research centers


Search results: Found 24

Listing 1 - 10 of 24 << page
of 3
>>
Sort by

Article
Optimizing Opto-Electronic Cellular Neural Networks Using Bees Swarm Intelligent
أفضلية التمثيل الالكتروضوئي للشبكات العصبية الخلوية باستخدام ذكاء النحل

Author: Hanan A.R.Akkar
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2010 Volume: 28 Issue: 21 Pages: 6237-6252
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This paper presents an application of Bees algorithm to the optimization of cellular neural network for opto-electronics design, where cellular neural networks bees are a large – scale nonlinear analog circuit which processes signals in real time. It is made of massive cells, which communicate with each other directly onlythrough its nearest neighbors. Each bee cell is made of a linear capacitor, a nonlinear voltage controlled current source, and a few resistive linear circuit elements with photo diode and photo-detector for connections. In this paper application of bee cellular neural networks in pattern recognition is presented with its opto-electronic circuit design. It is found the real opto-electronic arrays, with alltheir deficiencies are able to learn and perform various processing tasks well.

یقدم البحث تطبیق لذكاء النحل في تصمیم وتدریب الش بكات العص بیة الخلویة, حیث تعتبر دوائر لا خطیة تنفذ العملیات في الزمن الفعلي . تتكون الشبكات العصبیة الخلویة للنحل من مجموعة من الخلایا العصبیة متصلة مع بعضھا من خلال الاتصال المباشر فقط لكل خلیة عصبیة مع جارھا الاقرب المحیط بھا ویكون التمثیل المكافئ للخلیة الخلویة الالكتروضوئیة للنحل منمتسعة ومصدر فولتیة لا خطي معتمد على مصدر تیار ومجموعة من المقاومات الخطیة وطریقةتوصیل الخلایا العصبیة الخلویة للنحل مع المحیطة بھا تكون ضوئیة باستخدام الدایود الضوئي والمتحسس الضوئي . تم في ھذا البحث تطبیق الشبكات العصبیة الخلویة للنحل بعد تمثیلھا الكتروضوئیاً في مجال تمیز الأنماط وان ھناك مجالات متعددة للتطبیق طالما ھذه الشبكات لدیھا القدرة على التعلم لتنفیذ العملیات المعقدة


Article
Automated Electronic Circuit Design for Low Pass Filter Based on Genetic Algorithm
نمذجة التصميم الالكتروني لمرشحات الترددات الواطئة باستخدام الخوارزميات الجينية

Authors: Hanan. A. R. Akkar --- Mohammed. K. Abrahem
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2008 Volume: 26 Issue: 2 Pages: 180-188
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

In this paper a proposed method to design electronic circuits by using software approach based ongenetic algorithms is presented. The method is implemented to design low pass filter with aminimal knowledge about the design (the response of the filter and cutoff frequency).Butterworth filter type is chosen because of its smooth response. This method providesimpressive results and the circuits obtained provide higher efficiency than the circuits whichmight be designed by the expert engineer. This method allows the topology, the componentvalues, and the number of the component of the circuit to be evolved by using genetic algorithms(GAs) without human interference. Therefore, the proposed method can be expandied to be usedwith any analog (passive or active) circuit by making a few changes in the program steps (i.e. bychanging the fitness function and improving the simulation of the circuits). MATLAB (Ver. 7)language is used in programming the genetic algorithm. The circuits created by geneticalgorithms are built using EWB program to make sure that the obtained results are true andaccurate.

Keywords


Article
Training Artificial Neural Networks by PSO to Perform Digital Circuits Using Xilinx FPGA

Authors: Hanan A. R. Akkar --- Firas R. Mahdi
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2011 Volume: 29 Issue: 7 Pages: 1329-1344
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

One of the major constraints on hardware implementations of Artificial NeuralNetworks (ANNs) is the amount of circuitry required to perform the multiplicationprocess of each input by its corresponding weight and there subsequent addition. FieldProgrammable Gate Array (FPGA) is a suitable hardware IC for Neural Network (NN)implementation as it preserves the parallel architecture of the neurons in a layer andoffers flexibility in reconfiguration and cost issues. In this paper the adaption of theANN weights is proposed using Particle Swarm Optimization (PSO) as a mechanismto improve the performance of ANN and also for the reduction in the ANN hardware.For this purpose we modified the MATLAB PSO toolbox to be suitable for the takenapplication. In the proposed design training is done off chip then the fully traineddesign is download into the chip, in this way less circuitry is required. This paperexecutes four bit Arithmetic Logic Unit (ALU) implemented using Xilinx schematicdesign entry tools as an example for the implementation of digital circuits using ANNtrained by PSO algorithm.


Article
Training Artificial Neural Network Using Back-Propagation & Particle Swarm Optimization for Image Skin Diseases

Authors: Hanan A. R. Akkar --- Samem Abass Salman
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2011 Volume: 29 Issue: 13 Pages: 2739-2755
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This work is devoted to compression Image Skin Diseases by using Discrete Wavelet Transform (DWT) and training Feed-Forward Neural Networks (FFNN) by using Particle Swarm Optimization(PSO) and compares it with Back-Propagation (BP) neural networks in terms of convergence rate and accuracy of results .The comparison between the two techniques will be mentioned. A MATLAB 6.5 program is used in simulation.The structure Artificial Neural Network (ANN) of training image skin diseases is proposed as follows: 1- The proposed structure of NN that performs three compressions Images Skin training by BP algorithms with log sigmoid activation function, and three neurons in output layer.2- The proposed structure of FFNN using PSO that performs three compressions Images Skin with hardlim activation function, and three neurons in output layer. The results obtained using PSO are compared to those obtained using BP. Learning iterations (602-4700 epoch), convergence time (1sec.- 100 sec.), number of initialweights (1set - 75set), number of derivatives (0 - 38 derivatives) and accuracy (60% - 100%) are used as performance measurements. The obtained Mean Square Error (MSE) is 7 10 - to check the performance of algorithms. The results of the proposed neural networks performed indicate that PSO can be a superior training algorithm forneural networks, which is consistent with other research in the area.


Article
Integration of Swarm Intelligence and Artificial Neural Network for Medical Image Recognition
تكامل الشبكات العصبیة الاصطناعیة وذكاء السرب للتمییز الصور الطبیة

Authors: Hanan A. R. Akkar --- Samera Shams Hussain
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2013 Volume: 31 Issue: 13 Part (A) Engineering Pages: 2548-2560
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Neural network technology plays an important role in the development of newmedical diagnostic assistance or what is known as “computer aided” that based onimage recognition.Thispaper study the method used integration of back propagationneural network and Particle Swarm Optimizing (PSO) in parts of recognition the XRayof lungs for two disease cases (cancer and TB) along with the normal case. Theexperiments show that the improvement of algorithms for recognition side hasachieved a good result reached to 88.398% for input image size 1024 pixel and 500population size. The efficiency and recognition testes for training method wasperformed and reported in this paper


Article
Design of Intelligent Controller for Solar Tracking System Based on FPGA
تصميم متحكم ذكي لنظام تعقب شمسي بالاعتماد على مصفوفة البوابات الرقمية القابلة للبرمجة (FPGA)

Authors: Hanan A. R. Akkar --- Yaser M. Abid
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2015 Volume: 33 Issue: 1 Part (A) Engineering Pages: 114-128
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The needs for increasing the power generation make the use of solar cells plays an important role in the daily life. For this reason, it is important to use solar tracking system to increase or getting almost optimum amount from solar cells. In this paper, proposed intelligent controllers were designed and used to make solar cells facing the sun over the year. The proposed controller was trained by two ways; the first was trained by supervised feed forward neural network and the second by Particle Swarm Optimization (PSO) the results obtained for both designs are then compared. The controller was trained using MATLAB and then converted to SIMULINK model in order to test it, and convert it to a Very high speed integrated circuit Hardware Description Language (VHDL) language using MATLAB tool box in order to download it on Spartan 3A Field Programmable Gate Arrays (FPGAs) card. This makes the implementation of the intelligent controller more efficient and easy to use because of its reprogram-ability and the high speed performance. The controller was designed to a fully controlled DC motor driver which is used to rotate two DC motors in X-axis and Y-axis directions respectively.The experimental results show that tracking sun increases the efficiency of the system to produce energy from solar cell about 44.3778 % more energy than the solar cell without tracking system.

ان الحاجة لزيادة توليد الطاقة الكهربائية جعل استخدام الخلايا الشمسية تلعب دورا هاما في الحياة اليومية ، وعليه من المهم استخدام نظام يسمح بتتبع الخلايا الشمسية لضوء الشمس لزيادة أو الحصول على القيمة المثلى للطاقة الكهربائية من الخلايا الشمسية . اقترح في هذا العمل تصميم و حدات التحكم الذكية و التي استخدمت لجعل الخلايا الشمسية تكون بمواجهة الشمس على طول السنة . تم تدريب وحدة تحكم المقترحة بطريقتين الأولى عن طريق تغذية تحت إشراف الشبكة العصبية الامامية، و الثانية من قبل امثلة الحشد الجزيئي ( PSO ) ومن ثم مقارنة النتائج المتحصلة من كلا الطرفين. تم تدريب المتحكم بواسطة البرنامج الرياضي (MATLAB) وتم تحويله الى Simulink لغرض فحص النتائج التي تم الحصول عليها من المتحكم وبعدها تم تحويله بواسطة الاداة الموجودة في البرنامج المقترح الى لغة ال (VHDL) حيث انها اللغة التي يتعامل بها مصفوفة البوابات الرقمية القابلة للبرمجة (FPGA) وذلك لغرض تحميله على الــ (FPGA) الذي جعل بدوره التطبيق العملي لمتحكم كفوء وسهل الاستخدام وذلك لقدرته على اعادة البرمجة لعدة مرات وبالسرعة التي يمكن ان يوفرها الـ (FPGA). تم تصمم المتحكم لغرض السيطرة على حركة المحركين المستخدمين كلياً فالمحرك الاول يستخدم لتعقب الشمس بالاتجاه الايمن والايسر اما المحرك الثاني فيستخدم لتعقب الشمس بالاتجاه الاعلى والاسفل.اظهرت النتائج العملية و بالمقارنة مع الخلية الشمسية التي لا تستخدم المتحكم الذكي ان الخلايا الشمسية بالامكان ان تزداد قابليتها على توليد الطاقة الكهربائية بنسبة 44.3 % عند استخدام المسيطر.


Article
Characteristics and Evaluation of Nano Electronic Devices
تحليل خصائص العناصر النانو الكترونية

Authors: Hanan A. R. Akkar --- Sarmad Khalooq
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2014 Volume: 32 Issue: 3 Part (B) Scientific Pages: 486-497
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Recent developments in nanotechnology have demonstrated that it is feasible to manufacture Nano electronics devices using Carbon Nano Tubes (CNTs) because the mobility between the channels is increased while the switching delay is decreased. The devices based on Nano scale objects with well-defined structure and original electronic properties are great interest for the development of innovative electronic circuits. In this paper, a proposed design of carbon Nano tube transistors, Nano RAMS, Nano wires, Nano Flip Flops and Nano Diodes are presented. The Carbon Nano Tube Field Effect Transistor (CNT FET) leads to an area reduction, density of carbon Nano tube as well as the power consumption is decreased when it is compared with MOSFET. The comparison between Nano CMOS and CNTFET shows that CNTFET is very promising and superior technology for circuit design access time reduction with temperature increasing which is opposite to the Nano CMOS behavior delay. The results obtained are useful in characterizing and evaluating performance of Nano devices and related circuits. The results proved that CNTFET appears to be the best device in future for VLSI. The modeling and simulation has been implemented using MATLAB program.

يعتبر أستخدام أنابيب الكاربون النانوية من الأستخدامات الواعدة في مجال الالكترونيات في المستقبل القريب نظرﴽ لخصائصها الإلكترونية الممتازة مثل تحملها لدرجات حرارة عالية، قوة وصلادة كبيرة ، حركية عالية، توصيلية كهربائية جيدة والتوافق مع المواد ذات العازلية العالية وبأقطار صغيرة. تم درا سة أنابيب الكاربون وأنواعها المختلفة. حيث تم تصنيف أنابيب الكاربون الى نوعين أساسين وهي الأنابيب الكاربونية النانوية ذات الجدار الواحد (SWCNT)وأنابيب الكاربون متعددة الجدار(MWCNT) ومقارنتها, حيث تم اختبار تطبيقات أنابيب الكاربون لتصميم ترانزستور نوع (CNTFET) بانواعه المختلفة، الصمام الثنائي النانوي، المفتاح النانوي، بوابة النانو، نانو RAM، نطاطات النانو حيث تم تصميم هذه الانواع بالاعتماد على CNTFET. تم تحليل خصائص الترانزستور باستخدام برنامج المحاكاة الحاسوبية للمقارنة مع الانواع التقليدية، حيث تبين إمكانية عملها بتيارات قليلة تصل إلى النانو أمبير 1nA مقارنة مع ألانواع التقليدية التي تستهلك طاقة أقل. أجريت مقارنات بين CNTFET، MOSFET، نانو CMOS، بمساعدةالمختبر الرياضي MATLAB حيث بينت النتائج تفوق CNTFET من حيث السرعة والحد من وقت وصول أكثر من غير ما هوعليه حيث يمكن أعتبارCNTFET أفضل عنصر للعمل بالمستقبل في VLSI.


Article
Estimation Load Forecasting Based on the Intelligent Systems

Authors: Hanan A.R. Akkar --- Wissam H. Ali
Journal: AL-NAHRAIN JOURNAL FOR ENGINEERING SCIENCES مجلة النهرين للعلوم الهندسية ISSN: 25219154 / eISSN 25219162 Year: 2018 Volume: 21 Issue: 2 Pages: 285-291
Publisher: Al-Nahrain University جامعة النهرين

Loading...
Loading...
Abstract

The daily peak load forecasting for the next day is the basic operation of generation scheduling. The approach of using ANN methodology alone is limited which has generated interest to explore hybrid system. In this paper a search of genetic programming to a short term load forecasting is presented. A genetic architecture with the fitness normalization has been used to find as optimum data peak load of Baghdad city. The optimize data applied to the ANN to be trained and tested to estimate the daily peak load of Baghdad city. Different cases for load forecasting are considered with the aid of MATLAB 7 package to get the estimation of the next day. So an improvement method of genetic optimization is proposed to get a better solution for the load estimation rather than artificial neural network.


Article
Artificial Intelligent Technique for Power Management Lighting Based on FPGA

Authors: Hanan A. R. Akkar --- Sameh J. Mohammed
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2020 Volume: 38 Issue: 2 part (A) Engineering Pages: 232-239
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

The modern technological advances gave rise to new intelligent ways ofperformance and management in various fields of our lives. The employment ofthe artificial intelligent techniques proved influential in enhancing thetechnological developments and in meeting the demands for new, more efficient,more reliable and faster ways of performing activities and tasks. Lighting systemsare an important part of human life. For this reason, it is important to reduce andmanage energy consumption properly. Light dimming paves the way for massiveenergy saving in lighting applications. The options include simply reducing theoutput during the night and achieve maximum saving with variable dimming.Advantage can be taken of off-peak times (no light needed) to reduce energyconsumption significantly. Pulse Width Modulation (PWM) technique is used asdimming method. The proposed system offers intelligent management of lightingto reduce power consumption, extend lamp life and reduce maintenance. In thiswork, we will be using multiple sensors such as light dependent resistor (LDR)and Motion Sensor (PIR) for LED dimming system to achieve intelligent LEDlighting system to manage energy consumption. The data collected by sensors isprocessed by Artificial Neural Network (ANN), which is implemented by usingField Programmable Gate Arrays (FPGAs), Spartan 3A starter kit that controlsthe light intensity of LED from changing the duty cycle of the PWM signals.FPGA was used to implement the design, because of the re-programmability ofthe FPGAs, which can support the re-configuration necessary to implement thedesign. VHDL program was used to describe the functions of all necessarycomponents used. Xilinx ISE 14.7 design suite and MATLAB R2012A were usedas software tools to perform Spartan 3A starter kit program. The Simulationresults were obtained with Xilinx blocks found in MATLAB program


Article
Detection of Biomedical Images by Using Bio-inspired Artificial Intelligent

Authors: Hanan A. R. Akkar --- Sameem A. Salman
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2020 Volume: 38 Issue: 2 part (A) Engineering Pages: 255-264
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Computer vision and image processing are extremely necessary formedical pictures analysis. During this paper, a method of Bio-inspiredArtificial Intelligent (AI) optimization supported by an artificial neuralnetwork (ANN) has been widely used to detect pictures of skin carcinoma.A Moth Flame Optimization (MFO) is utilized to educate the artificialneural network (ANN). A different feature is an extract to train theclassifier. The comparison has been formed with the projected sample andtwo Artificial Intelligent optimizations, primarily based on classifierespecially with, ANN-ACO (ANN training with Ant Colony Optimization(ACO)) and ANN-PSO (training ANN with Particle Swarm Optimization(PSO)). The results were assessed using a variety of overall performancemeasurements to measure indicators such as Average Rate of Detection(ARD), Average Mean Square error (AMSTR) obtained from training,Average Mean Square error (AMSTE) obtained for testing the trainednetwork, the Average Effective Processing Time (AEPT) in seconds, andthe Average Effective Iteration Number (AEIN). Experimental resultsclearly show the superiority of the proposed (ANN-MFO) model withdifferent features.

Listing 1 - 10 of 24 << page
of 3
>>
Sort by
Narrow your search

Resource type

article (24)


Language

English (23)

Arabic and English (1)


Year
From To Submit

2020 (2)

2019 (1)

2018 (1)

2017 (1)

2016 (1)

More...