This document describes experiments using artificial neural networks (ANNs) to forecast indoor temperature in a "domotic" smart home environment. ANNs were trained on historical temperature and time data, and evaluated on their ability to predict temperature values up to 3 hours in the future. Creating an ensemble model combining ANNs trained for different forecast horizons improved accuracy over individual models. The best-performing ensemble model achieved mean absolute errors between 0.027-0.352°C on validation and test data for forecasts up to 3 hours ahead.
Prototyping a Wireless Sensor Node using FPGA for Mines Safety ApplicationIDES Editor
The sensor nodes in a wireless sensor network are
normally microcontroller based which are having limited
computational capability related to various applications. This
paper describes the selection, specification and realization of
a wireless sensor node using the field programmable gate
array (FPGA) based architecture for an early detection of
hazards (e.g fire and gas-leak ) in mines area. The FPGAs in
it’s place are more efficient for complex computations in
compare to microcontrollers, which is tested by implementing
the adaptive algorithm for removing the noise in sensor
received data in our work. Another advantage of using FPGA
is also due to it’s reconfigurable feature without changing
the hardware itself. The node is implemented using cyclone
II FPGA device present in Altera dE2 board .In this work the
network comprises of 4 nodes out of which 2 are test nodes,
one routing node and one base station node. An energy
efficient MAC protocol is tested for transmitting the data from
test node to base station node.
This document discusses the coexistence of Zigbee and IEEE 802.11b wireless networks. It provides an overview of both technologies:
- Zigbee is based on the IEEE 802.15.4 standard and operates on the 2.4GHz band using low data rates. It focuses on low power consumption and supports wireless sensor networks.
- IEEE 802.11b defines the MAC and physical layers for wireless LANs. It uses the 2.4GHz band divided into overlapping channels and employs CCK modulation.
Operating in the same band causes interference between the networks. The document presents a model to study the impact of this interference on network performance, focusing on power and timing
Pairwise Keys Generation Using Prime Number Function in Wireless Sensor NetworksIDES Editor
Providing security in wireless sensor networks is
a very crucial task. Because of its dynamic nature (no fixed
topology) and resource constraint devices. Which has limited
computational abilities, memory storage and physical
restrictions. Advancement in the field of intrusion and
evaesdroping has increased challenges for a secure
communication between nodes. So, establishments of pair wise
keys in a wireless network becomes a vital issue. Hence,
securely distributing keys among sensor nodes is a
fundamental challenge for providing seamless transmission
and security services. Having little resources in our hand,
it is always a tough task to design and implement protocols.
But this paper proposes a new robust key pre-distribution
scheme which resolves this issue without compromising
security. This paper presents a new mechanism to achieve
pair wise keys between two sensor nodes by using the
algebraic, exponential, logarithm functions and prime
numbers. The resilience method under this scheme is based
on discontinuous functions which is hard to be spoofed.
CrimeSPOT: Language Support for Programming Interactions among Wireless Senso...Coen De Roover
CrimeSPOT is a domain-specific language for programming active wireless sensor network (WSN) applications using an event-based middleware. It aims to minimize accidental complexity so developers can focus on the essential complexity. CrimeSPOT allows specifying node interactions declaratively through rules and specifying which rules govern which nodes to enable reuse within and among WSN apps. It is tailored towards active WSN applications to handle issues like sensor readings expiration and subsumption as well as tracking reactions so they can be compensated if no longer warranted.
This document discusses several emerging technologies that could potentially be weaponized and become weapons of mass destruction (WMDs) between 2010-2075. These include smart dust, smart clothing, smart bacteria, gel computing, conscious botnets, information waves, optical brain computers, and a solar wind deflection gun. The document warns that advances in nanotechnology, biotechnology, information technology and cognitive science could enable new types of extremism, terrorism and pose catastrophic risks if not developed and applied carefully and ethically. Overall the document presents a vision of rapidly advancing future technologies and their potential for both benefit and misuse unless precautions are taken to guide their development responsibly.
SRS-NET Smart Resource Aware Multi Sensor NetworkPaolo Omero
The document describes a research project aimed at designing a smart, multi-sensor network capable of autonomously detecting and localizing various events through limited infrastructure. The network allows for reconfiguration based on resource usage and analyzes audio/video to recognize objects and sounds. It can then detect complex events by analyzing relationships between simple events and behaviors through an ontological model. Data is stored in a multimedia database to enable retrieval, analysis and alerting of operators.
Introduction to Modern Methods and Tools for Biologically Plausible Modelling...SSA KPI
This document summarizes research on biologically plausible modeling of neural structures in the brain. It discusses several key points:
1. Mathematical modeling is widely used to study the brain since physiological methods have limitations. The brain can be modeled at different levels, from single ion channels to large neural networks.
2. Models of neural structures like the Purkinje cell and the thalamo-cortical visual system have been developed with a high level of biological detail, including thousands of neurons and ion channels.
3. Research is exploring how neural circuits in the thalamus could underlie different sleep/wake states using modified integrate-and-fire neuron models. Coincidence detection and excitation-inhibition populations are
Cryptography using artificial neural networkMahira Banu
This document proposes using artificial neural networks for cryptography. It describes using a backpropagation neural network for decryption, where the network is trained on encrypted-decrypted message pairs. Boolean algebra is used for encryption, permuting messages and "doping" with additional bits. The neural network can then be used as a public key for decryption, with a private key for encryption. Simulation results showed the neural network approach weakened key guessing compared to other methods.
Prototyping a Wireless Sensor Node using FPGA for Mines Safety ApplicationIDES Editor
The sensor nodes in a wireless sensor network are
normally microcontroller based which are having limited
computational capability related to various applications. This
paper describes the selection, specification and realization of
a wireless sensor node using the field programmable gate
array (FPGA) based architecture for an early detection of
hazards (e.g fire and gas-leak ) in mines area. The FPGAs in
it’s place are more efficient for complex computations in
compare to microcontrollers, which is tested by implementing
the adaptive algorithm for removing the noise in sensor
received data in our work. Another advantage of using FPGA
is also due to it’s reconfigurable feature without changing
the hardware itself. The node is implemented using cyclone
II FPGA device present in Altera dE2 board .In this work the
network comprises of 4 nodes out of which 2 are test nodes,
one routing node and one base station node. An energy
efficient MAC protocol is tested for transmitting the data from
test node to base station node.
This document discusses the coexistence of Zigbee and IEEE 802.11b wireless networks. It provides an overview of both technologies:
- Zigbee is based on the IEEE 802.15.4 standard and operates on the 2.4GHz band using low data rates. It focuses on low power consumption and supports wireless sensor networks.
- IEEE 802.11b defines the MAC and physical layers for wireless LANs. It uses the 2.4GHz band divided into overlapping channels and employs CCK modulation.
Operating in the same band causes interference between the networks. The document presents a model to study the impact of this interference on network performance, focusing on power and timing
Pairwise Keys Generation Using Prime Number Function in Wireless Sensor NetworksIDES Editor
Providing security in wireless sensor networks is
a very crucial task. Because of its dynamic nature (no fixed
topology) and resource constraint devices. Which has limited
computational abilities, memory storage and physical
restrictions. Advancement in the field of intrusion and
evaesdroping has increased challenges for a secure
communication between nodes. So, establishments of pair wise
keys in a wireless network becomes a vital issue. Hence,
securely distributing keys among sensor nodes is a
fundamental challenge for providing seamless transmission
and security services. Having little resources in our hand,
it is always a tough task to design and implement protocols.
But this paper proposes a new robust key pre-distribution
scheme which resolves this issue without compromising
security. This paper presents a new mechanism to achieve
pair wise keys between two sensor nodes by using the
algebraic, exponential, logarithm functions and prime
numbers. The resilience method under this scheme is based
on discontinuous functions which is hard to be spoofed.
CrimeSPOT: Language Support for Programming Interactions among Wireless Senso...Coen De Roover
CrimeSPOT is a domain-specific language for programming active wireless sensor network (WSN) applications using an event-based middleware. It aims to minimize accidental complexity so developers can focus on the essential complexity. CrimeSPOT allows specifying node interactions declaratively through rules and specifying which rules govern which nodes to enable reuse within and among WSN apps. It is tailored towards active WSN applications to handle issues like sensor readings expiration and subsumption as well as tracking reactions so they can be compensated if no longer warranted.
This document discusses several emerging technologies that could potentially be weaponized and become weapons of mass destruction (WMDs) between 2010-2075. These include smart dust, smart clothing, smart bacteria, gel computing, conscious botnets, information waves, optical brain computers, and a solar wind deflection gun. The document warns that advances in nanotechnology, biotechnology, information technology and cognitive science could enable new types of extremism, terrorism and pose catastrophic risks if not developed and applied carefully and ethically. Overall the document presents a vision of rapidly advancing future technologies and their potential for both benefit and misuse unless precautions are taken to guide their development responsibly.
SRS-NET Smart Resource Aware Multi Sensor NetworkPaolo Omero
The document describes a research project aimed at designing a smart, multi-sensor network capable of autonomously detecting and localizing various events through limited infrastructure. The network allows for reconfiguration based on resource usage and analyzes audio/video to recognize objects and sounds. It can then detect complex events by analyzing relationships between simple events and behaviors through an ontological model. Data is stored in a multimedia database to enable retrieval, analysis and alerting of operators.
Introduction to Modern Methods and Tools for Biologically Plausible Modelling...SSA KPI
This document summarizes research on biologically plausible modeling of neural structures in the brain. It discusses several key points:
1. Mathematical modeling is widely used to study the brain since physiological methods have limitations. The brain can be modeled at different levels, from single ion channels to large neural networks.
2. Models of neural structures like the Purkinje cell and the thalamo-cortical visual system have been developed with a high level of biological detail, including thousands of neurons and ion channels.
3. Research is exploring how neural circuits in the thalamus could underlie different sleep/wake states using modified integrate-and-fire neuron models. Coincidence detection and excitation-inhibition populations are
Cryptography using artificial neural networkMahira Banu
This document proposes using artificial neural networks for cryptography. It describes using a backpropagation neural network for decryption, where the network is trained on encrypted-decrypted message pairs. Boolean algebra is used for encryption, permuting messages and "doping" with additional bits. The neural network can then be used as a public key for decryption, with a private key for encryption. Simulation results showed the neural network approach weakened key guessing compared to other methods.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2021/08/case-study-facial-detection-and-recognition-for-always-on-applications-a-presentation-from-synopsys/
Jamie Campbell, Product Marketing Manager for Embedded Vision IP at Synopsys, presents the “Case Study: Facial Detection and Recognition for Always-On Applications” tutorial at the May 2021 Embedded Vision Summit.
Although there are many applications for low-power facial recognition in edge devices, perhaps the most challenging to design are always-on, battery-powered systems that use facial recognition for access control. Laptop, tablet and cellphone users expect hands-free and instantaneous facial recognition. This means the electronics must be always on, constantly looking to detect a face, and then ready to pull from a data set to recognize the face.
This presentation describes the challenges of moving traditional facial detection neural networks to the edge. It explores a case study of a face recognition access control application requiring continuous operation and extreme energy efficiency. Finally, it describes how the combination of Synopsys DesignWare ARC EM and EV processors provides low-power, efficient DSP and CNN acceleration for this application.
Brain-Computer Interfacing, Consciousness, and the Global Brain: Towards the ...ringoring
Brain implants to increase intellectual capabilities, control machines using thought alone, or transfer information directly into the brain are quite popular in sci-fi and have been recently adopted as concrete research goals by many science and engineering teams around the world. Currently developed prototypes adopt a "black box" model - they do not allow the user to experience what is going on inside the implant. Our brain, however, doesn\'t only process sensory input and calculate appropriate behaviors based on it, but also enables us to experience what is happening. In other words, brain activity is accompanied by consciousness.
Potentially, brain chips can also be designed to have consciousness inside them. Inserted into a human brain, such a conscious implant would expand the user\'s conscious experience with its own contents. For this, however, a new kind of brain-machine interface should be developed that would merge consciousness in two separate systems - the chip and the brain - into single, unified one.
Progress in conscious interfaces could eventually allow us to unify consciousness of different human beings, leading to the emergence of special kind of global brain, in which every individual will experience itself being a GB, and won\'t become just one of the cogs in this huge super-intelligent system.
NeuroCrypto: C++ Implementation of Neural Cryptography with Rijndael CipherSagun Man Singh Shrestha
This work is the software implementation of the concept of neural cryptography, which is a communication of two tree parity machines for agreement on a common key over a public channel. This key is utilized to encrypt a sensitive message to be transmitted over an insecure channel using Rijndael cipher. This is a new potential source for public key cryptography schemes which are not based on number theoretic functions, and have small time and memory complexities. This paper will give a brief introduction to artificial neural networks, cryptography and its types, which will help explain why the two communicating terminals converge to a common key in neural cryptography and will also cover the Rijndael (AES) cipher. This paper is intended to show that such neural key exchange protocol and AES encryption can be practically implemented in a high-level programming language viz. C++, which could be further extended in higher-level applications. Both CLI and GUI implementations of the software created using Visual C++ (.NET framework) are presented.
From Physical to Virtual Wireless Sensor Networks using Cloud Computing IJORCS
In the modern world, billions of physical sensors are used for various dedications: Environment Monitoring, Healthcare, Education, Defense, Manufacturing, Smart Home, Agriculture Precision and others. Nonetheless, they are frequently utilized by their own applications and thereby snubbing the significant possibilities of sharing the resources in order to ensure the availability and performance of physical sensors. This paper assumes that the immense power of the Cloud can only be fully exploited if it is impeccably integrated into our physical lives. The principal merit of this work is a novel architecture where users can share several types of physical sensors easily and consequently many new services can be provided via a virtualized structure that allows allocation of sensor resources to different users and applications under flexible usage scenarios within which users can easily collect, access, process, visualize, archive, share and search large amounts of sensor data from different applications. Moreover, an implementation has been achieved using Arduino-Atmega328 as hardware platform and Eucalyptus/Open Stack with Orchestra-Juju for Private Sensor Cloud. Then this private Cloud has been connected to some famous public clouds such as Amazon EC2, ThingSpeak, SensorCloud and Pachube. The testing was successful at 80%. The recommendation for future work would be to improve the effectiveness of virtual sensors by applying optimization techniques and other methods.
Concealed Data Aggregation with Dynamic Intrusion Detection System to Remove ...csandit
Data Aggregation is a vital aspect in WSNs (Wireless Sensor Networks) and this is because it
reduces the quantity of data to be transmitted over the complex network. In earlier studies
authors used homomorphic encryption properties for concealing statement during aggregation
such that encrypted data can be aggregated algebraically without decrypting them. These
schemes are not applicable for multi applications which lead to proposal of Concealed Data
Aggregation for Multi Applications (CDAMA). It is designed for multi applications, as it
provides secure counting ability. In wireless sensor networks SN are unarmed and are
susceptible to attacks. Considering the defence aspect of wireless environment we have used
DYDOG (Dynamic Intrusion Detection Protocol Model) and a customized key generation
procedure that uses Digital Signatures and also Two Fish Algorithms along with CDAMA for
augmentation of security and throughput. To prove our proposed scheme’s robustness and
effectiveness, we conducted the simulations, inclusive analysis and comparisons at the ending.
Deep learning and neural networks are inspired by biological neurons. Artificial neural networks (ANN) can have multiple layers and learn through backpropagation. Deep neural networks with multiple hidden layers did not work well until recent developments in unsupervised pre-training of layers. Experiments on MNIST digit recognition and NORB object recognition datasets showed deep belief networks and deep Boltzmann machines outperform other models. Deep learning is now widely used for applications like computer vision, natural language processing, and information retrieval.
The document provides an introduction to neuromorphic computing and discusses General Vision's CM1K neuromorphic processing chip. Some key points:
- Neuromorphic chips are inspired by the human brain and consist of numerous simple processors that operate in parallel at very low power. This contrasts with traditional CPU/GPU architectures.
- The CM1K chip contains 1024 neural processing units that classify patterns in constant time using a radial basis function network. Multiple chips can be combined for more processing power.
- Testing on the MNIST handwritten digit dataset showed the CM1K achieving over 90% accuracy with 60,000 training examples. Applying translations to unknown images improved accuracy but hurt precision.
This document provides an overview of wireless sensor networks, including their architecture, requirements, and differences from conventional networks. Wireless sensor networks consist of dense deployments of sensor nodes that self-organize into a collaborative network. The nodes have stringent limitations on energy, computing power, and bandwidth. They monitor physical conditions and transmit aggregated sensor data in a multi-hop fashion to sink nodes for collection and analysis. Routing protocols are critical given the constraints of wireless sensor networks.
The document discusses keystroke authentication using local search algorithms. It proposes using an individual's typing pattern and measuring the time period between keystrokes. A local search algorithm is presented as an alternative to k-means clustering for representing each user's typing pattern as a cluster that can be differentiated from other users. The local search algorithm directly minimizes an error function through iterative local searching along decent directions, requiring only a forward path without backpropagation. This makes it simpler to implement than backpropagation-based methods. Experimental results found local search algorithms can provide effective keystroke authentication.
This document summarizes sensor networks, including their definition, components, applications, characteristics, architectures, challenges, and security approaches. Sensor networks consist of spatially distributed nodes that monitor environmental conditions and pass data to a central location. The nodes have sensors, microcontrollers, memory, and radios. Applications include area monitoring, healthcare, and environmental monitoring. Challenges include limited energy, computation, and transmission range. PEGASIS is an approach that forms nodes into chains to more efficiently pass data to the base station and minimize energy use. Security is provided using secret key encryption algorithms.
This document presents a proposal for a final year project that uses convolutional neural networks for hand gesture recognition to control devices in a home automation system. The proposal outlines introducing CNNs and home automation, the problem of accurately recognizing hand gestures, and the aims to develop an accurate and user-friendly gesture recognition system to control devices. The methodology describes collecting and preprocessing training data, configuring and training the CNN model in Python using common libraries, and deploying the trained model. Expected results are for the system to be highly accurate, fast, robust, user-friendly, and efficient to run on low-power IoT devices. A project cost estimate and timeline are also provided.
This document provides an overview of Mahdi Hosseini Moghaddam's background and work applying machine learning and cognitive computing for intrusion detection. It discusses his education in computer science and engineering and awards. It then outlines the goals of the presentation to discuss real-world applications of machine learning rather than scientific details. The document proceeds to discuss problems with current intrusion detection systems, introduce concepts in machine learning and cognitive computing, and describe Mahdi's methodology and architecture for a hardware-based machine learning system using a cognitive processor to enable fast intrusion detection.
This document is a homework assignment from a distributed systems course. It is divided into 4 parts that define distributed systems, discuss their evolution and architectures, and provide examples of application fields. The 3 students listed submitted this homework on distributed systems.
This document compares Elliptic Curve Cryptography (ECC) and Elliptic Curve Integrated Encryption Scheme (ECIES) for securing patient privacy in wireless body sensor networks. Both techniques can encrypt patient health record data collected from sensors. ECC encrypts/decrypts data using elliptic curve operations, while ECIES is a hybrid scheme that uses elliptic curves for key exchange and symmetric encryption to encrypt messages. The document analyzes the implementation of ECC and ECIES on body sensor networks and concludes that ECIES requires less storage space and computation time compared to ECC for encrypting data from multiple patients.
This document summarizes a research paper that proposes using a Hamming network to recognize noisy numerals. Specifically:
1) The paper aims to design a system that can recognize both clean and noisy (corrupted by salt and pepper noise) numerals using a Hamming network.
2) The Hamming network contains a feedforward layer to calculate correlations between input and prototype patterns, and a recurrent layer that determines the closest prototype.
3) Test results showed the network could recognize clean numerals with 100% accuracy and noisy numerals with an average of 89% accuracy.
The document discusses a wireless sensor network project that involves collecting sensor data from nodes in the network. It describes the architecture of the sensor nodes and how they communicate with a base station. The project involves nodes sensing data, storing it locally, and aggregating it before the base station fetches and displays the results. The nodes use Zigbee networking and MSP430 microcontrollers to sense temperature and other environmental data. Future work includes improving data aggregation and displaying results on smartphones.
This document contains a list of 13 titles from the IEEE Transactions on Embedded Systems journal from 2015. The titles cover a range of topics related to embedded systems including secure cyber-physical systems, automotive system security and mapping, interrupt controllers for real-time systems, network-on-chip protection against time-driven attacks, on-chip communication comparisons, scheduling for reconfigurable platforms, FPGA protection against hardware trojans, approximate computing using partially-forgetful memories, sustaining computation during intermittent supply, thermal management impacts in mobile devices, on-chip temperature estimation using virtual sensors, hierarchical high-level synthesis design space exploration, and a NoC router estimation tool.
The Global Environment for Network Innovations (GENI) is a virtual laboratory that aims to explore the future of the internet by understanding global networks and their relationship to society, innovating beyond the boundaries of science and engineering, and transforming network research and society as a whole. GENI supports large-scale research through a shared, heterogeneous infrastructure and enables in-depth configuration to promote innovation. It provides a collaborative environment for institutions and companies to foster discoveries and innovations. GENI includes programmable nodes, virtualization of resources, and an ecosystem of different organizations contributing resources in the form of slices across various locations.
This document proposes pluggable real world interfaces that allow objects to have embedded software and sensors. It describes a two-step approach where real world interfaces with hardware are first deployed to objects, giving them awareness of their context, and then logic can be deployed through a network. This would allow objects like chairs to have code stored in them to recognize their state and interact in an office environment. The implementation uses small sensor nodes and a Java virtual machine to execute code on the objects. An evaluation shows the overhead is small and sensors can easily fit on low-cost memory. The conclusion is that context-awareness can be achieved by storing code in physical objects, and embedded systems can benefit from virtual machine abstraction.
This document discusses a research project using MEMS "smart dust motes" for intelligent lighting control. The goals are to use wireless sensor networks to better understand occupancy patterns, validate sensor readings, and optimize lighting for energy savings while considering user preferences. Researchers plan to characterize mote sensors, develop validation and fusion algorithms, and eventually implement a smart lighting system in the BEST Lab to automatically control dimming based on human presence and interactions. This would personalize lighting while reducing electricity costs.
This document summarizes a wireless sensor network system implemented by the authors. The system uses 4 sensor nodes to sense temperature and a control node interfaced with a base station PC. It implements a modified version of the TOPDISC topology discovery algorithm using DHCP for dynamic addressing. The routing algorithm uses a mixture of spanning tree and N-link state protocols. Future enhancements include implementing fail safes and fully configuring the wireless sensor network system.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2021/08/case-study-facial-detection-and-recognition-for-always-on-applications-a-presentation-from-synopsys/
Jamie Campbell, Product Marketing Manager for Embedded Vision IP at Synopsys, presents the “Case Study: Facial Detection and Recognition for Always-On Applications” tutorial at the May 2021 Embedded Vision Summit.
Although there are many applications for low-power facial recognition in edge devices, perhaps the most challenging to design are always-on, battery-powered systems that use facial recognition for access control. Laptop, tablet and cellphone users expect hands-free and instantaneous facial recognition. This means the electronics must be always on, constantly looking to detect a face, and then ready to pull from a data set to recognize the face.
This presentation describes the challenges of moving traditional facial detection neural networks to the edge. It explores a case study of a face recognition access control application requiring continuous operation and extreme energy efficiency. Finally, it describes how the combination of Synopsys DesignWare ARC EM and EV processors provides low-power, efficient DSP and CNN acceleration for this application.
Brain-Computer Interfacing, Consciousness, and the Global Brain: Towards the ...ringoring
Brain implants to increase intellectual capabilities, control machines using thought alone, or transfer information directly into the brain are quite popular in sci-fi and have been recently adopted as concrete research goals by many science and engineering teams around the world. Currently developed prototypes adopt a "black box" model - they do not allow the user to experience what is going on inside the implant. Our brain, however, doesn\'t only process sensory input and calculate appropriate behaviors based on it, but also enables us to experience what is happening. In other words, brain activity is accompanied by consciousness.
Potentially, brain chips can also be designed to have consciousness inside them. Inserted into a human brain, such a conscious implant would expand the user\'s conscious experience with its own contents. For this, however, a new kind of brain-machine interface should be developed that would merge consciousness in two separate systems - the chip and the brain - into single, unified one.
Progress in conscious interfaces could eventually allow us to unify consciousness of different human beings, leading to the emergence of special kind of global brain, in which every individual will experience itself being a GB, and won\'t become just one of the cogs in this huge super-intelligent system.
NeuroCrypto: C++ Implementation of Neural Cryptography with Rijndael CipherSagun Man Singh Shrestha
This work is the software implementation of the concept of neural cryptography, which is a communication of two tree parity machines for agreement on a common key over a public channel. This key is utilized to encrypt a sensitive message to be transmitted over an insecure channel using Rijndael cipher. This is a new potential source for public key cryptography schemes which are not based on number theoretic functions, and have small time and memory complexities. This paper will give a brief introduction to artificial neural networks, cryptography and its types, which will help explain why the two communicating terminals converge to a common key in neural cryptography and will also cover the Rijndael (AES) cipher. This paper is intended to show that such neural key exchange protocol and AES encryption can be practically implemented in a high-level programming language viz. C++, which could be further extended in higher-level applications. Both CLI and GUI implementations of the software created using Visual C++ (.NET framework) are presented.
From Physical to Virtual Wireless Sensor Networks using Cloud Computing IJORCS
In the modern world, billions of physical sensors are used for various dedications: Environment Monitoring, Healthcare, Education, Defense, Manufacturing, Smart Home, Agriculture Precision and others. Nonetheless, they are frequently utilized by their own applications and thereby snubbing the significant possibilities of sharing the resources in order to ensure the availability and performance of physical sensors. This paper assumes that the immense power of the Cloud can only be fully exploited if it is impeccably integrated into our physical lives. The principal merit of this work is a novel architecture where users can share several types of physical sensors easily and consequently many new services can be provided via a virtualized structure that allows allocation of sensor resources to different users and applications under flexible usage scenarios within which users can easily collect, access, process, visualize, archive, share and search large amounts of sensor data from different applications. Moreover, an implementation has been achieved using Arduino-Atmega328 as hardware platform and Eucalyptus/Open Stack with Orchestra-Juju for Private Sensor Cloud. Then this private Cloud has been connected to some famous public clouds such as Amazon EC2, ThingSpeak, SensorCloud and Pachube. The testing was successful at 80%. The recommendation for future work would be to improve the effectiveness of virtual sensors by applying optimization techniques and other methods.
Concealed Data Aggregation with Dynamic Intrusion Detection System to Remove ...csandit
Data Aggregation is a vital aspect in WSNs (Wireless Sensor Networks) and this is because it
reduces the quantity of data to be transmitted over the complex network. In earlier studies
authors used homomorphic encryption properties for concealing statement during aggregation
such that encrypted data can be aggregated algebraically without decrypting them. These
schemes are not applicable for multi applications which lead to proposal of Concealed Data
Aggregation for Multi Applications (CDAMA). It is designed for multi applications, as it
provides secure counting ability. In wireless sensor networks SN are unarmed and are
susceptible to attacks. Considering the defence aspect of wireless environment we have used
DYDOG (Dynamic Intrusion Detection Protocol Model) and a customized key generation
procedure that uses Digital Signatures and also Two Fish Algorithms along with CDAMA for
augmentation of security and throughput. To prove our proposed scheme’s robustness and
effectiveness, we conducted the simulations, inclusive analysis and comparisons at the ending.
Deep learning and neural networks are inspired by biological neurons. Artificial neural networks (ANN) can have multiple layers and learn through backpropagation. Deep neural networks with multiple hidden layers did not work well until recent developments in unsupervised pre-training of layers. Experiments on MNIST digit recognition and NORB object recognition datasets showed deep belief networks and deep Boltzmann machines outperform other models. Deep learning is now widely used for applications like computer vision, natural language processing, and information retrieval.
The document provides an introduction to neuromorphic computing and discusses General Vision's CM1K neuromorphic processing chip. Some key points:
- Neuromorphic chips are inspired by the human brain and consist of numerous simple processors that operate in parallel at very low power. This contrasts with traditional CPU/GPU architectures.
- The CM1K chip contains 1024 neural processing units that classify patterns in constant time using a radial basis function network. Multiple chips can be combined for more processing power.
- Testing on the MNIST handwritten digit dataset showed the CM1K achieving over 90% accuracy with 60,000 training examples. Applying translations to unknown images improved accuracy but hurt precision.
This document provides an overview of wireless sensor networks, including their architecture, requirements, and differences from conventional networks. Wireless sensor networks consist of dense deployments of sensor nodes that self-organize into a collaborative network. The nodes have stringent limitations on energy, computing power, and bandwidth. They monitor physical conditions and transmit aggregated sensor data in a multi-hop fashion to sink nodes for collection and analysis. Routing protocols are critical given the constraints of wireless sensor networks.
The document discusses keystroke authentication using local search algorithms. It proposes using an individual's typing pattern and measuring the time period between keystrokes. A local search algorithm is presented as an alternative to k-means clustering for representing each user's typing pattern as a cluster that can be differentiated from other users. The local search algorithm directly minimizes an error function through iterative local searching along decent directions, requiring only a forward path without backpropagation. This makes it simpler to implement than backpropagation-based methods. Experimental results found local search algorithms can provide effective keystroke authentication.
Similar to Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment - KDIR 2012
This document summarizes sensor networks, including their definition, components, applications, characteristics, architectures, challenges, and security approaches. Sensor networks consist of spatially distributed nodes that monitor environmental conditions and pass data to a central location. The nodes have sensors, microcontrollers, memory, and radios. Applications include area monitoring, healthcare, and environmental monitoring. Challenges include limited energy, computation, and transmission range. PEGASIS is an approach that forms nodes into chains to more efficiently pass data to the base station and minimize energy use. Security is provided using secret key encryption algorithms.
This document presents a proposal for a final year project that uses convolutional neural networks for hand gesture recognition to control devices in a home automation system. The proposal outlines introducing CNNs and home automation, the problem of accurately recognizing hand gestures, and the aims to develop an accurate and user-friendly gesture recognition system to control devices. The methodology describes collecting and preprocessing training data, configuring and training the CNN model in Python using common libraries, and deploying the trained model. Expected results are for the system to be highly accurate, fast, robust, user-friendly, and efficient to run on low-power IoT devices. A project cost estimate and timeline are also provided.
This document provides an overview of Mahdi Hosseini Moghaddam's background and work applying machine learning and cognitive computing for intrusion detection. It discusses his education in computer science and engineering and awards. It then outlines the goals of the presentation to discuss real-world applications of machine learning rather than scientific details. The document proceeds to discuss problems with current intrusion detection systems, introduce concepts in machine learning and cognitive computing, and describe Mahdi's methodology and architecture for a hardware-based machine learning system using a cognitive processor to enable fast intrusion detection.
This document is a homework assignment from a distributed systems course. It is divided into 4 parts that define distributed systems, discuss their evolution and architectures, and provide examples of application fields. The 3 students listed submitted this homework on distributed systems.
This document compares Elliptic Curve Cryptography (ECC) and Elliptic Curve Integrated Encryption Scheme (ECIES) for securing patient privacy in wireless body sensor networks. Both techniques can encrypt patient health record data collected from sensors. ECC encrypts/decrypts data using elliptic curve operations, while ECIES is a hybrid scheme that uses elliptic curves for key exchange and symmetric encryption to encrypt messages. The document analyzes the implementation of ECC and ECIES on body sensor networks and concludes that ECIES requires less storage space and computation time compared to ECC for encrypting data from multiple patients.
This document summarizes a research paper that proposes using a Hamming network to recognize noisy numerals. Specifically:
1) The paper aims to design a system that can recognize both clean and noisy (corrupted by salt and pepper noise) numerals using a Hamming network.
2) The Hamming network contains a feedforward layer to calculate correlations between input and prototype patterns, and a recurrent layer that determines the closest prototype.
3) Test results showed the network could recognize clean numerals with 100% accuracy and noisy numerals with an average of 89% accuracy.
The document discusses a wireless sensor network project that involves collecting sensor data from nodes in the network. It describes the architecture of the sensor nodes and how they communicate with a base station. The project involves nodes sensing data, storing it locally, and aggregating it before the base station fetches and displays the results. The nodes use Zigbee networking and MSP430 microcontrollers to sense temperature and other environmental data. Future work includes improving data aggregation and displaying results on smartphones.
This document contains a list of 13 titles from the IEEE Transactions on Embedded Systems journal from 2015. The titles cover a range of topics related to embedded systems including secure cyber-physical systems, automotive system security and mapping, interrupt controllers for real-time systems, network-on-chip protection against time-driven attacks, on-chip communication comparisons, scheduling for reconfigurable platforms, FPGA protection against hardware trojans, approximate computing using partially-forgetful memories, sustaining computation during intermittent supply, thermal management impacts in mobile devices, on-chip temperature estimation using virtual sensors, hierarchical high-level synthesis design space exploration, and a NoC router estimation tool.
The Global Environment for Network Innovations (GENI) is a virtual laboratory that aims to explore the future of the internet by understanding global networks and their relationship to society, innovating beyond the boundaries of science and engineering, and transforming network research and society as a whole. GENI supports large-scale research through a shared, heterogeneous infrastructure and enables in-depth configuration to promote innovation. It provides a collaborative environment for institutions and companies to foster discoveries and innovations. GENI includes programmable nodes, virtualization of resources, and an ecosystem of different organizations contributing resources in the form of slices across various locations.
This document proposes pluggable real world interfaces that allow objects to have embedded software and sensors. It describes a two-step approach where real world interfaces with hardware are first deployed to objects, giving them awareness of their context, and then logic can be deployed through a network. This would allow objects like chairs to have code stored in them to recognize their state and interact in an office environment. The implementation uses small sensor nodes and a Java virtual machine to execute code on the objects. An evaluation shows the overhead is small and sensors can easily fit on low-cost memory. The conclusion is that context-awareness can be achieved by storing code in physical objects, and embedded systems can benefit from virtual machine abstraction.
This document discusses a research project using MEMS "smart dust motes" for intelligent lighting control. The goals are to use wireless sensor networks to better understand occupancy patterns, validate sensor readings, and optimize lighting for energy savings while considering user preferences. Researchers plan to characterize mote sensors, develop validation and fusion algorithms, and eventually implement a smart lighting system in the BEST Lab to automatically control dimming based on human presence and interactions. This would personalize lighting while reducing electricity costs.
This document summarizes a wireless sensor network system implemented by the authors. The system uses 4 sensor nodes to sense temperature and a control node interfaced with a base station PC. It implements a modified version of the TOPDISC topology discovery algorithm using DHCP for dynamic addressing. The routing algorithm uses a mixture of spanning tree and N-link state protocols. Future enhancements include implementing fail safes and fully configuring the wireless sensor network system.
The document introduces the National Supercomputer Center in Tianjin (NSCC-TJ) and its TH-1A supercomputer system. It describes that NSCC-TJ is sponsored by the Chinese government to provide high performance computing services. It then provides details about the TH-1A system including its hybrid CPU and GPU architecture, proprietary interconnect network, 262TB of memory and 2PB of storage. It also summarizes the system's software stack including the Kylin Linux operating system, compilers, programming environment and visualization system.
Energy-Efficient Protocol for Deterministic and Probabilistic Coverage In Sen...ambitlick
The document proposes a new probabilistic coverage protocol (PCP) for sensor networks that can employ different sensing models. PCP aims to address the costly task of designing and testing different coverage protocols for each sensing model. It works with common disk sensing models as well as probabilistic sensing models with minimal changes. Simulation results show that PCP outperforms other deterministic and probabilistic protocols in terms of number of activated sensors, total energy consumed, and network lifetime while being robust against failures and inaccuracies.
Energy-Efficient Protocol for Deterministic and Probabilistic Coverage In Sen...ambitlick
The document proposes a new probabilistic coverage protocol (PCP) for sensor networks that can employ different sensing models. PCP aims to address the costly task of designing and testing different coverage protocols for each sensing model. It works with common disk sensing models as well as probabilistic sensing models with minimal changes. Simulation results show that PCP outperforms other deterministic and probabilistic protocols in terms of number of activated sensors, total energy consumed, and network lifetime while being robust against failures and inaccuracies.
This document contains instructions for conducting network simulation experiments using the NCTUns simulator. It discusses setting up NCTUns, drawing network topologies, editing node properties, running simulations, and performing post-analysis. Experiment 1 involves simulating a 3-node point-to-point network with duplex links, varying the bandwidth, and measuring the number of dropped packets. The steps provided outline how to draw the topology in NCTUns and configure the nodes before running the simulation.
International Refereed Journal of Engineering and Science (IRJES)irjes
International Refereed Journal of Engineering and Science (IRJES) is a leading international journal for publication of new ideas, the state of the art research results and fundamental advances in all aspects of Engineering and Science. IRJES is a open access, peer reviewed international journal with a primary objective to provide the academic community and industry for the submission of half of original research and applications
International Refereed Journal of Engineering and Science (IRJES)irjes
International Refereed Journal of Engineering and Science (IRJES) is a leading international journal for publication of new ideas, the state of the art research results and fundamental advances in all aspects of Engineering and Science. IRJES is a open access, peer reviewed international journal with a primary objective to provide the academic community and industry for the submission of half of original research and applications
Design & implementation of phasor data concentrator compliant to ieee c37.118...Nitesh Pandit
The use of synchrophasors for monitoring and improving the stability of power transmission networks is gaining in significance all over the world. The aim is to monitor the system state, to intensify awareness for system stability and to make optimal use of existing lines. This way, system stability can be improved overall and even the transmission performance can be increased. The data from so many PMU’s and PDC’s needs to be collected and directed to proper channels for its efficient use. Thus we need to develop an efficient, flexible and hybrid data concentrator that can serve this purpose. Besides accepting the data from PMU’s, PDC should be able to accept the data also from other PDC. We have designed such a PDC (iPDC) that accepts data from PMU & PDC that are IEEEC37.118 standard compliant.
WAMS architecture with iPDC and PMU at different levels. This architecture enables iPDC to receive data either from a PMU or other iPDC. Both PMU and iPDC from whom the data is being received should be IEEE C37.118 synchrophasor standard compliant. It is hybrid architecture.
iPDC Design
The client server architecture is common in networks when two peers are communicating with each other. Of the two peers (PMU and iPDC) that are communicating with each other in WAMS one acts as a client and the other as a server. Since PMU saves the requests coming
from iPDC by sending data or configuration frames it acts as a server. It listens for command frames from iPDC. PMU-iPDC communication can be either over TCP or UDP communication protocols. On receiving command frames, PMU replies to the iPDC with data or configuration frames according to the type of request.
iPDC functionality is bifurcated as server and client. iPDC as a Client - When iPDC receives data or configuration frames its acts as a client. When acting as a client, it creates a new thread for each PMU or a PDC from whom it is going to receive data/configuration frames. This thread would establish connection between the two communication entities. It handles both TCP and UDP connections. The first frame that the server (PMU/PDC) would receive is the command for sending the configuration frame. When the server replies with the configuration frame, iPDC (client) would generate another request to start sending the data frames. On receiving
such a command frame, the server starts sending the data frames. If there is some change in the status bits of data frame which the client (iPDC) notices, it would take an action. For example if it notices a bit 10 has been set, it would internally send a command to server to send the latest configuration frame.
iPDC as a Server- When iPDC receives command frames from another PDC it would acts as a server. There would be two reserved ports one for UDP and other for TCP on which the PDC would receive command frame requests. Thus PDC now plays the role of PMU waiting
for command frames.
This document describes the design and implementation of a Phasor Data Concentrator (PDC) compliant with the IEEE C37.118 synchrophasor standard for use in a Wide Area Measurement System. It presents the features of the implemented PDC (iPDC) including support for TCP/UDP communication, authentication and integrity checking of received data frames, local data storage, and a GUI. It also discusses the iPDC design including handling of different frame types, time alignment of data, and database storage. Experimental results demonstrate the iPDC's performance in various test cases.
Similar to Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment - KDIR 2012 (20)
Training Deep Neural Networks has been a difficult task for a long time. Recently diverse approaches have been presented to tackle these difficulties, showing that deep models improve the performance of shallow ones in some areas like signal processing, signal classification or signal segmentation, whatever type of signals, e.g. video, audio or images. One of the most important methods is greedy layer-wise unsupervised pre-training followed by a fine-tuning phase. Despite the advantages of this procedure, it does not fit some scenarios where real time learning is needed, as for adaptation of some time-series models. This paper proposes to couple both phases into one, modifying the loss function to mix together the unsupervised and supervised parts. Benchmark experiments with MNIST database prove the viability of the idea for simple image tasks, and experiments with time-series forecasting encourage the incorporation of this idea into on-line learning approaches. The interest of this method in time-series forecasting is motivated by the study of predictive models for domotic houses with intelligent control systems.
ESAI-CEU-UCH solution for American Epilepsy Society Seizure Prediction ChallengeFrancisco Zamora-Martinez
Presentation given at Cyient Insights (Hyderabad, India).
This work presents the solution proposed by Universidad CEU Cardenal Herrera (ESAI-CEU-UCH) at Kaggle American Epilepsy Society Seizure Prediction Challenge. The proposed solution was positioned as 4th at Kaggle competition.
Different kind of input features (different preprocessing pipelines) and different statistical models are being proposed. This diversity was motivated to improve model combination result.
It is important to note that any of the proposed systems use test set for calibration. The competition allow to do this model calibration using test set, but doing it will reduce the reproducibility of the results in a real world implementation.
Time-series forecasting of indoor temperature using pre-trained Deep Neural N...Francisco Zamora-Martinez
Artificial neural networks have proved to be good at time-series forecasting
problems, being widely studied at literature. Traditionally, shallow
architectures were used due to convergence problems when dealing with deep
models. Recent research findings enable deep architectures training, opening a
new interesting research area called deep learning. This paper presents a study
of deep learning techniques applied to time-series forecasting in a real indoor
temperature forecasting task, studying performance due to different
hyper-parameter configurations. When using deep models, better generalization
performance at test set and an over-fitting reduction has been observed.
Imbalance datasets impose serious problems in machine learning. For many tasks characterized by imbalanced data, the F-Measure seems more appropiate than the Mean Square Error or other relative error measures. This paper studies the use of F-Measure as the training criterion for Neural Networks by integrating it in the Backpropagation algorithm. This novel training criterion has been validated empirically on a real task for which F-Measure is typically applied to evaluate the quality. The task consists in cleaning and enhancing ancient document images which is performed, in this work, by means of neural filters.
Contributions to connectionist language modeling and its application to seque...Francisco Zamora-Martinez
Natural Language Processing is an area of Artificial Intelligence, in
particular, of Pattern Recognition. It is a multidisciplinary field that studies
human language, both oral and written. It deals with the development and
research of computational mechanisms for communication between people and
computers, using natural languages. Natural Language Processing is a reasearch
area constantly evolving, and this work focuses only on the part related to
language modeling, and its application to various tasks:
recognition/understanding of sequences and statistical machine translation.
Specifically, this thesis focus its interest on the so-called connectionist
language models (or continuos space language models), i.e., language models
based on neural networks. Their excellent performance in various Natural
Language Processing areas has motivated this study.
Because of certain computational problems suffered by connectionist language
models, the most widespread approach followed by the systems that currently
use these models, is based on two totally decoupled stages. At a first stage,
using a standard and cheaper language model, a set of feasible hypotheses,
assuming that this set is representative of the search space in which the best
hypothesis is located, is generated. In a second stage, on this set, a
connectionist language model is applied and a rescoring of the list of
hypotheses is done.
This scenario motivates scientific goals of this thesis:
- Developing techniques to reduce drastically the computational cost degrading
as less as possible the quality.
- Study the effect of a totally coupled approach that integrates neural network
language models on decoding stage.
- Developing some extensions of original model in order to improve it quality
and to fulfill context domain adaptation.
- Empirical application of neural network language models to sequence
recognition and machine translation tasks.
All developed algorithms were implemented in C++ and using Lua as scripting
language. The implementations are compared with those that are considered
standard on each of the addressed tasks. Neural network language models achieve
very interesting improvements of quality over the reference baseline systems:
- competitive results are achieved on automatic speech recognition and spoken
language understanding;
- improvement of state-of-the-art handwritten text recognition;
- state-of-the-art results on statistical machine translation, as was stated
with the participation on international evaluation campaigns.
On sequence recognition tasks, the integration of neural network language models
on the first decoding stage achieve very competitive computational
costs. However, their integration in machine translation tasks requires a deeper
development because the computation cost of the system is still somewhat high.
In this paper, we describe a novel approach to Part-Of-Speech tagging based on neural networks. Multilayer perceptrons are used following corpus-based learning from contextual and lexical information. The Penn Treebank corpus has been used for the training and evaluation of the tagging system. The results show that the connectionist approach is feasible and comparable with other approaches.
In this paper, we describe our recent advances on a novel approach to Part-Of-Speech tagging based on neural networks. Multilayer perceptrons are used following corpus-based learning from contextual, lexical and morphological information. The Penn Treebank corpus has been used for the training and evaluation of the tagging system. The results show that the connectionist approach is feasible and comparable with other approaches.
Mejora del reconocimiento de palabras manuscritas aisladas mediante un clasif...Francisco Zamora-Martinez
Este documento describe un estudio para mejorar el reconocimiento de palabras manuscritas aisladas cortas mediante la combinación de diferentes clasificadores. Se utilizaron clasificadores basados en HMM y HMM-MLP para palabras de cualquier longitud, y clasificadores basados en MLP para palabras cortas de hasta 3 letras. Al combinar los resultados de los diferentes clasificadores mediante un método de recuento de Borda, se obtuvo una mejora significativa en la tasa de error de palabra en comparación con los clasificadores individuales.
Behaviour-based Clustering of Neural Networks applied to Document EnhancementFrancisco Zamora-Martinez
This document proposes using behavior-based clustering of multilayer perceptrons (MLPs) to group noise filters for document enhancement. It trains MLPs on different types of noise, clusters them based on behavior, and trains a classifier to select the best filter for new images. An experiment clusters 72 noise filters into 7 groups, reducing filters but still outperforming a single filter. Evaluation shows the system enhances images better than a general filter or using the wrong filter type.
In this paper we propose a family of Viterbi algorithms specialized for lexical tree based FSA and HMM acoustic models. Two algorithms to decode a tree lexicon with left-to-right models with or without skips and other algorithm which takes a directed acyclic graph as input and performs error correcting decoding are presented. They store the set
of active states topologically sorted in contiguous memory queues. The number of basic operations needed to update each hypothesis is reduced and also more locality in memory is obtained reducing the expected number of cache misses and achieving a speed-up over other implementations.
The goal of this work is to present an efficient implementation of the Backpropagation (BP) algorithm to train Artificial Neural Networks with general feedforward topology. This will lead us to the "consecutive retrieval problem" that studies how to arrange
efficiently sets into a sequence so that every set appears contiguously in the sequence. The BP implementation is analyzed, comparing efficiency results with another similar tool. Together with the BP implementation, the data description and manipulation features of our toolkit facilitates the development of experiments in numerous
fields.
Connectionist language models offer many advantages over their statistical counterparts, but they also have some drawbacks like a much more expensive computational cost. This paper describes a novel method to overcome this problem. A set of normalization values associated to the most frequent N-grams is pre-computed and the model is smoothed with lower N-gram connectionist or statistical models. The
proposed approach is favourably compared to standard connectionist language models and with statistical back-off language models.
Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment - KDIR 2012
1. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Some empirical evaluations of a temperature
forecasting module based on Artificial Neural
Networks for a domotic home environment
F. Zamora-Mart´nez, P. Romeu, J. Pardo, D. Tormo
ı
Embedded Systems and Artificial Intelligence group
´
Departamento de ciencias f´sicas, matematicas y de la computacion
ı ´
˜ ´
Escuela Superior de Ensenanzas Tecnicas (ESET)
Universidad CEU Cardenal Herrera, 46115 Alfara del Patriarca, Valencia (Spain)
KDIR – October 6, 2012
2. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
3. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Introduction
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
4. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Introduction
SMLhouse
5. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Introduction
Introduction and motivation
SMLhouse is a domotic solar house project presented at the
SolarDecathlon 2010.
The Computer Aided Energy Saving (CAES) system is being
developed to decrease power consumption, increasing energy
efficiency, keeping comfort parameters.
Indoor temperature is related with comfort and power
consumption.
Artificial Neural Networks (ANNs) are a powerful tool for pattern
classification and forecasting.
This work is an empirical experimentation to set the best ANN
parameters in a real forecasting task.
6. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
7. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Hardware architecture
Lights,
roller-shutters,
HVAC, . . .
Temperature, air
⇒ ⇒ Ethernet
quality, humidity,
...
Light Switches,
dimmers, . . .
8. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Software architecture
First layer: data is acquired from the KNX bus by iOS interface ANN Modules
the Open Home Automation Bus (openHAB).
Persistence
Second layer: data persistence module collect (REST interface)
sensor and actuator values every minute. KNX-IP Bridge → openHAB ⇐
9. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Software architecture
First layer: data is acquired from the KNX bus by iOS interface ANN Modules
the Open Home Automation Bus (openHAB).
Persistence ⇐
Second layer: data persistence module collect (REST interface)
sensor and actuator values every minute. KNX-IP Bridge → openHAB
Timestamp Name Value
... ... ...
2011-03-30 10:51 Dinning Room Temperature 30.0
2011-03-30 10:52 Dinning Room Humidity 52.0
... ... ...
10. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Software architecture
iOS interface ANN Modules ⇐
Third layer: two applications that could
communicate between themselves. A native iOS Persistence
application for manual control. A couple of
(REST interface)
modules that can actuate autonomously. KNX-IP Bridge → openHAB
11. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Domotic home environment setup
Software architecture
iOS interface ANN Modules ⇐
Third layer: two applications that could
communicate between themselves. A native iOS Persistence
application for manual control. A couple of
(REST interface)
modules that can actuate autonomously. KNX-IP Bridge → openHAB
12. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Data preprocessing
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
13. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Data preprocessing
Data details
Acquisition
The data temperature signal is a sequence s1 s2 . . . sN of values,
sampled with a period of 1 minute.
Preprocessing
1 Low-pass filter (mean with 5 samples): s1 s2 . . . sN where
si = (si + si−1 + si−2 + si−3 + si−4 )/5
2 Data normalized subtracting mean and dividing by the standard
deviation: s1 s2 . . . sN where
si − s
¯
si =
σ(s )
14. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Data preprocessing
Dataset size
Partition Number of patterns Days
Training 30 240 21
Validation 10 080 7
Test 10 080 7
Validation partition is sequential with training partition.
Test partition is one week ahead from last validation point.
Mean and standard deviation normalization values were
computed over the training plus validation.
15. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Data preprocessing
Plot of the dinning room temperature for validation partition
26
25
24
23
22
21
ºC
20
19
18
17
16
15
0 2000 4000 6000 8000 10000
Time (minutes)
16. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
17. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Neural Network description
At time step i:
18. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Neural Network description
At time step i:
the ANN input receives:
the hour component of the current time (locally encoded) and
a window of the previous temperature values (α is step, and M is
number of steps):
si si−α si−2α . . . si−(M−1)·α
19. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Neural Network description
At time step i:
and computes a window with the next predicted temperature
values (L is forecast horizon):
si+1 si+2 si+3 . . . si+L
Known as multi-step-ahead direct forecasting.
20. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Multi-step-ahead forecasting approaches
Multi-step-ahead iterative forecasting was very extended in
literature. Only one future value is predicted and reused to predict
iteratively the whole window. Better for small future horizons.
Multi-step-ahead direct forecasting approach is based on the
computation of the future window in one step. Better for large
future horizons.
21. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Training details
Error back-propagation algorithm with momentum term.
The ANN learn to map predicted output values (oi ) with
corresponding true values ( pi ),
minimizing the MSE function
MSE
1
E = ∑ (oi − pi )2
2L i
22. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Neural Network description
Training details
Error back-propagation algorithm with momentum term.
The ANN learn to map predicted output values (oi ) with
corresponding true values ( pi ),
minimizing the MSE function, adding weight decay L2
regularization
MSE weight decay
1 w2
E = ∑ (oi − pi )2 + ε ∑
2L i w∈{W HO W IH }
2
23. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
24. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation: training parameters
An exhaustive exploration leads to this parameters:
learning rate of 0.001,
momentum of 0.0005,
weight decay of 1 × 10−7 ,
input window step of α = 2,
input window size of M = 30,
one hidden layer with 8 neurons and logistic activation function.
output window horizon L experiments will be shown in detail.
The ANN best topology was (15 + 24) × 8 × L.
25. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (II): evaluation
ANNs were trained modifying the output window horizon focusing
results only on L = 60, 120, 180 (denoted by NN–060, NN–120,
NN–180).
Evaluation measures
Mean Absolute Error (MAE):
1
MAE = |pi − pi |
N∑i
Normalized Root Mean Square Error (NRMSE):
∑ (pi − pi )2
i
NRMSE =
∑ ( pi − pi )2
¯
i
26. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (III): forecasting mean temperatures
In order to focus the temperature forecasting measured errors on
their future use on an automatic control system, we will compute
the mean (or max/min) temperature forecasted by the model in
the selected forecasting window.
Then we could measure the MAE value between this mean and
the ground truth mean on the same window.
27. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (IV): individual models plot
0.14
NN−060
NN−120
NN−180
0.12
0.10
0.08
MAE
0.06
0.04
0.02
0.00
20 40 60 80 100 120 140 160 180
Window upper bound
Plot of the MAE error computed over the mean of forecasting windows
0–20, 0–40, 0–60, 0–80, . . . , 0–180, using ANN models trained with
L = 60, 120, 180.
28. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (V): ensemble of models
An ensemble of NN–060 and NN–180 model would ensure good
performance in all cases.
A linear combination of ANN outputs was performed, following:
NN–060 NN–180
os + ol
i i
, for 0 ≤ i < 60 ;
oi = 2
NN–180
l
oi , for 60 ≤ i < 180 .
29. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (VI): ensemble vs individual models plot
0.14 0.14
NN−060 NN−060
NN−120 NN−120
NN−180 NN−MIX
0.12 0.12
0.10 0.10
0.08 0.08
MAE
MAE
0.06 0.06
0.04 0.04
0.02 0.02
0.00 0.00
20 40 60 80 100 120 140 160 180 20 40 60 80 100 120 140 160 180
Window upper bound Window upper bound
Plot of the MAE error computed over the mean of forecasting windows
0–20, 0–40, 0–60, 0–80, . . . , 0–180, using NN–060, NN–120, and
NN–MIX models (right).
30. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (VII): validation and test set final results
NN–MIX model results for validation set
Window Min Max Mean
0–60 0.029/0.050 0.047/0.061 0.027/0.043
60–120 0.068/0.115 0.099/0.135 0.079/0.122
120–180 0.129/0.214 0.165/0.233 0.143/0.223
NN–MIX model results for test set
Window Min Max Mean
0–60 0.139/0.188 0.173/0.254 0.150/0.205
60–120 0.255/0.371 0.239/0.360 0.270/0.394
120–180 0.334/0.539 0.381/0.603 0.352/0.566
NRMSE/MAE on minimum, maximum, and mean temperature
forecasting for validation and test sets.
31. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (VIII): validation set forecasting plot
26
NN−MIX
25 Ground Truth
24
23
22
21
ºC
20
19
18
17
16
15
0 2000 4000 6000 8000 10000
Time (minutes)
Plot of validation set forecasted mean temperature versus ground truth
mean temperature using a forecasting window of 0–60 with NN–MIX
model.
32. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Experimentation
Experimentation (IX): test set forecasting plot
30
NN−MIX
Ground Truth
28
26
ºC
24
22
20
18
0 2000 4000 6000 8000 10000
Time (minutes)
Plot of test set forecasted mean temperature versus ground truth mean
temperature using a forecasting window of 0–60 with NN–MIX model.
33. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Conclusions and future work
Index
1 Introduction
2 Domotic home environment setup
3 Data preprocessing
4 Neural Network description
5 Experimentation
6 Conclusions and future work
34. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Conclusions and future work
Conclusions
A real hardware/software architecture was introduced for domotic
home environments: SMLhouse.
Preliminary data was used for model testing and validation.
Monitoring and manual control systems are running.
Intelligent control modules are being developed: dinning room
temperature forecast module.
Promising results: little MAE error was achieved (0.6◦ C for three
hours forecast).
It motivates the integration of this ideas into an automatic control
system.
35. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Conclusions and future work
Future work
Covariate forecasting.
Extend forecasting module to air quality, humidity, power
consumption, insolation, . . .
Introduce confidence on the prediction, based on prediction
intervals.
Replace feedforward ANN with a recurrent neural network:
Long-Short Term Memory.
36. Some empirical evaluations of a temperature forecasting module based on Artificial Neural Networks for a domotic home environment
Conclusions and future work
Questions?
Thanks for your attention!