 생각하는 것과 다른 class가 정답으로 labeling되어 있는 경우도 많았습니다. 또한 terrier만 20종이 넘는 등 전문가가 아니면 판단하기 어려운 label도 많다는 문제도 있었구요. 이 밖에도 다양한 실험을 통해서 정량적인 분석과 함께 human-in-the-loop을 이용한 평가로 현재 model들의 성능이 어디까지 와있는지, 그리고 앞으로 더 높은 성능을 내기 위해서 data labeling 측면에서 해결해야할 과제는 무엇인지에 대해서 이야기하고 있습니다. 논문이 양이 좀 많긴 하지만 기술적인 내용이 별로 없어서 쉽게 읽으실 수 있는데요, 자세한 내용이 궁금하신 분들은 영상을 참고해주세요!
논문링크: https://arxiv.org/abs/2005.11295
발표영상링크: https://youtu.be/CPMgX5ikL_8
Intrusion Detection Model using Self Organizing Maps.Tushar Shinde
Proposed Model:
[I] Pre-processing of server logs:
Our web-site server log file analyser performs the following steps when provided with a log file:
1) It scans the entries in the log files to help identify unique visitor’s sessions.
2) For each identified sessions, the analyser has to examine its key matching features to generate the session’s dimensional feature-vector representation.
[II] Session identification:
In this process of dividing a web-site server access log enters into sessions. Session identification is performed by:
1) Grouping all HTTP requests on web-sites that originate from the same IP address that matches the visitor and also are described by the same user-agent strings.
2) By applying a timeout approach to divide into unique sessions to avoid any mishaps.
[III] Dataset labelling:
labels each feature-vector as belonging to one of the following four categories:
1. Human visitor’s normal Known.
2. well-behaved web-site attackers.
3. malicious attackers.
4. unknown visitors unidentified.
Thus, allow a better understanding of the cluster’s nature and significance results can be generated.
Techniques:
SOM Algorithm, NNtool, MATLAB, WEKA toolkit, KDD Data-set.
Data Mining is an analytic process designed to explore data in search of consistent patterns and systematic relationships between variables, and then to validate the results by applying the patterns found to a new subset of data. Data mining is often described as the process of discovering patterns, correlations, trends or relationships by searching through a large amount of data stored in repositories, databases, and data warehouses. Diabetes, often referred to by doctors as diabetes mellitus, describes a group of metabolic diseases in which the person has high blood [3] glucose (blood sugar), either because insulin production is insufficient, or because the body's cells do not respond properly to insulin, or both. This project helps in identifying whether a person has diabetes or not, if predicted diabetic[4] the project suggest measures for maintaining normal health and if not diabetic it predicts the risk of getting diabetic. In this project Classification algorithm was used to classify the Pima Indian diabetes dataset. Results have been obtained using Android Application.
Image enhancement plays an important role in vision applications. Recently a lot of work has been performed in the field of image enhancement. Many techniques have already been proposed till now for enhancing the digital images. This paper has presented a comparative analysis of various image enhancement techniques. This paper has shown that the fuzzy logic and histogram based techniques have quite effective results over the available techniques. This paper ends up with suitable future directions to enhance fuzzy based image enhancement technique further. In the proposed technique, an approach is made to enhance the images other than low-contrast images as well by balancing the stretching parameter (K) according to the color contrast. Proposed technique is designed to restore the degraded edges resulted due to contrast enhancement as well.
Security for Effective Data Storage in Multi CloudsEditor IJCATR
Cloud Computing is a technology that uses the internet and central remote servers to maintain data and
applications. Cloud computing allows consumers and businesses to use applications without installation and access their personal
files at any computer with internet access. This technology allows for much more efficient computing by centralizing data
storage, processing and bandwidth. The use of cloud computing has increased rapidly in many organizations. Cloud computing
provides many benefits in terms of low cost and accessibility of data. Ensuring the security of cloud computing is a major factor
in the cloud computing environment, as users often store sensitive information with cloud storage providers but these providers
may be untrusted. Dealing with “single cloud” providers is predicted to become less popular with customers due to risks of
service availability failure and the possibility of malicious insiders in the single cloud. A movement towards “multi-clouds”, or in
other words, “interclouds” or “cloud-of clouds” has emerged recently. This paper surveys recent research related to single and
multi-cloud security and addresses possible solutions. It is found that the research into the use of multicloud providers to maintain
security has received less attention from the research community than has the use of single clouds. This work aims to promote the
use of multi-clouds due to its ability to reduce security risks that affect the cloud computing user.
Grid computing is a modularized way of structuring network resources so as to share the information and resources, to perform heavily intense problems. Grid computing is a part of distributed processing which allows the distribution of the problem over multiple computational resources. The formation of grid decides the computation cost, the performance metrics of the operation to be carried out. The grid computing favours the formation of an adhoc structure formed at the time of request (it does not hold an infrastructure) that is termed as virtual organization. This paper presents dynamic source routing for modeling virtual organization.
In this paper, we consider a criminal investigation on the collective guilt of part members in a working group. Assuming that the statistics we used are reliable, we present the Page Rank Model based on mutual information. First, we use the average mutual information between non-suspicious topics and the suspicious topics to score the topics by degree of suspicion. Second, we build the correlation matrix based on the degree of suspicion and acquire the corresponding Markov state transition matrix. Then, we set the original value for all members of the working group based on the degree of suspicion. At the last, we calculate the suspected degree of each member in the working group. In the small 10-people case, we build the improved Page Rank model. By calculating the statistics of this case, we acquire a table which indicates the ranking of the suspected degree. In contrast with the results given in this issue, we find these two results basically match each other, indicating the model we have built is feasible. In the current case, firstly, we obtain a ranking list on 15 topics in order of suspicion via Page Rank Model based on mutual information. Secondly, we acquire the stable point of Markov state transition matrix using the Markov chain. Then, we build the connection matrix based on the degree of suspicion and acquire the corresponding Markov state transition matrix. Last, we calculate the degree of 83 candidates. From the result, we can see that those suspicious are on the top of the ranking list while those innocent people are at the bottom of the list, representing that the model we have built is feasible. When suspicious topics and conspirators changed, a relatively good result can also be obtained by this model. In the current case, we have the evidence to believe that Dolores and Jerome, who are the senior managers, have significant suspicion. It is recommended that future attention should be paid to them. The Page Rank Model, based on mutual information, takes full account of the information flow in message distribution network. This model can not only deal with the statistics used in conspiracy, but also be applied to detect the infected cells in a biological network. Finally, we present the advantages and disadvantages of this model and the direction of improvements.
Wireless data broadcast is an efficient way of disseminating data to users in the mobile computing environments. From the server’s point of view, how to place the data items on channels is a crucial issue, with the objective of minimizing the average access time and tuning time. Similarly, how to schedule the data retrieval process for a given request at the client side such that all the requested items can be downloaded in a short time is also an important problem. In this paper, we investigate the multi-item data retrieval scheduling in the push-based multichannel broadcast environments. The most important issues in mobile computing are energy efficiency and query response efficiency. However, in data broadcast the objectives of reducing access latency and energy cost can be contradictive to each other. Consequently, we define a new problem named Minimum Cost Data Retrieval Problem (MCDR) and Large Number Data Retrieval (LNDR) Problem. We also develop a heuristic algorithm to download a large number of items efficiently. When there is no replicated item in a broadcast cycle, we show that an optimal retrieval schedule can be obtained in polynomial time
Multi-Agent systems (Autonomous agents or agents) and knowledge discovery (or data mining) are two active
areas in information technology. A profound insight of bringing these two communities together has unveiled a tremendous
potential for new opportunities and wider applications through the synergy of agents and data mining. Multi-agent systems
(MAS) often deal with complex applications that require distributed problem solving. In many applications the individual and
collective behavior of the agents depends on the observed data from distributed data sources. Data mining technology has
emerged, for identifying patterns and trends from large quantities of data. The increasing demand to scale up to massive data sets
inherently distributed over a network with limited band width and computational resources available motivated the development of
distributed data mining (DDM).Distributed data mining is originated from the need of mining over decentralized data
sources. DDM is expected to perform partial analysis of data at individual sites and then to send the outcome as partial result
to other sites where it sometimes required to be aggregated to the global result
One of the most popular areas of research is wireless communication. Mobile Ad Hoc network (MANET) is a network with wireless mobile nodes, infrastructure less and self organizing. With its wireless and distributed nature it is exposed to several security threats. One of the threats in MANET is the wormhole attack. In this attack a pair of attacker forms a virtual link thereby recording and replaying the wireless transmission. This paper presents types of wormhole attack and also includes different technique for detecting wormhole attack in MANET..
Risk Prediction for Production of an EnterpriseEditor IJCATR
Despite all preventive measures, there is so much possibility of risks in any project development as well as in enterprise management. There is no any standard mechanism or methodology available to assess the risks in any project or production management. Using some precautionary steps, the manager can only avoid the risks as much as he can. To address this issue, this paper presents a probabilistic risk assessment model for the production of an enterprise. For this, Multi-Entity Bayesian Network (MEBN) has been used to represent the requirements for production management as well as to assess the risks adherence in production management, where MEBN combines expressivity of first-order logic and probabilistic feature of Bayesian network. Bayesian network provides the feature to represent the probabilistic uncertainty and reasoning about probabilistic knowledge base, which is used here to represent the probable risks behind each causes of a risk. The proposed probabilistic model is discussed with the help of a case study, which is used to predict risks inherent in the production of an enterprise, which depends upon various measures like labour availability, power backup, transport availability etc.
In this paper, we introduce the notion of intuitionistic fuzzy semipre generalized connected space, intuitionistic fuzzy semipre generalized super connected space and intuitionistic fuzzy semipre generalized extremally disconnected spaces. We investigate some of their properties.
Online Social Network (OSN) sites act as a medium to spread their own views, activities and their thoughts to some camaraderie. Contents of this network are spread over web, so it was hard to determine by a human decision. Currently, they do not provide any mechanism to ensure privacy concerns towards data associated with each user. Due to this problem, number of users lacks from their ownership control. In this paper, we proposed AC2P (Activity Control-Access Control Protocol) for information control on the web. Alternatively, Tag Refinement strategy determines illegal tagging over images and send notification about particular image spread within different communities/groups. These techniques reduce risk of information flow and avoid unwanted tagging toward images.
Assistive Examination System for Visually ImpairedEditor IJCATR
This paper presents a design of voice enabled examination system which can be used by the visually challenged students.
The system uses Text-to-Speech (TTS) and Speech-to-Text (STT) technology. The text-to-speech and speech-to-text web based
academic testing software would provide an interaction for blind students to enhance their educational experiences by providing them
with a tool to give the exams. This system will aid the differently-abled to appear for online tests and enable them to come at par with
the other students. This system can also be used by students with learning disabilities or by people who wish to take the examination in
a combined auditory and visual way.
A Formal Machine Learning or Multi Objective Decision Making System for Deter...Editor IJCATR
Decision-making typically needs the mechanisms to compromise among opposing norms. Once multiple objectives square measure is concerned of machine learning, a vital step is to check the weights of individual objectives to the system-level performance. Determinant, the weights of multi-objectives is associate in analysis method, associated it's been typically treated as a drawback. However, our preliminary investigation has shown that existing methodologies in managing the weights of multi-objectives have some obvious limitations like the determination of weights is treated as one drawback, a result supporting such associate improvement is limited, if associated it will even be unreliable, once knowledge concerning multiple objectives is incomplete like an integrity caused by poor data. The constraints of weights are also mentioned. Variable weights square measure is natural in decision-making processes. Here, we'd like to develop a scientific methodology in determinant variable weights of multi-objectives. The roles of weights in a creative multi-objective decision-making or machine-learning of square measure analyzed, and therefore the weights square measure determined with the help of a standard neural network.
Risk-Aware Response Mechanism with Extended D-S theoryEditor IJCATR
Mobile Ad hoc Networks (MANET) are having dynamic nature of its network infrastructure and
it is vulnerable to all types of attacks. Among these attacks, the routing attacks getting more attention
because its changing the whole topology itself and it causes more damage to MANET. Even there are lot of
intrusion detection Systems available to diminish those critical attacks, existing causesunexpected network
partition, and causes additional damages to the infrastructure of the network , and it leads to uncertainty in
finding routing attacks in MANET. In this paper, we propose a adaptive risk-aware response mechanism with
extended Dempster-Shafer theory in MANET to identify the routing attacks and malicious node. Our
techniques find the malicious node with degree of evidence from the expert knowledge and detect the
important factors for each node.It creates black list and all those malicious nodes so that it may not enter the
network again
A HYBRID FILTERING TECHNIQUE FOR ELIMINATING UNIFORM NOISE AND IMPULSE NOIS...sipij
A new hybrid filtering technique is proposed to improving denoising process on digital images.
This technique is performed in two steps. In the first step, uniform noise and impulse noise is
eliminated using decision based algorithm (DBA). Image denoising process is further improved
by an appropriately combining DBA with Adaptive Neuro Fuzzy Inference System (ANFIS) at
the removal of uniform noise and impulse noise on the digital images. Three well known images
are selected for training and the internal parameters of the neuro-fuzzy network are adaptively
optimized by training. This technique offers excellent line, edge, and fine detail preservation
performance while, at the same time, effectively denoising digital images. Extensive simulation
results were realized for ANFIS network and different filters are compared. Results show that
the proposed filter is superior performance in terms of image denoising and edges and fine
details preservation properties.
A Hybrid Filtering Technique for Random Valued Impulse Noise Elimination on D...IDES Editor
A novel adaptive network fuzzy inference system
(ANFIS) based filter is presented for the enhancement of
images corrupted by random valued impulse noise (RVIN).
This technique is performed in two steps. In the first step,
impulse noise using an Asymmetric Trimmed Median Filter
(ATMF). In the second step, image restoration is obtained by
an appropriately combining ATMF with ANFIS at the removal
of higher level of RVIN on the digital images. Three well
known images are selected for training and the internal
parameters of the neuro-fuzzy network are adaptively
optimized by training. This technique offers excellent line,
edge, and fine detail preservation performance while, at the
same time, effectively enhancing digital images. Extensive
simulation results were realized for ANFIS network and
different filters are compared. Results show that the proposed
filter is superior performance in terms of image denoising
and edges and fine details preservation properties.
Novel adaptive filter (naf) for impulse noise suppression from digital imagesijbbjournal
In general, it is known that an adaptive filter adjusts its parameters iteratively such as size of the working
window, decision threshold values used in two stage detection-estimation based switching filters, number of
iterations etc. It is also known that nonlinear filters such as median filters and its several variants are
popularly known for their ability in dealing with the unknown circumstances. In this paper an efficient and
simple adaptive nonlinear filtering scheme is presented to eliminate the impulse noise from the digital images with an impulsive noise detection and reduction scheme based on adaptive nonlinear filter techniques. The proposed scheme employs image statistics based dynamically varying working window and an adaptive threshold for noise detection with a Noise Exclusive Median (NEM) based restoration. The intensity value of the Noise Exclusive Median (NEM) is derived from the processed pixels in local
neighborhood of a dynamically adaptive window. In the proposed scheme use of an adaptive threshold value derived from the noisy image statistics returns more precise results for the noisy pixel detection. The
proposed scheme is simple and can be implemented as either a single pass or a multi-pass with a maximum
of three iterations with a simple stopping criterion. The goodness of the proposed scheme is evaluated with respect to the qualitative and quantitative measures obtained by MATLAB simulations with standard images added with impulsive noise of varying densities. From the comparative analysis it is evident that the proposed scheme out performs the state-of-art schemes, preferably in cases of high-density impulse noise
Adaptive Digital Filter Design for Linear Noise Cancellation Using Neural Net...iosrjce
Noise is the most serious issue in the filters and adaptive filters are subjected to this unwanted
component. This paper deals with the problem of the adaptive noise and various adaptive algorithms functions
which when implemented practically shows that the noise is cancelled or removed by the neural network
approach using the exact random basis function. The adaptive filters are used to control the noise and it has a
linear input and output characteristics. This approach is done so as to get the minimum possible error so that to
obtain the error free desired signal. The designed filter will reduce this noise from measured signal by a
reference signal which is highly correlated with the noise signal. This approach gives excellent result for this
signal processing technique that removes or eliminates the linear noise from the different functions. The
simulation results are also mentioned so as to gives a vivid idea of reduced noise using neural networks
algorithm.
International Journal of Computational Engineering Research(IJCER)ijceronline
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
Image Filtering Using all Neighbor Directional Weighted Pixels: Optimization ...sipij
In this paper a novel approach for de noising images corrupted by random valued impulses has been proposed. Noise suppression is done in two steps. The detection of noisy pixels is done using all neighbor directional weighted pixels (ANDWP) in the 5 x 5 window. The filtering scheme is based on minimum variance of the four directional pixels. In this approach, relatively recent category of stochastic global optimization technique i.e., particle swarm optimization (PSO) has also been used for searching the parameters of detection and filtering operators required for optimal performance. Results obtained shows better de noising and preservation of fine details for highly corrupted images.
A Decision tree and Conditional Median Filter Based Denoising for impulse noi...IJERA Editor
Impulse noise is often introduced into images during acquisition and transmission. Even though so many denoising techniques are existing for the removal of impulse noise in images, most of them are high complexity methods and have only low image quality. Here a low cost, low complexity VLSI architecture for the removal of random valued impulse noise in highly corrupted images is introduced. In this technique a decision- tree- based impulse noise detector is used to detect the noisy pixels and an efficient conditional median filter is used to reconstruct the intensity values of noisy pixels. The proposed technique can improve the signal to noise ratio than any other technique.
PERFORMANCE ANALYSIS OF UNSYMMETRICAL TRIMMED MEDIAN AS DETECTOR ON IMAGE NOI...ijistjournal
This Paper Analyze the performance of Unsymmetrical trimmed median, which is used as detector for the detection of impulse noise, Gaussian noise and mixed noise is proposed. The proposed algorithm uses a fixed 3x3 window for the increasing noise densities. The pixels in the current window are arranged in sorting order using a improved snake like sorting algorithm with reduced comparator. The processed pixel is checked for the occurrence of outliers, if the absolute difference between processed pixels is greater than fixed threshold. Under high noise densities the processed pixel is also noisy hence the median is checked using the above procedure. if found true then the pixel is considered as noisy hence the corrupted pixel is replaced by the median of the current processing window. If median is also noisy then replace the corrupted pixel with unsymmetrical trimmed median else if the pixel is termed uncorrupted and left unaltered. The proposed algorithm (PA) is tested on varying detail images for various noises. The proposed algorithm effectively removes the high density fixed value impulse noise, low density random valued impulse noise, low density Gaussian noise and lower proportion of mixed noise. The proposed algorithm is targeted on Xc3e5000-5fg900 FPGA using Xilinx 7.1 compiler version which requires less number of slices, optimum speed and low power when compared to the other median finding architectures.
PERFORMANCE ANALYSIS OF UNSYMMETRICAL TRIMMED MEDIAN AS DETECTOR ON IMAGE NOI...ijistjournal
This Paper Analyze the performance of Unsymmetrical trimmed median, which is used as detector for the detection of impulse noise, Gaussian noise and mixed noise is proposed. The proposed algorithm uses a fixed 3x3 window for the increasing noise densities. The pixels in the current window are arranged in sorting order using a improved snake like sorting algorithm with reduced comparator. The processed pixel is checked for the occurrence of outliers, if the absolute difference between processed pixels is greater than fixed threshold. Under high noise densities the processed pixel is also noisy hence the median is checked using the above procedure. if found true then the pixel is considered as noisy hence the corrupted pixel is replaced by the median of the current processing window. If median is also noisy then replace the corrupted pixel with unsymmetrical trimmed median else if the pixel is termed uncorrupted and left unaltered. The proposed algorithm (PA) is tested on varying detail images for various noises. The proposed algorithm effectively removes the high density fixed value impulse noise, low density random valued impulse noise, low density Gaussian noise and lower proportion of mixed noise. The proposed algorithm is targeted on Xc3e5000-5fg900 FPGA using Xilinx 7.1 compiler version which requires less number of slices, optimum speed and low power when compared to the other median finding architectures.
Performance of Various Order Statistics Filters in Impulse and Mixed Noise Re...sipij
Remote sensing images (ranges from satellite to seismic) are affected by number of noises like interference, impulse and speckle noises. Image denoising is one of the traditional problems in digital image processing, which plays vital role as a pre-processing step in number of image and video applications. Image denoising still remains a challenging research area for researchers because noise
removal introduces artifacts and causes blurring of the images. This study is done with the intension of designing a best algorithm for impulsive noise reduction in an industrial environment. A review of the typical impulsive noise reduction systems which are based on order statistics are done and particularized for the described situation. Finally, computational aspects are analyzed in terms of PSNR values and some solutions are proposed.
Performance analysis of image filtering algorithms for mri imageseSAT Publishing House
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
Text Mining in Digital Libraries using OKAPI BM25 ModelEditor IJCATR
The emergence of the internet has made vast amounts of information available and easily accessible online. As a result, most libraries have digitized their content in order to remain relevant to their users and to keep pace with the advancement of the internet. However, these digital libraries have been criticized for using inefficient information retrieval models that do not perform relevance ranking to the retrieved results. This paper proposed the use of OKAPI BM25 model in text mining so as means of improving relevance ranking of digital libraries. Okapi BM25 model was selected because it is a probability-based relevance ranking algorithm. A case study research was conducted and the model design was based on information retrieval processes. The performance of Boolean, vector space, and Okapi BM25 models was compared for data retrieval. Relevant ranked documents were retrieved and displayed at the OPAC framework search page. The results revealed that Okapi BM 25 outperformed Boolean model and Vector Space model. Therefore, this paper proposes the use of Okapi BM25 model to reward terms according to their relative frequencies in a document so as to improve the performance of text mining in digital libraries.
Green Computing, eco trends, climate change, e-waste and eco-friendlyEditor IJCATR
This study focused on the practice of using computing resources more efficiently while maintaining or increasing overall performance. Sustainable IT services require the integration of green computing practices such as power management, virtualization, improving cooling technology, recycling, electronic waste disposal, and optimization of the IT infrastructure to meet sustainability requirements. Studies have shown that costs of power utilized by IT departments can approach 50% of the overall energy costs for an organization. While there is an expectation that green IT should lower costs and the firm’s impact on the environment, there has been far less attention directed at understanding the strategic benefits of sustainable IT services in terms of the creation of customer value, business value and societal value. This paper provides a review of the literature on sustainable IT, key areas of focus, and identifies a core set of principles to guide sustainable IT service design.
Policies for Green Computing and E-Waste in NigeriaEditor IJCATR
Computers today are an integral part of individuals’ lives all around the world, but unfortunately these devices are toxic to the environment given the materials used, their limited battery life and technological obsolescence. Individuals are concerned about the hazardous materials ever present in computers, even if the importance of various attributes differs, and that a more environment -friendly attitude can be obtained through exposure to educational materials. In this paper, we aim to delineate the problem of e-waste in Nigeria and highlight a series of measures and the advantage they herald for our country and propose a series of action steps to develop in these areas further. It is possible for Nigeria to have an immediate economic stimulus and job creation while moving quickly to abide by the requirements of climate change legislation and energy efficiency directives. The costs of implementing energy efficiency and renewable energy measures are minimal as they are not cash expenditures but rather investments paid back by future, continuous energy savings.
Performance Evaluation of VANETs for Evaluating Node Stability in Dynamic Sce...Editor IJCATR
Vehicular ad hoc networks (VANETs) are a favorable area of exploration which empowers the interconnection amid the movable vehicles and between transportable units (vehicles) and road side units (RSU). In Vehicular Ad Hoc Networks (VANETs), mobile vehicles can be organized into assemblage to promote interconnection links. The assemblage arrangement according to dimensions and geographical extend has serious influence on attribute of interaction .Vehicular ad hoc networks (VANETs) are subclass of mobile Ad-hoc network involving more complex mobility patterns. Because of mobility the topology changes very frequently. This raises a number of technical challenges including the stability of the network .There is a need for assemblage configuration leading to more stable realistic network. The paper provides investigation of various simulation scenarios in which cluster using k-means algorithm are generated and their numbers are varied to find the more stable configuration in real scenario of road.
Optimum Location of DG Units Considering Operation ConditionsEditor IJCATR
The optimal sizing and placement of Distributed Generation units (DG) are becoming very attractive to researchers these days. In this paper a two stage approach has been used for allocation and sizing of DGs in distribution system with time varying load model. The strategic placement of DGs can help in reducing energy losses and improving voltage profile. The proposed work discusses time varying loads that can be useful for selecting the location and optimizing DG operation. The method has the potential to be used for integrating the available DGs by identifying the best locations in a power system. The proposed method has been demonstrated on 9-bus test system.
Analysis of Comparison of Fuzzy Knn, C4.5 Algorithm, and Naïve Bayes Classifi...Editor IJCATR
Early detection of diabetes mellitus (DM) can prevent or inhibit complication. There are several laboratory test that must be done to detect DM. The result of this laboratory test then converted into data training. Data training used in this study generated from UCI Pima Database with 6 attributes that were used to classify positive or negative diabetes. There are various classification methods that are commonly used, and in this study three of them were compared, which were fuzzy KNN, C4.5 algorithm and Naïve Bayes Classifier (NBC) with one identical case. The objective of this study was to create software to classify DM using tested methods and compared the three methods based on accuracy, precision, and recall. The results showed that the best method was Fuzzy KNN with average and maximum accuracy reached 96% and 98%, respectively. In second place, NBC method had respective average and maximum accuracy of 87.5% and 90%. Lastly, C4.5 algorithm had average and maximum accuracy of 79.5% and 86%, respectively.
Web Scraping for Estimating new Record from Source SiteEditor IJCATR
Study in the Competitive field of Intelligent, and studies in the field of Web Scraping, have a symbiotic relationship mutualism. In the information age today, the website serves as a main source. The research focus is on how to get data from websites and how to slow down the intensity of the download. The problem that arises is the website sources are autonomous so that vulnerable changes the structure of the content at any time. The next problem is the system intrusion detection snort installed on the server to detect bot crawler. So the researchers propose the use of the methods of Mining Data Records and the method of Exponential Smoothing so that adaptive to changes in the structure of the content and do a browse or fetch automatically follow the pattern of the occurrences of the news. The results of the tests, with the threshold 0.3 for MDR and similarity threshold score 0.65 for STM, using recall and precision values produce f-measure average 92.6%. While the results of the tests of the exponential estimation smoothing using ? = 0.5 produces MAE 18.2 datarecord duplicate. It slowed down to 3.6 datarecord from 21.8 datarecord results schedule download/fetch fix in an average time of occurrence news.
Evaluating Semantic Similarity between Biomedical Concepts/Classes through S...Editor IJCATR
Most of the existing semantic similarity measures that use ontology structure as their primary source can measure semantic similarity between concepts/classes using single ontology. The ontology-based semantic similarity techniques such as structure-based semantic similarity techniques (Path Length Measure, Wu and Palmer’s Measure, and Leacock and Chodorow’s measure), information content-based similarity techniques (Resnik’s measure, Lin’s measure), and biomedical domain ontology techniques (Al-Mubaid and Nguyen’s measure (SimDist)) were evaluated relative to human experts’ ratings, and compared on sets of concepts using the ICD-10 “V1.0” terminology within the UMLS. The experimental results validate the efficiency of the SemDist technique in single ontology, and demonstrate that SemDist semantic similarity techniques, compared with the existing techniques, gives the best overall results of correlation with experts’ ratings.
Semantic Similarity Measures between Terms in the Biomedical Domain within f...Editor IJCATR
The techniques and tests are tools used to define how measure the goodness of ontology or its resources. The similarity between biomedical classes/concepts is an important task for the biomedical information extraction and knowledge discovery. However, most of the semantic similarity techniques can be adopted to be used in the biomedical domain (UMLS). Many experiments have been conducted to check the applicability of these measures. In this paper, we investigate to measure semantic similarity between two terms within single ontology or multiple ontologies in ICD-10 “V1.0” as primary source, and compare my results to human experts score by correlation coefficient.
A Strategy for Improving the Performance of Small Files in Openstack Swift Editor IJCATR
This is an effective way to improve the storage access performance of small files in Openstack Swift by adding an aggregate storage module. Because Swift will lead to too much disk operation when querying metadata, the transfer performance of plenty of small files is low. In this paper, we propose an aggregated storage strategy (ASS), and implement it in Swift. ASS comprises two parts which include merge storage and index storage. At the first stage, ASS arranges the write request queue in chronological order, and then stores objects in volumes. These volumes are large files that are stored in Swift actually. During the short encounter time, the object-to-volume mapping information is stored in Key-Value store at the second stage. The experimental results show that the ASS can effectively improve Swift's small file transfer performance.
Integrated System for Vehicle Clearance and RegistrationEditor IJCATR
Efficient management and control of government's cash resources rely on government banking arrangements. Nigeria, like many low income countries, employed fragmented systems in handling government receipts and payments. Later in 2016, Nigeria implemented a unified structure as recommended by the IMF, where all government funds are collected in one account would reduce borrowing costs, extend credit and improve government's fiscal policy among other benefits to government. This situation motivated us to embark on this research to design and implement an integrated system for vehicle clearance and registration. This system complies with the new Treasury Single Account policy to enable proper interaction and collaboration among five different level agencies (NCS, FRSC, SBIR, VIO and NPF) saddled with vehicular administration and activities in Nigeria. Since the system is web based, Object Oriented Hypermedia Design Methodology (OOHDM) is used. Tools such as Php, JavaScript, css, html, AJAX and other web development technologies were used. The result is a web based system that gives proper information about a vehicle starting from the exact date of importation to registration and renewal of licensing. Vehicle owner information, custom duty information, plate number registration details, etc. will also be efficiently retrieved from the system by any of the agencies without contacting the other agency at any point in time. Also number plate will no longer be the only means of vehicle identification as it is presently the case in Nigeria, because the unified system will automatically generate and assigned a Unique Vehicle Identification Pin Number (UVIPN) on payment of duty in the system to the vehicle and the UVIPN will be linked to the various agencies in the management information system.
Assessment of the Efficiency of Customer Order Management System: A Case Stu...Editor IJCATR
The Supermarket Management System deals with the automation of buying and selling of good and services. It includes both sales and purchase of items. The project Supermarket Management System is to be developed with the objective of making the system reliable, easier, fast, and more informative.
Energy-Aware Routing in Wireless Sensor Network Using Modified Bi-Directional A*Editor IJCATR
Energy is a key component in the Wireless Sensor Network (WSN)[1]. The system will not be able to run according to its function without the availability of adequate power units. One of the characteristics of wireless sensor network is Limitation energy[2]. A lot of research has been done to develop strategies to overcome this problem. One of them is clustering technique. The popular clustering technique is Low Energy Adaptive Clustering Hierarchy (LEACH)[3]. In LEACH, clustering techniques are used to determine Cluster Head (CH), which will then be assigned to forward packets to Base Station (BS). In this research, we propose other clustering techniques, which utilize the Social Network Analysis approach theory of Betweeness Centrality (BC) which will then be implemented in the Setup phase. While in the Steady-State phase, one of the heuristic searching algorithms, Modified Bi-Directional A* (MBDA *) is implemented. The experiment was performed deploy 100 nodes statically in the 100x100 area, with one Base Station at coordinates (50,50). To find out the reliability of the system, the experiment to do in 5000 rounds. The performance of the designed routing protocol strategy will be tested based on network lifetime, throughput, and residual energy. The results show that BC-MBDA * is better than LEACH. This is influenced by the ways of working LEACH in determining the CH that is dynamic, which is always changing in every data transmission process. This will result in the use of energy, because they always doing any computation to determine CH in every transmission process. In contrast to BC-MBDA *, CH is statically determined, so it can decrease energy usage.
Security in Software Defined Networks (SDN): Challenges and Research Opportun...Editor IJCATR
In networks, the rapidly changing traffic patterns of search engines, Internet of Things (IoT) devices, Big Data and data centers has thrown up new challenges for legacy; existing networks; and prompted the need for a more intelligent and innovative way to dynamically manage traffic and allocate limited network resources. Software Defined Network (SDN) which decouples the control plane from the data plane through network vitalizations aims to address these challenges. This paper has explored the SDN architecture and its implementation with the OpenFlow protocol. It has also assessed some of its benefits over traditional network architectures, security concerns and how it can be addressed in future research and related works in emerging economies such as Nigeria.
Measure the Similarity of Complaint Document Using Cosine Similarity Based on...Editor IJCATR
Report handling on "LAPOR!" (Laporan, Aspirasi dan Pengaduan Online Rakyat) system depending on the system administrator who manually reads every incoming report [3]. Read manually can lead to errors in handling complaints [4] if the data flow is huge and grows rapidly, it needs at least three days to prepare a confirmation and it sensitive to inconsistencies [3]. In this study, the authors propose a model that can measure the identities of the Query (Incoming) with Document (Archive). The authors employed Class-Based Indexing term weighting scheme, and Cosine Similarities to analyse document similarities. CoSimTFIDF, CoSimTFICF and CoSimTFIDFICF values used in classification as feature for K-Nearest Neighbour (K-NN) classifier. The optimum result evaluation is pre-processing employ 75% of training data ratio and 25% of test data with CoSimTFIDF feature. It deliver a high accuracy 84%. The k = 5 value obtain high accuracy 84.12%
Hangul Recognition Using Support Vector MachineEditor IJCATR
The recognition of Hangul Image is more difficult compared with that of Latin. It could be recognized from the structural arrangement. Hangul is arranged from two dimensions while Latin is only from the left to the right. The current research creates a system to convert Hangul image into Latin text in order to use it as a learning material on reading Hangul. In general, image recognition system is divided into three steps. The first step is preprocessing, which includes binarization, segmentation through connected component-labeling method, and thinning with Zhang Suen to decrease some pattern information. The second is receiving the feature from every single image, whose identification process is done through chain code method. The third is recognizing the process using Support Vector Machine (SVM) with some kernels. It works through letter image and Hangul word recognition. It consists of 34 letters, each of which has 15 different patterns. The whole patterns are 510, divided into 3 data scenarios. The highest result achieved is 94,7% using SVM kernel polynomial and radial basis function. The level of recognition result is influenced by many trained data. Whilst the recognition process of Hangul word applies to the type 2 Hangul word with 6 different patterns. The difference of these patterns appears from the change of the font type. The chosen fonts for data training are such as Batang, Dotum, Gaeul, Gulim, Malgun Gothic. Arial Unicode MS is used to test the data. The lowest accuracy is achieved through the use of SVM kernel radial basis function, which is 69%. The same result, 72 %, is given by the SVM kernel linear and polynomial.
Application of 3D Printing in EducationEditor IJCATR
This paper provides a review of literature concerning the application of 3D printing in the education system. The review identifies that 3D Printing is being applied across the Educational levels [1] as well as in Libraries, Laboratories, and Distance education systems. The review also finds that 3D Printing is being used to teach both students and trainers about 3D Printing and to develop 3D Printing skills.
Survey on Energy-Efficient Routing Algorithms for Underwater Wireless Sensor ...Editor IJCATR
In underwater environment, for retrieval of information the routing mechanism is used. In routing mechanism there are three to four types of nodes are used, one is sink node which is deployed on the water surface and can collect the information, courier/super/AUV or dolphin powerful nodes are deployed in the middle of the water for forwarding the packets, ordinary nodes are also forwarder nodes which can be deployed from bottom to surface of the water and source nodes are deployed at the seabed which can extract the valuable information from the bottom of the sea. In underwater environment the battery power of the nodes is limited and that power can be enhanced through better selection of the routing algorithm. This paper focuses the energy-efficient routing algorithms for their routing mechanisms to prolong the battery power of the nodes. This paper also focuses the performance analysis of the energy-efficient algorithms under which we can examine the better performance of the route selection mechanism which can prolong the battery power of the node
Comparative analysis on Void Node Removal Routing algorithms for Underwater W...Editor IJCATR
The designing of routing algorithms faces many challenges in underwater environment like: propagation delay, acoustic channel behaviour, limited bandwidth, high bit error rate, limited battery power, underwater pressure, node mobility, localization 3D deployment, and underwater obstacles (voids). This paper focuses the underwater voids which affects the overall performance of the entire network. The majority of the researchers have used the better approaches for removal of voids through alternate path selection mechanism but still research needs improvement. This paper also focuses the architecture and its operation through merits and demerits of the existing algorithms. This research article further focuses the analytical method of the performance analysis of existing algorithms through which we found the better approach for removal of voids
Decay Property for Solutions to Plate Type Equations with Variable CoefficientsEditor IJCATR
In this paper we consider the initial value problem for a plate type equation with variable coefficients and memory in
1 n R n ), which is of regularity-loss property. By using spectrally resolution, we study the pointwise estimates in the spectral
space of the fundamental solution to the corresponding linear problem. Appealing to this pointwise estimates, we obtain the global
existence and the decay estimates of solutions to the semilinear problem by employing the fixed point theorem
বাংলাদেশের অর্থনৈতিক সমীক্ষা ২০২৪ [Bangladesh Economic Review 2024 Bangla.pdf] কম্পিউটার , ট্যাব ও স্মার্ট ফোন ভার্সন সহ সম্পূর্ণ বাংলা ই-বুক বা pdf বই " সুচিপত্র ...বুকমার্ক মেনু 🔖 ও হাইপার লিংক মেনু 📝👆 যুক্ত ..
আমাদের সবার জন্য খুব খুব গুরুত্বপূর্ণ একটি বই ..বিসিএস, ব্যাংক, ইউনিভার্সিটি ভর্তি ও যে কোন প্রতিযোগিতা মূলক পরীক্ষার জন্য এর খুব ইম্পরট্যান্ট একটি বিষয় ...তাছাড়া বাংলাদেশের সাম্প্রতিক যে কোন ডাটা বা তথ্য এই বইতে পাবেন ...
তাই একজন নাগরিক হিসাবে এই তথ্য গুলো আপনার জানা প্রয়োজন ...।
বিসিএস ও ব্যাংক এর লিখিত পরীক্ষা ...+এছাড়া মাধ্যমিক ও উচ্চমাধ্যমিকের স্টুডেন্টদের জন্য অনেক কাজে আসবে ...
This presentation includes basic of PCOS their pathology and treatment and also Ayurveda correlation of PCOS and Ayurvedic line of treatment mentioned in classics.
How to Add Chatter in the odoo 17 ERP ModuleCeline George
In Odoo, the chatter is like a chat tool that helps you work together on records. You can leave notes and track things, making it easier to talk with your team and partners. Inside chatter, all communication history, activity, and changes will be displayed.
Exploiting Artificial Intelligence for Empowering Researchers and Faculty, In...Dr. Vinod Kumar Kanvaria
Exploiting Artificial Intelligence for Empowering Researchers and Faculty,
International FDP on Fundamentals of Research in Social Sciences
at Integral University, Lucknow, 06.06.2024
By Dr. Vinod Kumar Kanvaria
Thinking of getting a dog? Be aware that breeds like Pit Bulls, Rottweilers, and German Shepherds can be loyal and dangerous. Proper training and socialization are crucial to preventing aggressive behaviors. Ensure safety by understanding their needs and always supervising interactions. Stay safe, and enjoy your furry friends!
Biological screening of herbal drugs: Introduction and Need for
Phyto-Pharmacological Screening, New Strategies for evaluating
Natural Products, In vitro evaluation techniques for Antioxidants, Antimicrobial and Anticancer drugs. In vivo evaluation techniques
for Anti-inflammatory, Antiulcer, Anticancer, Wound healing, Antidiabetic, Hepatoprotective, Cardio protective, Diuretics and
Antifertility, Toxicity studies as per OECD guidelines
This presentation was provided by Steph Pollock of The American Psychological Association’s Journals Program, and Damita Snow, of The American Society of Civil Engineers (ASCE), for the initial session of NISO's 2024 Training Series "DEIA in the Scholarly Landscape." Session One: 'Setting Expectations: a DEIA Primer,' was held June 6, 2024.
Safalta Digital marketing institute in Noida, provide complete applications that encompass a huge range of virtual advertising and marketing additives, which includes search engine optimization, virtual communication advertising, pay-per-click on marketing, content material advertising, internet analytics, and greater. These university courses are designed for students who possess a comprehensive understanding of virtual marketing strategies and attributes.Safalta Digital Marketing Institute in Noida is a first choice for young individuals or students who are looking to start their careers in the field of digital advertising. The institute gives specialized courses designed and certification.
for beginners, providing thorough training in areas such as SEO, digital communication marketing, and PPC training in Noida. After finishing the program, students receive the certifications recognised by top different universitie, setting a strong foundation for a successful career in digital marketing.
it describes the bony anatomy including the femoral head , acetabulum, labrum . also discusses the capsule , ligaments . muscle that act on the hip joint and the range of motion are outlined. factors affecting hip joint stability and weight transmission through the joint are summarized.
Random Valued Impulse Noise Elimination using Neural Filter
1. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 261
Random Valued Impulse Noise Elimination using Neural
Filter
R.Pushpavalli
Pondicherry Engineering College
Puducherry-605 014
India.
G.Sivaradje
Pondicherry Engineering College
Puducherry-605 014
India.
Abstract: A neural filtering technique is proposed in this paper for restoring the images extremely corrupted with random valued
impulse noise. The proposed intelligent filter is carried out in two stages. In first stage the corrupted image is filtered by applying an
asymmetric trimmed median filter. An asymmetric trimmed median filtered output image is suitably combined with a feed forward
neural network in the second stage. The internal parameters of the feed forward neural network are adaptively optimized by training of
three well known images. This is quite effective in eliminating random valued impulse noise. Simulation results show that the
proposed filter is superior in terms of eliminating impulse noise as well as preserving edges and fine details of digital images and
results are compared with other existing nonlinear filters.
Keywords: Feed forward neural network; Impulse noise; Image restoration; Nonlinear filter.
1. INTRODUCTION
The image corrupted by different types of noises is a
frequently encountered problem in image acquisition and
transmission. The noise comes from noisy sensors or channel
transmission errors. Several kinds of noises are discussed
here. The impulse noise (or salt and pepper noise) is caused
by sharp, sudden disturbances in the image signal; its
appearance is randomly scattered white or black (or both)
pixels over the image. Digital images are often corrupted by
impulse noise during transmission over communication
channel or image acquisition. In the early stages, many filters
had been investigated for noise elimination [1-3]. Majority of
the existing filtering methods, compromise order statistics
filters utilizing the rank order information of an appropriate
set of noisy input pixels. These filters are usually developed in
the general framework of rank selection filters, which are
nonlinear operators, constrained to an output of order statistic
from a set of input samples.
The standard median filter is a simple rank selection filter and
attempts to remove impulse noise from the center pixel of the
processing window by changing the luminance value of the
center pixel with the median of the luminance values of the
pixels contained within the window. This approach provides a
reasonable noise removal performance with the cost of
introducing undesirable blurring effects into image details
even at low noise densities. Since its application to impulse
noise removal, the median filter has been of research interest
and a number of rank order based filters trying to avoid the
inherent drawbacks of the standard median filter have been
investigated [4-7]. These filters yield better edges and fine
detail preservation performance than the median filter at the
expense of reduced noise suppression.
Conventional order statistics filters usually distort the
uncorrupted regions of the input image during restoration of
the corrupted regions, introducing undesirable blurring effects
into the image. In switching median filters, the noise detector
aims to determine whether the center pixel of a given filtering
window is corrupted or not. If the center pixel is identified by
the noise detector as corrupted, then the output of the system
is switched to the output of the noise filter, which has the
restored value for the corrupted pixel. if the center pixel is
identified as uncorrupted, which means that there is no need
to perform filtering, the noise removal operator is bypassed
and the output of the system is switched directly to the input.
This approach has been employed to significantly exploiting
different impulse detection mechanisms have been
investigated [8-25]. Existing switching median filters are
commonly found to be non-adaptive to noise density
variations and prone to misclassifying pixel characteristics.
This exposes the critical need to evolve a sophisticated
switching scheme and median filter. In order to improve
filtering performances, decision-based median filtering
schemes had been investigated. These techniques aim to
achieve optimal performance over the entire image. A good
noise filter is required to satisfy two criteria, namely,
suppressing the noise and preserving the useful information in
the signal. Unfortunately, a great majority of currently
available noise filters cannot simultaneously satisfy both of
these criteria. The existing filters either suppress the noise at
the cost of reduced noise suppression performance. In order to
address these issues, many neural networks have been
investigated for image denoising.
Neural networks are composed of simple elements operating
in parallel. These elements are inspired by biological nervous
systems. As in nature, the network function is determined
largely the connection between elements. This type of training
is used to perform a particular function by adjusting the values
of the connections (weights) between elements. Commonly
neural networks are adjusted or trained to a specific target
output which is based on a comparison of the output and the
target, until the network output matches the target. Typically
many such input-target pairs are needed to train a network. A
feed forward neural architecture with back propagation
learning algorithms have been investigated [26-34] to satisfy
both noise elimination and edges and fine details preservation
properties when digital images are contaminated by higher
level of impulse noise. Back propagation is a common method
of training artificial neural networks algorithm so as to
minimize the objective function. It is a multi-stage dynamic
system optimization method.
In addition to these, the back-propagation learning algorithm
is simple to implement and computationally efficient in which
its complexity is linear in the synaptic weights of the neural
2. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 262
network. The input-output relation of a feed forward adaptive
neural network can be viewed as a powerful nonlinear
mapping. Conceptually, a feed forward adaptive network is
actually a static mapping between its input and output spaces.
Even though, intelligent techniques required certain pattern of
data to learn the input. This filtered image data pattern is
given through nonlinear filter for training of the input.
Therefore, intelligent filter performance depends on
conventional filters performance. This work aims to achieving
good de-noising without compromising on the useful
information of the signal.
In this paper, a novel structure is proposed to eliminate the
impulse noise and preserves the edges and fine details of
digital images; a feed forward neural architecture with back
propagation learning algorithm is used and is referred as an
Neural Filtering Technique for restoring digital images. The
proposed intelligent filtering operation is carried out in two
stages. In first stage the corrupted image is filtered by
applying a special class of filtering technique. This filtered
image output data sequence and noisy image data sequence
are suitably combined with a feed forward neural (FFN)
network in the second stage. The internal parameters of the
feed forward neural network are adaptively optimized by
training of the feed forward back propagation algorithm.
The rest of the paper is organized as follows. Section 2
explains the structure of the proposed filter and its building
blocks. Section 3 discusses the results of the proposed filter
on different test images. 4 is the final section, presents the
conclusion.
2. PROPOSED FILTER
A feed forward neural network is a flexible system trained by
heuristic learning techniques derived from neural networks
can be viewed as a 3-layer neural network with weights and
activation functions. Fig. 1 shows the structure of the
proposed impulse noise removal filter. The proposed filter is
obtained by appropriately combining output image from new
tristate switching median filter with neural network. Learning
and understanding aptitude of neural network congregate
information from the two filters to compute output of the
system which is equal to the restored value of noisy input
pixel.
Fig. 1 Block diagram of proposed filter
The neural network learning procedure is used for the input-
output mapping which is based on learning the proposed filter
and the neural network utilizes back propagation algorithm.
The special class of filter is described in section
2.1 asymmetric trimmed median filter
Standard Median filtering scheme is subsequently used to
remove impulse noise and preserve edge and fine details on
digital images, depending on the characteristic of pixel.
According to the decision-mechanism, impulse noise is
identified within the filtering window. In this paper,
elimination of random valued impulse noise from digital
images and filtering operation is obtained in two decision
levels are as: 1) Action of “no filtering” is performed on the
uncorrupted pixels at the first decision level. In second
decision level, noisy pixels are removed as well as edges and
fine details are preserved on the digital image simultaneously.
This filtering operation is obtained by using median filtering
at the current pixel within the sliding window on digital
image. These values are the impulse noise intensity values. If
the current pixel is detected as an uncorrupted pixel and it is
left unaltered, otherwise, it is corrupted. Then median filter is
performed on it. In order to apply the proposed filter, the
corrupted and uncorrupted pixels in the selected filtering
window are separated and then numbers of uncorrupted pixels
are determined. The corrupted pixels in the image are detected
by checking the pixel element value in the dynamic range of
maximum (HNL) and minimum (LNL) respectively. Median
is calculated only for a number of uncorrupted pixels in
selected filtering window. Then the corrupted pixel is
replaced by this new median value. This condition is used to
preserves the Edges and fine details of the given image.
Consider an image of size M×N having 8-bit gray scale pixel
resolution. The steps involved in detecting the presence of an
impulse or not are described as follows:
Step 1) A two dimensional square filtering window of size 3 x
3 is slid over on a contaminated image x(i,j) from left to right,
top to bottom in a raster scan fashion.
, = , , , , , ,( , ) 1( , ) 0( , ) 1( , ) ( , )w i j X X X X Xn i j i j i j i j n i j (2.1)
where X0(i,j) (or X(i,j)) is the original central vector-valued pixel
at location (i,j). Impulse noise can appear because of a random
bit error on a communication channel. The source images are
corrupted only by random valued impulse noise in the
dynamic range of shades of salt (LNL) & pepper (HNL).
Step 2) In the given contaminated image, the central pixel
inside the 3x3 window is checked whether it is corrupted or
not. If the central pixel is identified as uncorrupted, it is left
unaltered. A 3 x 3 filter window w(i,j) centered around X0(i,j) is
considered for filtering and is given by
, = , , , , , ,4( , ) 1( , ) 0( , ) 1( , ) 4( , )w i j X X X X Xi j i j i j i j i j (2.2)
Step 3) If the central pixel is identified as corrupted,
determine the number of uncorrupted pixels in the selected
filtering window and median value is found among these
uncorrupted pixels. The corrupted pixel is replaced by this
median value.
Step 4) Then the window is moved to form a new set of
values, with the next pixel to be processed at the centre of the
window. This process is repeated until the last image pixel is
processed. Then the window is moved to form a new set of
values, with the next pixel to be processed at the centre of the
window. This process is repeated until the last image pixel is
processed. This filter output is one of input for neural network
training.
2.2 Feed forward Neural Network
Noisy
Imag
e
FeedForwardNeuralNetwork
Restored
Image
Convention
al
filter
Neural
filter
ATMF
3. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 263
In feed forward neural network, back propagation algorithm is
computationally effective and works well with optimization
and adaptive techniques, which makes it very attractive in
dynamic nonlinear systems. This network is popular general
nonlinear modeling tool because it is very suitable for tuning
by optimization and one to one mapping between input and
output data. The input-output relationship of the network is as
shown in Fig.2. In Fig.2 xm represents the total number of
input image pixels as data, nkl represents the number of
neurons in the hidden unit, k represents the number hidden
layer and l represents the number of neurons in each hidden
layer. A feed forward back propagation neural network
consists of three layers.
Fig.2 Feed Forward Neural Network Architecture
The first layer is referred as input layer and the second layer is
represents the hidden layer, has a tan sigmoid (tan-sig)
activation function is represented by
( ) tanh( )yi vi (2.3)
This function is a hyperbolic tangent which ranges from -1 to
1, yi is the output of the ith node (neuron) and vi is the
weighted sum of the input and the second layer or output
layer, has a linear activation function. Thus, the first layer
limits the output to a narrow range, from which the linear
layer can produce all values. The output of each layer can be
represented by
( )
1 ,1 ,1
Y f W X b
Nx NxM M N
( 2.4)
where Y is a vector containing the output from each of the N
neurons in each given layer, W is a matrix containing the
weights for each of the M inputs for all N neurons, X is a
vector containing the inputs, b is a vector containing the
biases and f(·) is the activation function for both hidden layer
and output layer.
The trained network was created using the neural
network toolbox from Matlab9b.0 release. In a back
propagation network, there are two steps during training. The
back propagation step calculates the error in the gradient
descent and propagates it backwards to each neuron in the
hidden layer. In the second step, depending upon the values of
activation function from hidden layer, the weights and biases
are then recomputed, and the output from the activated
neurons is then propagated forward from the hidden layer to
the output layer. The network is initialized with random
weights and biases, and was then trained using the Levenberq-
Marquardt algorithm (LM). The weights and biases are
updated according to
1
1 [ ]
T T
Dn Dn J J I J e
(2.5)
where Dn is a matrix containing the current weights and
biases, Dn+1 is a matrix containing the new weights and
biases, e is the network error, J is a Jacobian matrix
containing the first derivative of e with respect to the current
weights and biases. In the neural network case, it is a K-by-L
matrix, where K is the number of entries in our training set
and L is the total number of parameters (weights+biases) of
our network. It can be created by taking the partial derivatives
of each in respect to each weight, and has the form:
( , ) ( , )1 1
...
1
( , ) ( , )1 1
...
1
F x w F x w
w ww
J
F x w F x w
w ww
(2.6)
where F(xi,L) is the network function evaluated for the i-th
input vector of the training set using the weight vector L and
wj is the j-th element of the weight vector L of the network. In
traditional Levenberg-Marquardt implementations, the
jacobian is approximated by using finite differences,
Howerever, for neural networks, it can be computed very
effieciently by using the chain rule of calculus and the first
derivatives of the activation functions. For the least-squares
problem, the Hessian generally doesn't needs to be caclualted.
As stated earlier, it can be approximated by using the Jacobian
matrix with the formula:
T
H J J (2.7)
I is the identity matrix and µ is a variable that increases or
decreases based on the performance function. The gradient of
the error surface, g, is equal to JTe.
2.3 Training of the Feed Forward Neural
Network
Feed forward neural network is trained using back
propagation algorithm. There are two types of training or
learning modes in back propagation algorithm namely
sequential mode and batch mode respectively. In sequential
learning, a given input pattern is propagated forward and error
is determined and back propagated, and the weights are
updated. Whereas, in Batch mode learning; weights are
updated only after the entire set of training network has been
presented to the network. Thus the weight update is only
performed after every epoch. It is advantageous to accumulate
the weight correction terms for several patterns. Here batch
mode learning is used for training.
In addition, neural network recognizes certain pattern of data
only and also it entails difficulties to learn logically to identify
the error data from the given input image. In order to improve
the learning and understanding properties of neural network,
noisy image data and filtered output image data are introduced
for training. Noisy image data and filtered output data are
Hidden
Layer 1
n12
n1
n
x1
Trained
Data
n11
Input
Layer
x2
Output
Layer
.
.
.
4. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 264
considered as inputs for neural network training and noise free
image is considered as a target image for training of the neural
network. Back propagation is pertained as network training
principle and the parameters of this network are then
iteratively tuned. Once the training of the neural network is
completed, its internal parameters are fixed and the network is
combined with noisy image data and the nonlinear filter
output data to construct the proposed technique, as shown in
Fig.3. While training a neural network, network structure is
fixed and the unknown images are tested for given fixed
network structure respectively. The performance evaluation is
obtained through simulation results and shown to be superior
performance to other existing filtering techniques in terms of
impulse noise elimination and edges and fine detail
preservation properties.
The feed forward neural network used in the structure of the
proposed filter acts like a mixture operator and attempts to
construct an enhanced output image by combining the
information from the noisy image and asymmetric trimmed
median filter. The rules of mixture are represented by the
rules in the rule base of the neural network and the mixture
process is implemented by the mechanism of the neural
network. The feed forward neural network is trained by using
back propagation algorithm and the parameters of the neural
network are then iteratively tuned using the Levenberg–
Marquardt optimization algorithm, so as to minimize the
learning error, e. The neural network trained structure is
optimized and the tuned parameters are fixed for testing the
unknown images.
The internal parameters of the neural network are optimized
by training. Fig.3 represents the setup used for training and
here, based on definition, the parameters of this network are
iteratively optimized so that its output converges to original
noise free image and completely removes the noise from its
input image. The well known images are trained using this
neural network and the network structure is optimized. The
unknown images are tested using optimized neural network
structure.
Fig.3 Training of the Feed forward Neural Network
In order to get effective filtering performance, already existing
neural network filters are trained with image data and tested
using equal noise density. But in practical situation,
information about the noise density of the received signal is
unpredictable one. Therefore; in this paper, the neural network
architecture is trained using denoised three well known
images which are corrupted by adding different noise density
levels of 0.4, 0.45, 0.5 and 0.6 and also the network is trained
for different hidden layers with different number of neurons.
Noise density with 0.45 gave optimum solution for both lower
and higher level noise corruption. Therefore images are
corrupted with 45% of noise is selected for training. Then the
performance error of the given trained data and trained neural
network structure are observed for each network. Among
these neural network Structures, the trained neural network
structure with the minimum error level is selected (10-3
) and
this trained network structures are fixed for testing the
received image signal.
Network is trained for 22 different architectures and
corresponding network structure is fixed. PSNR is measured
on Lena test image for all architectures with various noise
densities. Among these, based on the maximum PSNR values;
selected architectures is summarized in table 4 for Lena image
corrupted with 50% impulse noise. Finally, the maximum
PSNR value with the neural network architecture of noise
density 0.45 and two hidden layers with 2 neurons for each
layer has been selected for training. Fig.4 shows the images
which are used for training. Three different images are used
for network. This noise density level is well suited for testing
the different noise level of unknown images in terms of
quantitative and qualitative metrics. The image shown in Fig.4
(a1, 2 and 3) are the noise free training image: cameraman
Baboonlion and ship. The size of an each training image is
256 x 256. The images in Fig.4 (b1,2 and 3) are the noisy
training images and is obtained by corrupting the noise free
training image by impulse noise of 45% noise density. The
image in Fig.4 (c1,2 and 3) are the trained images by neural
network. The images in Fig.4 (b) and (a) are employed as the
input and the target (desired) images during training,
respectively.
Fig.4 Performance of training image: (a1,2 and 3) original
images, (b1,2 and 3) images corrupted with 45% of noise and (c1,
2 and 3) trained images
2.4 Testing of unknown images using
trained structure of neural network
The optimized architecture that obtained the best performance
for training with three images has 196608 data in the input
layer, two hidden layers with 6 neurons for each layer and one
output layer. The network trained with 45% impulse noise
shows superior performance for testing under various noise
levels. Also, to ensure faster processing, only the corrupted
Noise free image as
Target image
Noisyimagefortraining
ATMF
Trainedimagedata
X
FeedForwardNeural
Networkstructurefortraining
t
a
e=t-a
a1
a2
b1
b2
c1
c2
c2
a3 b3 c2
b3a3
5. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 265
pixels from test images are identified and processed by the
optimized neural network structure. As the uncorrupted pixels
do not require further processing, they are directly taken as
the output.
The chosen network has been extensively tested for several
images with different level of impulse noise. Fig.5 shows the
exact procedure for taking corrupted data for testing the
received image signals for the proposed filter. In order to
reduce the computation time in real time implementation; in
the first stage, a special class of filter is applied on unknown
images and then pixels (data) from the outputs of noisy image
and an asymmetric trimmed median filter are obtained and
applied as inputs for optimized neural network structure for
testing; these pixels are corresponding to the pixel position of
the corrupted pixels on noisy image.
Fig.5 Testing of the images using optimized feed forward
adaptive neural network structure
At the same time, noise free pixels from input are directly
taken as output pixels. The tested pixels are replaced in the
same location on corrupted image instead of noisy pixels. The
most typical feature of the proposed filter offers excellent line,
edge, and fine detail preservation performance and also
effectively removes impulse noise from the image. Usually
conventional filters are giving denoised image output and then
these images are enhanced using these conventional outputs as
input for neural filter while these outputs are combined with
the network. Since, networks need certain pattern to learn and
understand the given data.
2.5 Filtering of the Noisy Image
The noisy input image is processed by sliding the 3x3 filtering
window on the image. This filtering window is considered for
the nonlinear filter. The window is started from the upper-left
corner of the noisy input image, and moved rightwards and
progressively downwards in a raster scanning fashion. For
each filtering window, the nine pixels contained within the
window of noisy image are first fed to the new tristate
switching median filter. Next, the center pixel of the filtering
window on noisy image, the output of the conventional
filtered output is applied to the appropriate input for the neural
network. Finally, the restored image is obtained at the output
of this network.
3. RESULTS AND DISCUSSION
The performance of the proposed filtering technique
for image quality enhancement is tested for various level
impulse noise densities. Four images are selected for testing
with size of 256 x 256 including Baboon, Lena, Pepper and
Ship. All test images are 8-bit gray level images. The
experimental images used in the simulations are generated by
contaminating the original images by impulse noise with
different level of noise density. The experiments are
especially designed to reveal the performances of the filters
for different image properties and noise conditions. The
performances of all filters are evaluated by using the peak
signal-to-noise ratio (PSNR) criterion, which is defined as
more objective image quality measurement and is given by
the equation (3.1)
2
255
10 log10PSNR
MSE
(3.1)
where
2
1
( ( , ) ( , )
1 1
M N
MSE x i j y i j
MN i j
(3.2)
Here, M and N represents the number of rows and column of
the image and ( , )x i j and ( , )y i j represents the original
and the restored versions of a corrupted test image,
respectively. Since all experiments are related with impulse
noise.
The experimental procedure to evaluate the performance of a
proposed filter is as follows: The noise density is varied from
10% to 90% with 10% increments. For each noise density
step, the four test images are corrupted by impulse noise with
that noise density. This generates four different experimental
images, each having the same noise density. These images are
restored by using the operator under experiment, and the
PSNR values are calculated for the restored output images. By
this method ten different PSNR values representing the
filtering performance of that operator for different image
properties, then this technique is separately repeated for all
noise densities from 10% to 90% to obtain the variation of the
average PSNR value of the proposed filter as a function of
noise density. The entire input data are normalized in to the
range of [0 1], whereas the output data is assigned to one for
the highest probability and zero for the lowest probability.
Table 1 PSNR obtained by applying proposed filter on Lena
image corrupted with 50 % of impulse noise
S.No
Neural network architecture
PSNRNo. of
hidden layers
No. of neuron
in each
hidden layer
Layer 1 Layer2 Layer3
1 1 5 - - 26.9162
2 1 7 - - 26.9538
3 1 9 - - 26.9056
4 1 10 - - 26.9466
5 1 12 - - 26.9365
6 1 14 - - 26.9323
7 2 22 - - 26.9030
8 2 2 2 - 27.1554
9 2 4 4 - 26.9619
10 2 5 5 - 26.9267
The architecture with two hidden layers and each hidden layer
has 2 neurons yielded the best performance. The various
parameters for the neural network training for all the patterns
are summarized in Table 2 and 3. In Table 2, Performance
Noisyimagefortesting
ATMF
Denoised
Image
pixels
using
FFNN
Network
Denoised
Image
Uncorrupted
pixels on
Noisy image
Pixels
extracted
from ATMF
corresponding
to the
corrupted
pixels position
on noisy image
Corrupted
pixels
extracted
from Noisy
image
FFNetworktrainedstructure
6. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 266
error is nothing but Mean square error (MSE). It is a sum of
the statistical bias and variance. The neural network
performance can be improved by reducing both the statistical
bias and the statistical variance. However there is a natural
trade-off between the bias and variance. Learning Rate is a
control parameter of training algorithms, which controls the
step size when weights are iteratively adjusted. The learning
rate is a constant in the algorithm of a neural network that
affects the speed of learning. It will apply a smaller or larger
proportion of the current adjustment to the previous weight If
LR is low, network will learn all information from the given
input data and it takes long time to learn. If it is high, network
will skip some information from the given input data and it
will make fast training. However lower learning rate gives
better performance than higher learning rate. The learning
time of a simple neural-network model is obtained through an
analytic computation of the Eigen value spectrum for the
Hessian matrix, which describes the second-order properties
of the objective function in the space of coupling coefficients.
The results are generic for symmetric matrices obtained by
summing outer products of random vectors.
Table 2 Optimized training parameters for feed forward neural
network
S.No Parameters Achieved
1 Performance error 0.00312
2 Learning Rate (LR) 0.01
3
No. of epochs taken
to meet
the performance goal
2500
4 Time taken to learn 1620 seconds
Table.3 Bias and Weight updation in optimized training
neural network
Hidden layer
Weight Bias
1st
Hidden
layer
Weights from
x1&2 to n11
-0.071;-0.22 0.266
Weights from
x1&2 to n12
-0.249;0.062 -3.049
2nd
Hidden
layer
Weights from
n1,2,..6 to n21
0.123;-4.701 -4.743
Weights from
n1,2,..6 to n22
184.4;2.151 -4.617
Output
layer
Weights from
n21 to o
-34.976
-0.982
Weights from
n22 to o
-0.062
In Fig.6 and Fig.7 represent Performance error graph for
error minimization and training state respectively. This
Learning curves produced by networks using non-random
(fixed-order) and random submission of training and also this
shows the error goal and error achieved by the neural
system. In order to prove the effectiveness of this filter,
existing filtering techniques are experimented and compared
with the proposed filter for visual perception and subjective
evaluation on Lena image including an Asymmetric Trimmed
Median Filter (ATMF) and proposed filter in Fig.8. Lena test
image contaminated with the impulse noise of various
densities are summarized in Table 3 for quantitative metrics
for different filtering techniques and compared with the
proposed filtering technique and is graphically illustrated in
Fig.9. This graphical illustration shows the performance
comparison of the proposed intelligent filter. This qualitative
measurement proves that the proposed filtering technique
outperforms the other filtering schemes for the noise densities
up to 50%.
Fig.6 Performance error graph for feed forward neural
network with back propagation algorithm
Fig. 7 Performance of gradient for feed Forward neural
network with back propagation algorithm
Fig.8 Subjective Performance comparison of the proposed
filter with other existing filters on test image Lena (a) Noise
(a) (b)
(c) (d)
7. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 267
free images, (b) image corrupted by 80% impulse noise, (c)
images restored by ATMF and (d) image restored by the
proposed filter
Table 3. Performance of PSNR for different filtering
techniques on Lena image corrupted with various % of
impulse noise
Noise
level
ATMF
(1-59, 196-
255)
Proposed
filter
(1-59, 196-
255)
10 33.3743 33.8700
20 31.7138 31.8925
30 30.3687 31.0138
40 28.6183 29.2464
5-0 26.7540 27.1554
60 24.5403 25.0490
70 23.1422 23.5807
80 21.8535 21.5282
90 19.5594 20.2367
The PSNR performance explores the quantitative
measurement. In order to check the performance of the feed
forward neural network, percentage improvement (PI) in
PSNR is also calculated for performance comparison between
conventional filters and proposed neural filter for Lena image
and is summarized in Table 4. This PI in PSNR is calculated
by the following equation 3.3.
100
PSNR PSNRNFCF
PI x
PSNRCF
(3.3)
where PI represents percentage in PSNR, PSNRCF represents
PSNR for conventional filter and PSNRNF represents PSNR
values for the designed neural filter.
Here, the conventional filters are combined with neural
network which gives the proposed filter, so that the
performance of conventional filter is improved.
10 20 30 40 50 60 70 80 90
18
20
22
24
26
28
30
32
34
Noise percentage
PSNR
RINE
proposed filter
Fig.9 PSNR obtained using proposed filter and compared with
existing filtering technique on Lena image corrupted with
different densities of impulse noise
Table 4. Percentage improvement in PSNR obtained on Lena
image corrupted with different level of impulse noise
Noise
%
Proposed
filter (PF)
ATMF
PI for
Proposed
filter
10 45.36 42.57 6.5539
20 40.23 38.87 3.4984
30 37.56 35.38 6.1616
40 34.93 33.17 5.3059
50 31.63 29.34 8.8275
60 27.52 25.75 6.8737
70 22.17 19.52 13.575
80 16.90 13.47 25.464
90 12.68 10.13 25.173
In Table 4, the summarized PSNR values for conventional
filters namely NF and DBSMF seem to perform well for
human visual perception when images are corrupted up to
30% of impulse noise. These filters performance are better for
quantitative measures when images are corrupted up to 50%
of impulse noise. In addition to these, image enhancement is
nothing but improving the visual quality of digital images for
some application. In order to improve the performance of
visual quality of image using these filters, image enhancement
as well as reduction in misclassification of pixels on a given
image is obtained by applying Feed forward neural network
with back propagation algorithm.
The summarized PSNR values in Table 4 for the proposed
neural filter appears to perform well for human visual
perception when images are corrupted up to 50% of impulse
noise. These filters performance are better for quantitative
measures when images are corrupted up to 70% of impulse
noise. PI is graphically illustrated in Fig.10.
10 20 30 40 50 60 70 80 90
20
22
24
26
28
30
32
34
Noise percentage
PIinPSNR
PI for proposed filter and compared with ATMF
Fig.10 PI in PSNR obtained on Lena image for the proposed
filter corrupted with various densities of mixed impulse noise
Digital images are nonstationary process; therefore depends
on properties of edges and homogenous region of the test
images, each digital images having different quantitative
measures. Fig.11 illustrate the subjective performance for
proposed filtering Technique for Baboon, Lena, Pepper and
Rice images: noise free image in first column, images
corrupted with 50% impulse noise in second column,
Images restored by proposed Filtering Technique in third
column. This will felt out the properties of digital images.
Performance of quantitative analysis is evaluated and is
summarized in Table.5. This is graphically illustrated in
Fig.12. This qualitative and quantitative measurement shows
that the proposed filtering technique outperforms the other
filtering schemes for the noise densities up to 50%. Since
there is an improvement in PSNR values of all images up to
8. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 268
50% while compare to PSNR values of conventional filters
output which are selected for inputs of the network training.
Fig.11 Performance of test images:(a1,2 and 3) original
images,(b1,2 and 3) images corrupted with 80% of noise and (d1,
2 and 3) images enhanced by proposed filter
Table 5 PSNR obtained for the proposed filter on different test
images with various densities of random valued impulse noise
Noise level
Images
Baboon Lena pepper Rice
10 28.45 33.87 37.38 35.26
20 26.86 31.89 35.95 33.16
30 24.79 31.01 35.16 32.10
40 23.94 29.24 32.67 30.64
50 22.23 27.15 31.93 28.90
60 21.40 25.05 29.05 27.04
70 19.46 23.58 27.44 25.42
80 17.41 21.53 25.47 23.47
90 15.67 20.24 24.84 22.82
10 20 30 40 50 60 70 80 90
15
20
25
30
35
40
Noise percentage
PSNR
Baboon
Lena
Pepper
Rice
Fig. 12 PSNR obtained by applying proposed filter technique
for different images corrupted with various densities of mixed
impulse noise
The qualitative and quantitative performance of Pepper and
Rice images are better than the other images for the noise
levels ranging from 10% to 50%. But for higher noise levels,
the Pepper image is better. The Baboon image seems to
perform poorly for higher noise levels. Based on the intensity
level or brightness level of the image, it is concluded that the
performance of the images like pepper, Lena, Baboon and
Rice will change. Since digital images are nonstationary
process. The proposed filtering technique is found to have
eliminated the impulse noise completely while preserving the
image features quite satisfactorily. This novel filter can be
used as a powerful tool for efficient removal of impulse noise
from digital images without distorting the useful information
in the image and gives more pleasant for visual perception.
In addition, it can be observed that the proposed filter for
image enhancement is better in preserving the edges and fine
details than the other existing filtering algorithm. It is
constructed by appropriately combining a two nonlinear filters
and a neural network. This technique is simple in
implementation and in training; the proposed operator may be
used for efficiently filtering any image corrupted by impulse
noise of virtually any noise density. It is concluded that the
proposed filtering technique can be used as a powerful tool for
efficient removal of impulse noise from digital images
without distorting the useful information within the image.
4. CONCLUSION
A neural filtering Technique is described in this paper for
image restoration. This filter is seen to be quite effective in
preserving image boundary and fine details of digital images
while eliminating random valued impulse noise. The
efficiency of the proposed filter is illustrated applying the
filter on various test images contaminated different levels of
noise. This filter outperforms the existing median based filter
in terms of objective and subjective measures. So that the
proposed filter output images are found to be pleasant for
visual perception.
REFERENCES
[1] J.Astola and P.Kuosmanen Fundamental of Nonlinear Digital
Filtering. NewYork:CRC, 1997.
[2] I.Pitasand .N.Venetsanooulos, Nonlinear Digital Filters:Principles
Applications. Boston, MA: Kluwer, 1990.
[3] W.K. Pratt, Digital Image Processing, Wiley, 1978.
[4] T.Chen, K.-K.Ma,andL.-H.Chen, “Tristate median filter for image
denoising”, IEEE Trans.Image Process., 1991, 8, (12), pp.1834-1838.
[5] Zhigang Zeng and Jun Wang, “Advances in Neural Network
Research and Applications”, Lecture notesm springer, 2010.
[6] M. Barni, V. Cappellini, and A. Mecocci, “Fast vector median filter
based on Euclidian norm approximation”, IEEE Signal Process. Lett.,
vol.1, no. 6, pp. 92– 94, Jun. 1994.
[7] Sebastian hoyos and Yinbo Li, “Weighted Median Filters Admitting
Complex -Valued Weights and their Optimization”, IEEE
transactions on Signal Processing, Oct. 2004, 52, (10), pp. 2776-
2787.
[8] E.Abreu, M.Lightstone, S.K.Mitra, and K. Arakawa, “A new
efficient approach for the removal of impulse noise from highly
corrupted images”,IEEE Trans. Image Processing, 1996, 5, (6), pp.
1012–1025.
b3
b2
b1 c1
c2
c3
b4 c4
a1
a2
a3
a4
9. International Journal of Computer Applications Technology and Research
Volume 2– Issue 3, 261 - 269, 2013
www.ijcat.com 269
[9] T.Sun and Y.Neuvo, “Detail preserving median filters in image
processing”, Pattern Recognition Lett., April 1994, 15, (4), pp.341-
347.
[10] Zhang and M.- A. Karim, “A new impulse detector for
switching median filters”, IEEE Signal Process. Lett., Nov. 2002,
9, (11), pp. 360–363.
[11] Z. Wang and D. Zhang, “Progressive Switching median filter for the
removal of impulse noise from highly corrupted images”, IEEE
Trans. Circuits Syst. II, Jan. 2002, 46, (1), pp.78–80.
[12] H.-L. Eng and K.-K. Ma, “Noise adaptive soft –switching median
filter,” IEEE Trans.Image Processing, , Feb. 2001, 10, (2), pp. 242–
25.
[13] Pei-Eng Ng and Kai - Kuang Ma, “A Switching median filter with
boundary Discriminative noise detection for extremely corrupted
images”, IEEE Transactions on image Processing, June 2006, 15, (6),
pp.1500-1516.
[14] Tzu – Chao Lin and Pao - Ta Yu, “salt – Pepper Impulse noise
detection”, Journal of Information science and engineering, June
2007, 4, pp189-198.
[15] E.Srinivasan and R.Pushpavalli, “ Multiple Thresholds Switching
Median Filtering for Eliminating Impulse Noise in Images”,
International conference on Signal Processing, CIT, Aug. 2007.
[16] R.Pushpavalli and E.Srinivasan, “Multiple Decision Based
Switching Median Filtering for Eliminating Impulse Noise with
Edge and Fine Detail preservation Properties”, International
conference on Signal Processing, CIT , Aug. 2007.
[17] Yan Zhouand Quan-huanTang, “Adaptive Fuzzy Median Filter for
Images Corrupted by Impulse Noise”, Congress on image and signal
processing, 2008, 3, pp. 265 – 269.
[18] Shakair Kaisar and Jubayer AI Mahmud, “ Salt and Pepper Noise
Detection and removal by Tolerance based selective Arithmetic
Mean Filtering Technique for image restoration”, IJCSNS, June
2008, 8,(6), pp. 309 – 313.
[19] T.C.Lin and P.T.Yu, “Adaptive two-pass median filter based on
support vector machine for image restoration ”, Neural Computation,
2004, 16, pp.333-354,
[20] Madhu S.Nair, K.Revathy, RaoTatavarti, "An Improved Decision
Based Algorithm For Impulse Noise Removal", Proceedings of
International Congress on Image and Signal Processing - CISP 2008,
IEEE Computer Society Press, Sanya, Hainan, China, May 2008, 1,
pp.426-431.
[21] V.Jayaraj and D.Ebenezer,“A New Adaptive Decision Based Robust
Statistics Estimation Filter for High Density Impulse Noise in
Images and Videos”, International conference on Control,
Automation, Communication and Energy conversion, June 2009, pp 1
- 6.
[22] Fei Duan and Yu – Jin Zhang,“A Highly Effective Impulse Noise
Detection Algorithm for Switching Median Filters”, IEEE Signal
processing Letters, July 2010, 17,(7), pp. 647 – 650.
[23] R.Pushpavalli and G.Sivaradje, “Nonlinear Filtering Technique for
Preserving Edges and Fine Details on Digital Image”, International
Journal of Electronics and Communication Engineering and
Technology, January 2012, 3, (1),pp29-40.
[24] R.Pushpavalli and E.Srinivasan, “Decision based Switching Median
Filtering Technique for Image Denoising”, CiiT International
journal of Digital Image Processing, Oct.2010, 2, (10), pp.405-410.
[25] R.Pushpavalli, E. Srinivasan and S.Himavathi, “A New Nonlinear
Filtering technique”, 2010 International Conference on Advances in
Recent Technologies in Communication and Computing, ACEEE,
Oct. 2010, pp1-4.
[26] R.Pushpavalli and G.Sivaradje, “New Tristate Switching Median
Filter for Image Enhancement” International Journal of Advanced
research and Engineering Technology, January-June 2012, 3, (1),
pp.55-65.
[27] A.Fabijanska and D.Sankowski, “Noise adaptive switching
median-based filter for impulse noise removal from extremely
corrupted images”, IET image processing, July 2010, 5, (5),
pp.472-480.
[28] S.Esakkirajan, T,Veerakumar, Adabala.N Subramanyam, and C.H.
Premchand, “Removal of High Density Salt & pepper Noise
Through Modified Decision based Unsymmetric Trimmed Median
Filter”, IEEE Signal processing letters, May 2011, 18, (5), pp.287-
290.
[29] A.L.Betker,T.Szturm, Z. oussavi1,“Application of Feed forward Back
propagation Neural Network to Center of Mass Estimation for Use in
a Clinical Environment”, IEEE Proceedings of Engineering in
Medicine and Biology Society, April 2004, Vol.3, 2714 – 2717.
[30] Chen Jindu and Ding Runtao Ding, “A Feed forward neural
Network for Image processing”, in IEEE proceedings of ICSP,
pp.1477-1480, 1996.
[31] Wei Qian, Huaidong Li, Maria Kallergi, Dansheng Song and
Laurence P. Clarke, “Adaptive Neural Network for Nuclear
Medicine Image Restoration”, Journal of VLSI Signal Processing,
vol. 18, 297–315, 1998, Kluwer Academic Publishers.
[32] R.Pushpavalli, G.Shivaradje, E. Srinivasan and S.Himavathi, “
Neural Based Post Processing Filtering Technique For Image Quality
Enhancement”, International Journal of Computer Applications,
January-2012.
[33] Gaurang Panchal , Amit Ganatra, Y P Kosta and Devyani Panchal,
“Forecasting Employee Retention Probability using Back Propagation
Neural Network Algorithm”, Second International Conference on
Machine Learning and Computing,2010, pp.248-251.
[34] Sudhansu kumar Misra, Ganpati panda and Sukadev mehar, “Cheshev
Functional link Artificial neural Networks for Denoising of Image
Corrupted by Salt & Pepper Noise”, International journal of rcent
Trends in Engineering, may 2009, 1, (1), pp.413-417.
[35] Weibin Hong, Wei Chen and Rui Zhang, “ The Application of Neural
Network in the Technology of Image processing”, Proceddings of the
International Conference of Engineers and Computer Sciences, 2009,
1.
[36] A new methos of denoising mixed noise using limited Grayscale
Pulsed Coupled Neural Network”, Cross Quad-Regional Radio
Science and Wireless Technology Conference, 2011, pp.1411-1413.
[37] Shamik Tiwari, Ajay kumar Singh and V.P.Shukla, “Staistical
Moments based Noise Classification using Feed Forward back
Peopagation neural Network”, International journal of Computer
Applications, March 2011, 18, (2), pp.36-40.
[38] Anurag Sharma, “ Gradient Descent Feed Forward Neural Networks
for Forecasting the Trajectories”, International Journal of Advanced
Science and Technology, September 2011, 34, pp.83-88.