Sarah M. Al-sudany; .Ahmed S. Al-Araji1; Bassam M. Saeed
Volume 21, Issue 2 , June 2021, , Page 16-35
Abstract
This research presents a study for multicore Reduced Instruction SetComputer (RISC) processor implemented on the Field Programmable GateArray(FPGA).The Microprocessor without- Interlocked Pipeline Stages (MIPS)processor is designed for the implementation of educational purposes, as well as it isexpected ...
Read More ...
This research presents a study for multicore Reduced Instruction SetComputer (RISC) processor implemented on the Field Programmable GateArray(FPGA).The Microprocessor without- Interlocked Pipeline Stages (MIPS)processor is designed for the implementation of educational purposes, as well as it isexpected that this prototype of processor will be used for multimedia or big dataapplications. 32- bit MIPS processor was designed by using Very High speed HardwareDescription Language (VHDL). Pipelined MIPS processor contains three parts that are :data path 32-bit MIPS pipeline, control unit, and hazard unit. The single cycle MIPSsystem was subdivided into five pipeline stages to achieve the pipeline MIPS processor.The five parts include: instruction fetch (IF), Instruction Decode (ID), execution (EXE),memory (MEM) and Write Back (WB). Three types of hazard: data hazard , controlhazard and strctural hazard are resolved. Certain components in the pipelined stage forthe design processor were iterated for four core SIMD pipelined processors. The MIPS isdeveloped using Xilinx ISE 14.7 design suite. The designed processor was implementedsuccessfully on Xilinx Virtex-6 XC6VLX240T-1FFG1156 FPGA. The total poweranalysis of multi-core MIPS processor is obtanined 3.422 watt and the clock period was7.329 ns (frequency: 136.444MHz).
Omar Abdul Razzaq Abdul Wahhab; .Ahmed S. Al-Araji1
Volume 21, Issue 2 , June 2021, , Page 44-58
Abstract
The goal of navigating a mobile robot is to find the optimal path to direct itsmovement, so path planning is the best solution to find the optimal path. Therefore, thetwo most important problems of path planning must be solved; the first is that the pathmust avoid collision with obstacles, and second ...
Read More ...
The goal of navigating a mobile robot is to find the optimal path to direct itsmovement, so path planning is the best solution to find the optimal path. Therefore, thetwo most important problems of path planning must be solved; the first is that the pathmust avoid collision with obstacles, and second it must reduce the length of the path to aminimum. This paper will discuss finding the shortest path with the optimum cost functionby using the Chaotic Particle Swarm Optimization (CPSO), and A*, compare the resultsbetween them and the proposed hybrid algorithm that combines A* and Chaotic ParticleSwarm Optimization (ACPSO) algorithms to enhance A* algorithm to find the optimalpath and velocities of the wheeled mobile robot. These algorithms are simulated byMATLAB in a fixed obstacles environment to show the effectiveness of the proposedalgorithm in terms of minimum number of an evaluation function and the shortest pathlength as well as to obtain the optimal or near optimal wheel velocities.
Abdulhakeem Q. Albayati; Ah med S. Al-Araji1; Saman H. Ameen
Volume 20, Issue 4 , October 2020, , Page 9-20
Abstract
Sentiment Analysis (SA) is a field of Natural Language Processing (NLP) whose goal is to extract the emotion, sentiment or more general opinion expressed in a human-written text. Opinions and emotions play a central role in human life. Therefore, there are many academic researches in this field for processing ...
Read More ...
Sentiment Analysis (SA) is a field of Natural Language Processing (NLP) whose goal is to extract the emotion, sentiment or more general opinion expressed in a human-written text. Opinions and emotions play a central role in human life. Therefore, there are many academic researches in this field for processing many languages like English However, there is scarce in its implementation with addressing Arabic Sentiment Analysis (ASA). It is a challenging field where Arabic language has a rich morphological structure and there are many other defies more than in other languages. For that, the proposed model tackles ASA by using a Deep Learning approach. In this work, one of word embedding methods, such as a first hidden layer for features extracting from the input dataset and Long Short-Term Memory (LSTM) as a deep neural network, has been used for training. The model combined with Softmax layer is applied to turn numeric outputs from LSTM layer into probabilities to classify the outputs to positive or negative. There are two datasets that are used for training the model separately with each one. The first one is ASTD dataset as a dialectal Arabic type about different tweets from internet, the results with this dataset is compared with another academic work that used the same one. The results from this work outperforms through accuracy about 14.95% and F-score about 15.14% more than what performed in the previous work. The second one is HTL dataset as a modern standard Arabic type about opinions of reviewers on different hotels from several countries. This dataset is bigger in size than the first one to show the size effect on the results of this model. So, the accuracy increased about 11% and F-score about 10.8% more than what performed with the first dataset.
Mustafa M. Salih; Ahm ed S. Al-Araji1; Hassan A. Jeiad
Volume 20, Issue 4 , October 2020, , Page 29-47
Abstract
This paper presents an enhancement of the output performance of a linear buck converter system for the mobile (smartphone) devices using an adaptive digital Proportional–Integral–Derivative (PID) controller with off-line swarm optimization algorithm. The work focuses on improving the use ...
Read More ...
This paper presents an enhancement of the output performance of a linear buck converter system for the mobile (smartphone) devices using an adaptive digital Proportional–Integral–Derivative (PID) controller with off-line swarm optimization algorithm. The work focuses on improving the use of using single-input single-output (SISO) digital Field Programmable Gate Array (FPGA)-PID to control the linear buck converter system. The goal of the proposed adaptive SISO-FPGA-PID voltage-tracking controller is to rapidly and precisely identify the optimal voltage control action (optimal on-off duration time) that is used to control the buck converter output voltage level in order to avoid the troubleshooting hardware problem issues on mobile devices. The Particle Swarm Optimization (PSO) algorithms are used to find and tune the three weights of the SISO-FPGA-PID controller. The numerical simulation results and the experimental work using Spartan-3E xc3s500e-4fg320 board with Verilog hardware description language (HDL) show that the proposed controller is more accurate in terms of voltage error and the number of function evolutions are of high reduction. As well as to generate a smooth voltage control response without voltage oscillation in the output by investigating under mobile applications variations such as using Bluetooth, WI-FI, and CPU operating voltage when these results are compared with other controllers.
Wajdi T. Joudah Al-Rubaye; Ah med Al-Araji1; Hayder A. Dhahad
Volume 20, Issue 3 , July 2020, , Page 50-64
Abstract
This paper proposes an off-line adaptive digital Proportional Integral Derivative (PID) control algorithm based on Field Programmable Gate Array (FPGA) for Proton Exchange Membrane Fuel Cell (PEMFC) Model. The aim of this research is to obtain the best hydrogen partial pressure (PH2) value using FPGA ...
Read More ...
This paper proposes an off-line adaptive digital Proportional Integral Derivative (PID) control algorithm based on Field Programmable Gate Array (FPGA) for Proton Exchange Membrane Fuel Cell (PEMFC) Model. The aim of this research is to obtain the best hydrogen partial pressure (PH2) value using FPGA emulator to design and implement a digital PID controller that track the fuel cell output voltage during a variable load current applied. The off-line Particle Swarm Optimization (PSO) algorithm is used for finding and tuning the optimal value of the digital PID controller parameters that improve the dynamic behavior of the closed loop digital control fuel cell system and to achieve the stability of the desired output voltage of fuel cell. The numerical simulation results (MATLAB) package and FPGA emulator experimental work show the performance of the proposed FPGA-PID controller in terms of voltage error reduction and generating optimal value of the (PH2) control action without oscillation in the output and no saturation state when these results are compared with other control methodology.
Essra A. Jaber; Ahmed S. Al-Araji; Hayder A. Dhahad
Abstract
This paper proposes a predictive nonlinear PID neural voltagetracking controller design for Proton Exchange Membrane Fuel Cell (PEMFC)Model with an on-line auto-tuning intelligent algorithm. The purpose of theproposed robust feedback nonlinear PID neural predictive voltage controller isto find the optimal ...
Read More ...
This paper proposes a predictive nonlinear PID neural voltagetracking controller design for Proton Exchange Membrane Fuel Cell (PEMFC)Model with an on-line auto-tuning intelligent algorithm. The purpose of theproposed robust feedback nonlinear PID neural predictive voltage controller isto find the optimal value of the hydrogen partial pressure action in order tocontrol the stack terminal voltage of the (PEMFC) model for one-step-aheadprediction. The Chaotic Particle Swarm Optimization (CPSO) is utilized as astable and intelligent robust on-line auto-tuning algorithm to obtain the nearoptimal weights for the proposed controller so as to improve the performanceindex of the system as well as to minimize the energy consumption. TheSimulation results demonstrated the effectiveness of the proposed controllercompared with the linear PID neural controller
Ahmed S. Al-Araji1; Attarid K. Ahmed
Volume 18, Issue 2 , September 2018, , Page 1-16
Abstract
This paper presents a cognitive system based on a nonlinear Multi-Input Multi-Output (MIMO) Proportion Integral Derivative (PID) Modified Elman Neural Network(MENN) controller and the Square Road Map (SRM) method to guide the mobile robot duringthe continuous path-tracking with collision-free navigation ...
Read More ...
This paper presents a cognitive system based on a nonlinear Multi-Input Multi-Output (MIMO) Proportion Integral Derivative (PID) Modified Elman Neural Network(MENN) controller and the Square Road Map (SRM) method to guide the mobile robot duringthe continuous path-tracking with collision-free navigation through static obstacles. Theproposed cognitive system consists of two parts: the first part is to plan the desired path for themobile robot with the static obstacle environment in order to determine the target point and toavoid the obstacles based on the proposed square road map algorithm. The second part is toguide and track the wheeled mobile robot on the desired path equation based on the proposednonlinear MIMO-PID-MENN controller with the intelligent algorithm. The Particle SwarmOptimization (PSO) is used to on-line tune the variable control parameters of the proposedcontroller to get the optimal torques actions for the mobile robot platform. Based on using theMATLAB package (2017), the numerical simulation results show that the proposed cognitivesystem has high accuracy for planning the desired path equation in terms of avoiding the staticobstacles with smooth and short distance and generating a perfect torque action of (0.7 N.m)without a saturation state of (3.07 N.m), which leads to minimize the tracking pose error forthe mobile robot to the zero value approximation. These results were confirmed by acomparative study with different nonlinear PID controller types in terms of number ofiterations and the performance index.