Raida Al-Alawi - Academia.edu (original) (raw)

Papers by Raida Al-Alawi

Research paper thumbnail of Impact of proactive pharmacist‐assisted warfarin management using an electronic medication management system in Australian hospitalised patients

Journal of Pharmacy Practice and Research, 2020

AimTo evaluate whether pharmacist‐assisted electronic warfarin charting and monitoring reduces wa... more AimTo evaluate whether pharmacist‐assisted electronic warfarin charting and monitoring reduces warfarin‐related errors and improves post‐discharge continuum of care.MethodCardiology and medical patients admitted for at least 24 h and prescribed at least one warfarin dose were included in a pre/post‐intervention study. The intervention involved pharmacists proactively charting warfarin and ordering international normalised ratios (INRs) using electronic prescribing software, following discussion with medical doctors. Endpoints included: percentage of patients with one or more warfarin errors, INR > 5.0 during admission, readmission within 30 days for anticoagulant‐related issues and warfarin discharge plan (WDP) completeness (including documentation of next dose/s, and when and where the next INR was to be checked).ResultsPre‐ and post‐intervention groups comprised 130 and 108 patients, respectively. Post‐intervention, more patients received warfarin following heart valve replacem...

Research paper thumbnail of Performance Evaluation of Fuzzy Single Layer Weightless Neural Network

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, Jun 1, 2007

The paper evaluates the performance of a neuro-fuzzy pattern classification system based on the w... more The paper evaluates the performance of a neuro-fuzzy pattern classification system based on the weightless neural network architecture. The system utilizes a Single Layer Weightless Neural Network (SLWNN) to extract the features vector that measures the similarity of the input pattern to the different classification groups. In contrast to the traditional crisp Winner-Takes-All (WTA) classification scheme used by SLWNN, our system uses a Fuzzy Inference System (FIS) for classification. The network is trained by a hybrid learning scheme that combines a single pass learning phase for training the SLWNN followed by a supervised learning phase for extracting a set of fuzzy rules suitable to classify the training set. The FIS learns fuzzy rules from the feature vectors generated by the SLWNN for the set of training patterns. The recognition of handwritten numerals is employed as a test-bed to demonstrate the effectiveness of the proposed neuro-fuzzy system. Experimental results show that the performance of the proposed system surpasses the performance of the traditional SLWNN.

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, Aug 1, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

Research paper thumbnail of A Training Strategy and Functionality Analysis of Digital Multi-Layer Neural Networks

Journal of intelligent systems, 1992

The digital neuron model is evaluated in terms of its functional capacity, generalisation, traini... more The digital neuron model is evaluated in terms of its functional capacity, generalisation, training procedure and hardware implementtation, and contrasted with the analogue neuron model. A learning algorithm for digital multi-layer neural networks which uses a backpropagation search techniques is proposed and compared with other well-known training methods. Finally a dynamic mapping strategy for the nodes of the digital multi-layer network and the introduction of redundancy are evaluated as means of increasing the flexibility and functional capacity of the network.

Research paper thumbnail of Evaluation of the Functional Capacities of Multi-Layered Logical Neural Networks

The ability of neural networks to solve real data processing tasks is dependent on the network to... more The ability of neural networks to solve real data processing tasks is dependent on the network topology being able to support the desired functionality required by the problem under consideration. An analysis of popular network topologies reveals that they have very restricted functionality and no strategy for devicing a suitable topology is given. This paper presents a method for calculating the functional capacity of a multilayer neural network with analogue and digital neurons.

Research paper thumbnail of An Encoder for Differential Manchester and Inverse Differential Manchester Line Codes

The transactions of the Institute of Electrical Engineers of Japan.C, 2005

A synchronous digital circuit for encoding differential Manchester and inverse differential Manch... more A synchronous digital circuit for encoding differential Manchester and inverse differential Manchester codes is presented. The design is based on a new representation of these codes as Moore state machines, which is extracted from a new code definition through encoding equations. The encoder utilizes two flip-flops, one OR gate and one X-OR gate, which can be easily implemented in hardware using standard ICs or part of an LSI / VLSI circuit.

Research paper thumbnail of Performance of a Digital Associative Memory Model for Pattern Recognition

Journal of Intelligent and Fuzzy Systems, 1997

This article presents a digital associative memory (DAM) with pyramids of probabilistic logic nod... more This article presents a digital associative memory (DAM) with pyramids of probabilistic logic nodes used as the basic processing element. The DAM can be applied to various pattern recognition systems or image classifiers. A reward/ penalty error back propagation algorithm used to train the model will be described. Computer simulations are done to evaluate the peTj'ormance of the model by training the network on associating a number of patterns from each class of the numerals 0-9 with their prototype model. The effect of the size of the training set on the convergence of the training algorithm is investigated.

Research paper thumbnail of A hybrid n-tuple neuro-fuzzy classifier for handwritten numerals recognition

A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. T... more A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. The system combines the advantages of the n-tuple sampling technique and fuzzy inference system. The n-tuple unit is used as a preprocessing unit for extracting the feature vector from the input pattern. The outputs of the n-tuple unit are fed to a fuzzy inference unit that applies a set of fuzzy rules on the feature vectors and aggregates them to generate its classification response. The classification accuracy of the n-tuple neuro-fuzzy system and the classical n-tuple classifier is compared using handwritten numerals from NIST database. The n-tuple neuro-fuzzy classifier achieves an accuracy of 98.5% on classifying unseen numerals.

Research paper thumbnail of Design of a Multicode Bi-Phase Encoder for Data Transmission

Journal of Circuits, Systems, and Computers, Feb 1, 2006

In this paper, we present a versatile Multicode Bi-Phase Encoder (MBPE) circuit capable of encodi... more In this paper, we present a versatile Multicode Bi-Phase Encoder (MBPE) circuit capable of encoding five different Bi-Phase line codes, namely: Bi-Phase-Level (Bi-Φ-L), Bi-Phase-Mark (Bi-Φ-M), Bi-Phase-Space (Bi-Φ-S), Differential Manchester (DM) and Inverse Differential Manchester (IDM) codes. The design methodology is based on a new definition of these codes in terms of encoding rules and state diagrams, instead of the traditional way of representing them in terms of their bit transition. The operation mode of the MBPE is set by three selection lines, which can be either hardware or software controlled. This will facilitate the process of altering the data transmission protocol without the need of changing the encoder hardware. The functionality and design of the MBPE is outlined. VHDL has been used to describe the behavior of the MBPE whose operation was verified using the ModelSim XE II Simulation tools. Implementation and testing of the MBPE on XILINX Spartan-II FPGA showed that the MBPE circuit is capable of encoding NRZ data into any of the five codes.

Research paper thumbnail of Linear theory of radiation fine structure for an Alfven maser with frequency drift

Radiophysics and Quantum Electronics, 1990

Research paper thumbnail of IEEE Potentials Reviewer Team

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

Research paper thumbnail of A hybrid n-tuple neuro-fuzzy classifier for handwritten numerals recognition

2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)

A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. T... more A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. The system combines the advantages of the n-tuple sampling technique and fuzzy inference system. The n-tuple unit is used as a preprocessing unit for extracting the feature vector from the input pattern. The outputs of the n-tuple unit are fed to a fuzzy inference unit that applies a set of fuzzy rules on the feature vectors and aggregates them to generate its classification response. The classification accuracy of the n-tuple neuro-fuzzy system and the classical n-tuple classifier is compared using handwritten numerals from NIST database. The n-tuple neuro-fuzzy classifier achieves an accuracy of 98.5% on classifying unseen numerals.

Research paper thumbnail of A Training Strategy and Functionality Analysis of Digital Multi-Layer Neural Networks

Journal of Intelligent Systems, 1992

The digital neuron model is evaluated in terms of its functional capacity, generalisation, traini... more The digital neuron model is evaluated in terms of its functional capacity, generalisation, training procedure and hardware implementtation, and contrasted with the analogue neuron model. A learning algorithm for digital multi-layer neural networks which uses a backpropagation search techniques is proposed and compared with other well-known training methods. Finally a dynamic mapping strategy for the nodes of the digital multi-layer network and the introduction of redundancy are evaluated as means of increasing the flexibility and functional capacity of the network.

Research paper thumbnail of Evaluation of the Functional Capacities of Multi-Layered Logical Neural Networks

International Neural Network Conference, 1990

The ability of neural networks to solve real data processing tasks is dependent on the network to... more The ability of neural networks to solve real data processing tasks is dependent on the network topology being able to support the desired functionality required by the problem under consideration. An analysis of popular network topologies reveals that they have very restricted functionality and no strategy for devicing a suitable topology is given. This paper presents a method for calculating the functional capacity of a multilayer neural network with analogue and digital neurons.

Research paper thumbnail of An Encoder for Differential Manchester and Inverse Differential Manchester Line Codes

IEEJ Transactions on Electronics, Information and Systems, 2005

A synchronous digital circuit for encoding differential Manchester and inverse differential Manch... more A synchronous digital circuit for encoding differential Manchester and inverse differential Manchester codes is presented. The design is based on a new representation of these codes as Moore state machines, which is extracted from a new code definition through encoding equations. The encoder utilizes two flip-flops, one OR gate and one X-OR gate, which can be easily implemented in hardware using standard ICs or part of an LSI / VLSI circuit.

Research paper thumbnail of Performance of a Digital Associative Memory Model for Pattern Recognition

J. Intell. Fuzzy Syst., 1997

This article presents a digital associative memory DAM with pyramids of probabilistic logic nodes... more This article presents a digital associative memory DAM with pyramids of probabilistic logic nodes used as the basic processing element. The DAM can be applied to various pattern recognition systems or image classifiers. A reward/penalty error back propagation algorithm used to train the model will be described. Computer simulations are done to evaluate the performance of the model by training the network on associating a number of patterns from each class of the numerals 0--9 with their prototype model. The effect of the size of the training set on the convergence of the training algorithm is investigated.

Research paper thumbnail of RSSI based location estimation in wireless sensors networks

Location estimation of sensor nodes is a key component in many wireless sensor networks' (WSN... more Location estimation of sensor nodes is a key component in many wireless sensor networks' (WSN) applications such as target tracking, rescue operations, disaster relief and environmental monitoring. The accuracy of the localization algorithm is a vital component to the success of the localization technique. The RSSI ranged based localization algorithm is a simple and cost effective localization technique that relies on measuring the Receive Signal Strength Indicator (RSSI) for distance estimation. In this paper we present experimental results that are carried out to analyze the sensitivity of RSSI measurements in an outdoor and indoor environment. A calibration model that characterized the RF radio channel will be derived and used for distance estimation. The validity of the estimated distance will be verified to track the position of a sensor node within an indoor environment. The results of this study reveal the feasibility of RSSI based localization algorithm in designing corr...

Research paper thumbnail of Web-Based Intelligent Traffic Management System

The ever increasing number of vehicles in most metropolitan cities around the world and the limit... more The ever increasing number of vehicles in most metropolitan cities around the world and the limitation in altering the transportation infrastructure, led to serious traffic congestion and an increase in the travelling time. In this work we exploit the emergence of novel technologies such as the internet, to design an intelligent Traffic Management System (TMS) that can remotely monitor and control a network of traffic light controllers located at different sites. The system is based on utilizing Embedded Web Servers (EWS) technology to design a web-based TMS. The EWS located at each intersection uses IP technology for communicating remotely with a Central Traffic Management Unit (CTMU) located at the traffic department authority. Friendly GUI software installed at the CTMU is developed to select a specific node to monitor the sequence of operation of the traffic lights and the presence of traffic at each intersection as well as remotely controlling the operation of the signals. The ...

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

Research paper thumbnail of Impact of proactive pharmacist‐assisted warfarin management using an electronic medication management system in Australian hospitalised patients

Journal of Pharmacy Practice and Research, 2020

AimTo evaluate whether pharmacist‐assisted electronic warfarin charting and monitoring reduces wa... more AimTo evaluate whether pharmacist‐assisted electronic warfarin charting and monitoring reduces warfarin‐related errors and improves post‐discharge continuum of care.MethodCardiology and medical patients admitted for at least 24 h and prescribed at least one warfarin dose were included in a pre/post‐intervention study. The intervention involved pharmacists proactively charting warfarin and ordering international normalised ratios (INRs) using electronic prescribing software, following discussion with medical doctors. Endpoints included: percentage of patients with one or more warfarin errors, INR > 5.0 during admission, readmission within 30 days for anticoagulant‐related issues and warfarin discharge plan (WDP) completeness (including documentation of next dose/s, and when and where the next INR was to be checked).ResultsPre‐ and post‐intervention groups comprised 130 and 108 patients, respectively. Post‐intervention, more patients received warfarin following heart valve replacem...

Research paper thumbnail of Performance Evaluation of Fuzzy Single Layer Weightless Neural Network

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, Jun 1, 2007

The paper evaluates the performance of a neuro-fuzzy pattern classification system based on the w... more The paper evaluates the performance of a neuro-fuzzy pattern classification system based on the weightless neural network architecture. The system utilizes a Single Layer Weightless Neural Network (SLWNN) to extract the features vector that measures the similarity of the input pattern to the different classification groups. In contrast to the traditional crisp Winner-Takes-All (WTA) classification scheme used by SLWNN, our system uses a Fuzzy Inference System (FIS) for classification. The network is trained by a hybrid learning scheme that combines a single pass learning phase for training the SLWNN followed by a supervised learning phase for extracting a set of fuzzy rules suitable to classify the training set. The FIS learns fuzzy rules from the feature vectors generated by the SLWNN for the set of training patterns. The recognition of handwritten numerals is employed as a test-bed to demonstrate the effectiveness of the proposed neuro-fuzzy system. Experimental results show that the performance of the proposed system surpasses the performance of the traditional SLWNN.

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, Aug 1, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

Research paper thumbnail of A Training Strategy and Functionality Analysis of Digital Multi-Layer Neural Networks

Journal of intelligent systems, 1992

The digital neuron model is evaluated in terms of its functional capacity, generalisation, traini... more The digital neuron model is evaluated in terms of its functional capacity, generalisation, training procedure and hardware implementtation, and contrasted with the analogue neuron model. A learning algorithm for digital multi-layer neural networks which uses a backpropagation search techniques is proposed and compared with other well-known training methods. Finally a dynamic mapping strategy for the nodes of the digital multi-layer network and the introduction of redundancy are evaluated as means of increasing the flexibility and functional capacity of the network.

Research paper thumbnail of Evaluation of the Functional Capacities of Multi-Layered Logical Neural Networks

The ability of neural networks to solve real data processing tasks is dependent on the network to... more The ability of neural networks to solve real data processing tasks is dependent on the network topology being able to support the desired functionality required by the problem under consideration. An analysis of popular network topologies reveals that they have very restricted functionality and no strategy for devicing a suitable topology is given. This paper presents a method for calculating the functional capacity of a multilayer neural network with analogue and digital neurons.

Research paper thumbnail of An Encoder for Differential Manchester and Inverse Differential Manchester Line Codes

The transactions of the Institute of Electrical Engineers of Japan.C, 2005

A synchronous digital circuit for encoding differential Manchester and inverse differential Manch... more A synchronous digital circuit for encoding differential Manchester and inverse differential Manchester codes is presented. The design is based on a new representation of these codes as Moore state machines, which is extracted from a new code definition through encoding equations. The encoder utilizes two flip-flops, one OR gate and one X-OR gate, which can be easily implemented in hardware using standard ICs or part of an LSI / VLSI circuit.

Research paper thumbnail of Performance of a Digital Associative Memory Model for Pattern Recognition

Journal of Intelligent and Fuzzy Systems, 1997

This article presents a digital associative memory (DAM) with pyramids of probabilistic logic nod... more This article presents a digital associative memory (DAM) with pyramids of probabilistic logic nodes used as the basic processing element. The DAM can be applied to various pattern recognition systems or image classifiers. A reward/ penalty error back propagation algorithm used to train the model will be described. Computer simulations are done to evaluate the peTj'ormance of the model by training the network on associating a number of patterns from each class of the numerals 0-9 with their prototype model. The effect of the size of the training set on the convergence of the training algorithm is investigated.

Research paper thumbnail of A hybrid n-tuple neuro-fuzzy classifier for handwritten numerals recognition

A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. T... more A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. The system combines the advantages of the n-tuple sampling technique and fuzzy inference system. The n-tuple unit is used as a preprocessing unit for extracting the feature vector from the input pattern. The outputs of the n-tuple unit are fed to a fuzzy inference unit that applies a set of fuzzy rules on the feature vectors and aggregates them to generate its classification response. The classification accuracy of the n-tuple neuro-fuzzy system and the classical n-tuple classifier is compared using handwritten numerals from NIST database. The n-tuple neuro-fuzzy classifier achieves an accuracy of 98.5% on classifying unseen numerals.

Research paper thumbnail of Design of a Multicode Bi-Phase Encoder for Data Transmission

Journal of Circuits, Systems, and Computers, Feb 1, 2006

In this paper, we present a versatile Multicode Bi-Phase Encoder (MBPE) circuit capable of encodi... more In this paper, we present a versatile Multicode Bi-Phase Encoder (MBPE) circuit capable of encoding five different Bi-Phase line codes, namely: Bi-Phase-Level (Bi-Φ-L), Bi-Phase-Mark (Bi-Φ-M), Bi-Phase-Space (Bi-Φ-S), Differential Manchester (DM) and Inverse Differential Manchester (IDM) codes. The design methodology is based on a new definition of these codes in terms of encoding rules and state diagrams, instead of the traditional way of representing them in terms of their bit transition. The operation mode of the MBPE is set by three selection lines, which can be either hardware or software controlled. This will facilitate the process of altering the data transmission protocol without the need of changing the encoder hardware. The functionality and design of the MBPE is outlined. VHDL has been used to describe the behavior of the MBPE whose operation was verified using the ModelSim XE II Simulation tools. Implementation and testing of the MBPE on XILINX Spartan-II FPGA showed that the MBPE circuit is capable of encoding NRZ data into any of the five codes.

Research paper thumbnail of Linear theory of radiation fine structure for an Alfven maser with frequency drift

Radiophysics and Quantum Electronics, 1990

Research paper thumbnail of IEEE Potentials Reviewer Team

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.

Research paper thumbnail of A hybrid n-tuple neuro-fuzzy classifier for handwritten numerals recognition

2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)

A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. T... more A hybrid neuro-fuzzy system applied to the classification of handwritten numerals is presented. The system combines the advantages of the n-tuple sampling technique and fuzzy inference system. The n-tuple unit is used as a preprocessing unit for extracting the feature vector from the input pattern. The outputs of the n-tuple unit are fed to a fuzzy inference unit that applies a set of fuzzy rules on the feature vectors and aggregates them to generate its classification response. The classification accuracy of the n-tuple neuro-fuzzy system and the classical n-tuple classifier is compared using handwritten numerals from NIST database. The n-tuple neuro-fuzzy classifier achieves an accuracy of 98.5% on classifying unseen numerals.

Research paper thumbnail of A Training Strategy and Functionality Analysis of Digital Multi-Layer Neural Networks

Journal of Intelligent Systems, 1992

The digital neuron model is evaluated in terms of its functional capacity, generalisation, traini... more The digital neuron model is evaluated in terms of its functional capacity, generalisation, training procedure and hardware implementtation, and contrasted with the analogue neuron model. A learning algorithm for digital multi-layer neural networks which uses a backpropagation search techniques is proposed and compared with other well-known training methods. Finally a dynamic mapping strategy for the nodes of the digital multi-layer network and the introduction of redundancy are evaluated as means of increasing the flexibility and functional capacity of the network.

Research paper thumbnail of Evaluation of the Functional Capacities of Multi-Layered Logical Neural Networks

International Neural Network Conference, 1990

The ability of neural networks to solve real data processing tasks is dependent on the network to... more The ability of neural networks to solve real data processing tasks is dependent on the network topology being able to support the desired functionality required by the problem under consideration. An analysis of popular network topologies reveals that they have very restricted functionality and no strategy for devicing a suitable topology is given. This paper presents a method for calculating the functional capacity of a multilayer neural network with analogue and digital neurons.

Research paper thumbnail of An Encoder for Differential Manchester and Inverse Differential Manchester Line Codes

IEEJ Transactions on Electronics, Information and Systems, 2005

A synchronous digital circuit for encoding differential Manchester and inverse differential Manch... more A synchronous digital circuit for encoding differential Manchester and inverse differential Manchester codes is presented. The design is based on a new representation of these codes as Moore state machines, which is extracted from a new code definition through encoding equations. The encoder utilizes two flip-flops, one OR gate and one X-OR gate, which can be easily implemented in hardware using standard ICs or part of an LSI / VLSI circuit.

Research paper thumbnail of Performance of a Digital Associative Memory Model for Pattern Recognition

J. Intell. Fuzzy Syst., 1997

This article presents a digital associative memory DAM with pyramids of probabilistic logic nodes... more This article presents a digital associative memory DAM with pyramids of probabilistic logic nodes used as the basic processing element. The DAM can be applied to various pattern recognition systems or image classifiers. A reward/penalty error back propagation algorithm used to train the model will be described. Computer simulations are done to evaluate the performance of the model by training the network on associating a number of patterns from each class of the numerals 0--9 with their prototype model. The effect of the size of the training set on the convergence of the training algorithm is investigated.

Research paper thumbnail of RSSI based location estimation in wireless sensors networks

Location estimation of sensor nodes is a key component in many wireless sensor networks' (WSN... more Location estimation of sensor nodes is a key component in many wireless sensor networks' (WSN) applications such as target tracking, rescue operations, disaster relief and environmental monitoring. The accuracy of the localization algorithm is a vital component to the success of the localization technique. The RSSI ranged based localization algorithm is a simple and cost effective localization technique that relies on measuring the Receive Signal Strength Indicator (RSSI) for distance estimation. In this paper we present experimental results that are carried out to analyze the sensitivity of RSSI measurements in an outdoor and indoor environment. A calibration model that characterized the RF radio channel will be derived and used for distance estimation. The validity of the estimated distance will be verified to track the position of a sensor node within an indoor environment. The results of this study reveal the feasibility of RSSI based localization algorithm in designing corr...

Research paper thumbnail of Web-Based Intelligent Traffic Management System

The ever increasing number of vehicles in most metropolitan cities around the world and the limit... more The ever increasing number of vehicles in most metropolitan cities around the world and the limitation in altering the transportation infrastructure, led to serious traffic congestion and an increase in the travelling time. In this work we exploit the emergence of novel technologies such as the internet, to design an intelligent Traffic Management System (TMS) that can remotely monitor and control a network of traffic light controllers located at different sites. The system is based on utilizing Embedded Web Servers (EWS) technology to design a web-based TMS. The EWS located at each intersection uses IP technology for communicating remotely with a Central Traffic Management Unit (CTMU) located at the traffic department authority. Friendly GUI software installed at the CTMU is developed to select a specific node to monitor the sequence of operation of the traffic lights and the presence of traffic at each intersection as well as remotely controlling the operation of the signals. The ...

Research paper thumbnail of FPGA Implementation of a Pyramidal Weightless Neural Networks Learning System

International Journal of Neural Systems, 2003

A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model f... more A hardware architecture of a Probabilistic Logic Neuron (PLN) is presented. The suggested model facilitates the on-chip learning of pyramidal Weightless Neural Networks using a modified probabilistic search reward/penalty training algorithm. The penalization strategy of the training algorithm depends on a predefined parameter called the probabilistic search interval. A complete Weightless Neural Network (WNN) learning system is modeled and implemented on Xilinx XC4005E Field Programmable Gate Array (FPGA), allowing its architecture to be configurable. Various experiments have been conducted to examine the feasibility and performance of the WNN learning system. Results show that the system has a fast convergence rate and good generalization ability.