research centers


Search results: Found 23

Listing 1 - 10 of 23 << page
of 3
>>
Sort by

Article
Determine the effect of giving a patient multiple drugs at the same time by using neural network
تحديد تأثير إعطاء المريض أدوية متعددة في الوقت نفسه باستخدام الشبكة العصبية

Authors: Wedad Abdul khaddar Nasir وداد عبد القادر نصر --- Safana Hyder Abbas سفانة حيدر عباس
Journal: Iraqi Journal of Information Technology المجلة العراقية لتكنولوجيا المعلومات ISSN: 19948638/26640600 Year: 2017 Volume: 7 Issue: 4 اللغة الانكليزية Pages: 180-191
Publisher: iraqi association of information الجمعية العراقية لتكنولوجيا المعلومات

Loading...
Loading...
Abstract

The aim of this study is to construct a neural network for drug-interaction to facilitate the task of finding the interaction which occur between multiple drugs given to the patient at the same time. The suggested system used to enable physicians and pharmacists to find the interaction which occur between multiple drugs prescribed to patients to get the safe, beneficial and effective therapy. The suggested system may be considered as practical approach that can be implemented in general hospitals, pharmacies, also in colleges as educational and teaching system. It was a good practice for physician pharmacists to use the computer for prescribing a safe therapy to patients and for learning

الهدف من هذا البحث هو تكوين شبكة عصبية باستخدام خوارزميةBack-propagation من اجل تسهيل اكتشاف التداخل بين الادوية عندما يتناول المريض أكثر من دواء بنفس الوقت . الطريقة المقترحة تساعد الاطباء و الصيادلة في المستشفيات و كليات المجموعة الطبية لتحديد نوع الضرر الذي يصيب المريض نتيجة تناوله اكثر من دواء بنفس الوقت.


Article
Model Reference Adaptive Control based on a Self-Recurrent Wavelet Neural Network Utilizing Micro Artificial Immune Systems
نظام سيطرة متكيف ذو موديل مرجعي مبني على شبكة عصبية مويجية ذاتية التكرار باستخدام أنظمة المناعة الصناعية الدقيقة

Authors: Maryam Hassan Dawood مريم حسن داود --- Omar Farouq Lutfy عمر فاروق لطفي
Journal: Al-Khwarizmi Engineering Journal مجلة الخوارزمي الهندسية ISSN: 18181171 23120789 Year: 2017 Volume: 13 Issue: 2 Pages: 107-122
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

This paper presents an intelligent model reference adaptive control (MRAC) utilizing a self-recurrent wavelet neural network (SRWNN) to control nonlinear systems. The proposed SRWNN is an improved version of a previously reported wavelet neural network (WNN). In particular, this improvement was achieved by adopting two modifications to the original WNN structure. These modifications include, firstly, the utilization of a specific initialization phase to improve the convergence to the optimal weight values, and secondly, the inclusion of self-feedback weights to the wavelons of the wavelet layer. Furthermore, an on-line training procedure was proposed to enhance the control performance of the SRWNN-based MRAC. As the training method, the recently developed modified micro artificial immune system (MMAIS) was used to optimize the parameters of the SRWNN. The effectiveness of this control approach was demonstrated by controlling several nonlinear dynamical systems. For each of these systems, several evaluation tests were conducted, including control performance tests, robustness tests, and generalization tests. From these tests, the SRWNN-based MRAC has exhibited its effectiveness regarding accurate control, disturbance rejection, and generalization ability. In addition, a comparative study was made with other related controllers, namely the original WNN, the artificial neural network (ANN), and the modified recurrent network (MRN). The results of these comparison tests indicated the superiority of the SRWNN controller over the other related controllers.

يقدم هذا البحث نظام سيطرة متكيفا ذا موديل مرجعي ذكي باستخدام شبكة عصبية مويجية ذاتية التكرار للسيطرة على الأنظمة اللاخطية. الشبكة المقترحة هي نسخة محسنة لشبكة عصبية مويجية منشورة سابقا. وبالتحديد, هذا التحسين تم انجازه بتبني تعديلين على هيكل الشبكة الاصلي. وهذان التعديلات يتضمنان أولا استخدام مرحلة محددة لتوليد الأوزان لتحسين الاقتراب نحو قيم الأوزان المثلى, وثانيا تضمين أوزان ذاتية الإشارة العائدة لمويجات الطبقة المويجية. فضلا عن ذلك, تم اقتراح طريقة تعليم انية لتحسين أداء نظام السيطرة المقترح. وبوصفها طريقة تعليم, تم استخدام نظام المناعة الصناعي الدقيق المعدل والذي طور حديثا لايجاد القيم المثلى لمعاملات الشبكة المستخدمة. وقد تم عرض كفائة الطريقة المستخدة بالسيطرة على عدة انظمة ديناميكية لاخطية. وقد تم اعتماد عدة اختبارات تقييم لكل نظام مسيطر عليه وهذه الاختبارات تتضمن اختبارات اداء السيطرة و اختبارات المتانة واختبارات التعميم. ومن هذه الاختبارات اظهر النظام المقترح كفائته من حيث دقة السيطرة و رفض المؤثرات الخارجية وقابلية التعميم. بالاضافة لهذه الإختبارات, تم اجراء دراسة مقارنة مع مسيطرات اخرى ذات صلة وبالتحديد الشبكة العصبية المويجية الأصلية و الشبكة العصبية الصناعية والشبكة التكرارية المعدلة. وقد اظهرت نتائج هذه الدراسة تفوق المسيطر المقترح على المسيطرات الأخرى.


Article
Predicting the Daily Evaporation in Ramadi City by Using Artificial Neural Network
التنبؤ بالتبخر اليومي باستخدام الشبكات العصبية الصناعية

Author: Atheer Saleem Almawla
Journal: Anbar Journal of Engineering Sciences مجلة الأنبار للعلوم الهندسية ISSN: 19979428 Year: 2017 Volume: 7 Issue: 2 Pages: 134-139
Publisher: University of Anbar جامعة الانبار

Loading...
Loading...
Abstract

In this paper the artificial neural network used to predict dilly evaporation. The model was trained in MATLAB with five inputs. The inputs are Min. Temperature, Max. Temperature, average temperature, wind speed and humidity. The data collected from Alramadi meteorological station for one year. The transfer function models are sigmoid and tangent sigmoid in hidden and output layer, it is the most commonly used nonlinear activation function. The best numbers of neurons used in this paper was three nodes. The results concludes, that the artificial neural network is a good technique for predicting daily evaporation, the empirical equation can be used to compute daily evaporation (Eq.6) with regression more than 96% for all (training, validation and testing) as well as, in this model that the Max. Temperature is a most influence factor in evaporation with importance ratio equal to (30%) then humidity (26%).


Article
Multibiometric Identification System based on SVD and Wavelet Decomposition

Authors: R.A. Hussein --- H.A. Jeiad --- M.N. Abdullah
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2017 Volume: 35 Issue: 1 Part (A) Engineering Pages: 61-67
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

Biometric systems refer to the systems used for human recognition based on their characteristics. These systems are widely used in security institutions and access control. In this work three biometric sources were used for identification purposes. Singular value decomposition (SVD) was employed as a tool for feature extraction and artificial neural network (ANN) was used as pattern recognition for the model. High accuracy was obtained from this work with 95% recognition rate.


Article
SPRING BACK PREDICTION IN V-DIE BENDING PROCESS USING ARTIFICIAL NEURAL NETWORK (ANN)

Author: Mostafa Adel Abdullah
Journal: Al-Qadisiyah Journal for Engineering Sciences مجلة القادسية للعلوم الهندسية ISSN: 19984456 Year: 2017 Volume: 10 Issue: 2 Pages: 180-190
Publisher: Al-Qadisiyah University جامعة القادسية

Loading...
Loading...
Abstract

The Bending process is the critical operation in the sheet forming, there are large parameters influence on operation. Spring back is considering large influential indication to specify the quality of product parts. The basic parameters which are takes to study in this paper are: speed of punch, time of hold and thickness of plate. Experiment use L16 array with four levels for every parameters using V-bending die with 900, with different thickness of (0.5,1,1.5,2) mm ,hold time (0,5,10,15) min and punch speed(10,20,50,100)mm/min, for (1050) Al –alloy having employed as the work pieces. Spring back value prediction use Artificial Neural Network with conventional configuration. The results show that the thickness of plate is the large influential parameter effect in spring back by 77.29%, then punch speed by 10.51% and hold time by 3.36%. The predict result using Artificial Neural Network shown a best accuracy with (99.35%) in spring back compared to the measured value.


Article
Compression Index and Compression Ratio Prediction by Artificial Neural Networks
التنبؤ بمؤشر ونسبة الانضغاط بواسطة الشبكات العصبية الاصطناعية

Authors: Abbas Jawad Al-Taie عباس جواد الطائي --- Ahmed Faleh Al-Bayati احمد فالح البياتي --- Zahir Noori M. Taki زاهر نوري محمد تقي
Journal: Journal of Engineering مجلة الهندسة ISSN: 17264073 25203339 Year: 2017 Volume: 23 Issue: 12 Pages: 96-106
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Information about soil consolidation is essential in geotechnical design. Because of the time and expense involved in performing consolidation tests, equations are required to estimate compression index from soil index properties. Although many empirical equations concerning soil properties have been proposed, such equations may not be appropriate for local situations. The aim of this study is to investigate the consolidation and physical properties of the cohesive soil. Artificial Neural Network (ANN) has been adapted in this investigation to predict the compression index and compression ratio using basic index properties. One hundred and ninety five consolidation results for soils tested at different construction sites in Baghdad city were used. 70% of these results were used to train the prediction ANN models and the rest were equally divided to test and validate the ANN models. The performance of the developed models was examined using the correlation coefficient R. The final models have demonstrated that the ANN has capability for acceptable prediction of compression index and compression ratio. Two equations were proposed to estimate compression index using the connecting weights algorithm, and good agreements with test results were achieved.

ان معرفة خصائص الانضمام للتربة مهم في التصميم الجيوتقني. نظرا للوقت والنفقات المتضمنة في إجراء اختبارات الانضمام، فإن المعادلات التجريبية التي تتضمن مؤشرات خصائص التربة مطلوبة لتقدير مؤشر الانضغاط. وعلى الرغم من اقتراح العديد من المعادلات التجريبية المتعلقة بخصائص التربة، فإن هذه المعادلات قد لا تكون مناسبة للحالات المحلية. الهدف من هذه الدراسة هو إقامة علاقة ارتباط بين خصائص الانضمام والخصائص الفيزيائية للتربة المتماسكة. وقد تم استخدام الشبكة العصبية الاصطناعية (ANN) للتنبؤ بمؤشر ونسبة الانضغاط من الخصائص لأكثر بساطة. تم استخدام مئة وخمسة وتسعين نتيجة اختبار انضمام للتربة التي تم أخذ عيناتها من مواقع البناء المختلفة في مدينة بغداد. استخدمت 70٪ من هذه النتائج لتدريب نماذج الـ(ANN) وباقي النتائج قسمت بالتساوي للاختبار والتحقق من صحة نماذج الـ(ANN). تم فحص أداء النماذج الرياضية المطورة باستخدام معامل الارتباط R. وقد أظهرت النماذج النهائية قدرة الـ(ANN) على التنبؤ باؤشر الانضغاط ونسبة الانضغاط بشكل مقبول. تم اقتراح معادلتين لتقدير مؤشر الانضغاط باستخدام خوارزمية أوزان الربط (connecting weights algorithm)، وتم التوصل إلى تقارب جيد مع نتائج الاختبار


Article
Fingerprints Identification Using Contourlet Transform

Authors: T.M. Salman --- M.K.M. Al-Azawi
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2017 Volume: 35 Issue: 3 Part (A) Engineering Pages: 282-288
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

This paper suggests the use of contourlet transform for efficient feature extraction of fingerprints for identification purposes. Back propagated neural network is then used as a classifier. Two fingerprints databases are used to test the system. These include fingerprints images with different positions, rotations and scales to test the robustness of the system. Computer simulation results show that the proposed contourlet transform outperforms the classical wavelet method. Where an identification rate of 94.4% was obtained using contourlet transform compare with 87% using wavelet transform for standard FVC2002 database.


Article
Combined Neural Network and PD Adaptive Tracking Controller for Ship Steering System

Author: Abdul-Basset Al- Hussein
Journal: Iraqi Journal for Electrical And Electronic Engineering المجلة العراقية للهندسة الكهربائية والالكترونية ISSN: 18145892 Year: 2017 Volume: 13 Issue: 1 Pages: 59-66
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

In this paper, a combined RBF neural network sliding mode control and PD adaptive tracking controller is proposed for controlling the directional heading course of a ship. Due to the high nonlinearity and uncertainty of the ship dynamics as well as the effect of wave disturbances a performance evaluation and ship controller design is stay difficult task. The Neural network used for adaptively learn the uncertain dynamics bounds of the ship and their output used as part of the control law moreover the PD term is used to reduce the effect of the approximation error inherited in the RBF networks. The stability of the system with the combined control law guaranteed through Lyapunov analysis. Numeric simulation results confirm the proposed controller provide good system stability and convergence.


Article
Hover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller

Author: Abdul-Basset A. Al-Hussein
Journal: Iraqi Journal for Electrical And Electronic Engineering المجلة العراقية للهندسة الكهربائية والالكترونية ISSN: 18145892 Year: 2017 Volume: 13 Issue: 1 Pages: 67-72
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

Unmanned aerial vehicles (UAV), have enormous important application in many fields. Quanser three degree of freedom (3-DOF) helicopter is a benchmark laboratory model for testing and validating the validity of various flight control algorithms. The elevation control of a 3-DOF helicopter is a complex task due to system nonlinearity, uncertainty and strong coupling dynamical model. In this paper, an RBF neural network model reference adaptive controller has been used, employing the grate approximation capability of the neural network to match the unknown and nonlinearity in order to build a strong MRAC adaptive control algorithm. The control law and stable neural network updating law are determined using Lyapunov theory.


Article
Neural Network-Based Adaptive Control of Robotic Manipulator: Application to a Three Links Cylindrical Robot

Author: Abdul-Basset A. AL-Hussein
Journal: Iraqi Journal for Electrical And Electronic Engineering المجلة العراقية للهندسة الكهربائية والالكترونية ISSN: 18145892 Year: 2017 Volume: 13 Issue: 1 Pages: 114-122
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

A composite PD and sliding mode neural network (NN)-based adaptive controller, for robotic manipulator trajectory tracking, is presented in this paper. The designed neural networks are exploited to approximate the robotics dynamics nonlinearities, and compensate its effect and this will enhance the performance of the filtered error based PD and sliding mode controller. Lyapunov theorem has been used to prove the stability of the system and the tracking error boundedness. The augmented Lyapunov function is used to derive the NN weights learning law. To reduce the effect of breaching the NN learning law excitation condition due to external disturbances and measurement noise; a modified learning law is suggested based on e-modification algorithm. The controller effectiveness is demonstrated through computer simulation of cylindrical robot manipulator.

Listing 1 - 10 of 23 << page
of 3
>>
Sort by
Narrow your search

Resource type

article (23)


Language

English (21)

Arabic and English (2)


Year
From To Submit

2017 (23)