research centers


Search results: Found 7

Listing 1 - 7 of 7
Sort by

Article
Spam Classification Using MOEA/D

Authors: Rand Ahmad Atta --- Soukaena H. Hashem --- Ekhlas Khalaf Gbashi
Journal: Al-Nahrain Journal of Science مجلة النهرين للعلوم ISSN: (print)26635453,(online)26635461 Year: 2018 Volume: 21 Issue: 4 Pages: 109-118
Publisher: Al-Nahrain University جامعة النهرين

Loading...
Loading...
Abstract

In mathematics, it’s very easy to find the maximum point or minimum point of a function or a set of functions, but it’s difficult to find a set of function simultaneously in the real world due to the different kinds of mathematical relationships between objective functions. So the multi objective optimization algorithm has the ability to deal with a many objectives instead of one objective, because of the difficulties in the classical methods of multi objectives optimization, the evolutionary algorithm (EA) is effective to eliminate these difficulties, in order to apply the evolutionary algorithms to improve the multi-objective optimization algorithm, the multi - objective evolutionary algorithm based on decomposition is one of the algorithms that solve multi objective optimization problems. This paper aims to enhance the e-mail spam filtering by using multi - objective evolutionary algorithm for classifying the e-mail messages to spam or non-spam in high accuracy. The first step in the proposal is applying normalization. The second step is applying feature selection which is implemented to choose the best features. Finally, implement multi - objective evolutionary algorithm based on decomposition. The evaluation of the performance of model by using testing databases from the spam database. The model depended accuracy as a criterion to evaluate model performance. The experimental results showed that the proposed system provides good accuracy in the experiment 1 (91%), very good accuracy in the experiment 2 (92%) and excellent accuracy in the experience 3 (98%).


Article
Optimal Multi-objective Robust Controller Design for Magnetic Levitation System

Loading...
Loading...
Abstract

Abstract- In this work, the design of three types of robust controllers is presented to control the magnetic levitation system. These controllers are: basic H∞ controller, robust Genetic Algorithm (GA) based PID (GAPID) controller and robust Particle Swarm Optimization (PSO) based PID (PSOPID) controller. In the second and third controllers, the GA and PSO methods are used to tune the parameters of PID controller subject to multi-objective cost function (H∞ constraints and time domain specifications). The use of GA and PSO methods is used to simplify the design procedure and to overcome the difficulty of the resulting high order controller of the basic H∞ controller. The ability of the proposed controllers in compensating the system with a wide range of system parameters change is demonstrated by simulation using MATLAB 7.14.


Article
Multiple Performance Optimization of Carburized Steel Using Taguchi Based Moora Approach

Authors: Asraa K. Hameed --- Laith K. Abbas --- Abbas K. Hussein
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2018 Volume: 36 Issue: 7 Part (A) Engineering Pages: 770-776
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

In this research, a multi-response optimization based on Taguchi method-based MOORA (Multi-response optimization based on ratio analysis) is proposed for carburization process of low carbon steel. Experiments were designed using (Taguchi’s) method with six input carburization factors (carburization temperature, carburization time, tempering temperature, tempering time, activator wt.%, and quench media). Depth case and wear rate were considered as the most response measures in this study. Results of the analysis shows that the carburization temperature is the most significant variables for the optimum outcome results. The desired response measures and mathematical model were achieved and used as optimum condition tool. The outcome of this study had been explored the possible use of the developed carburized steel in high wear resistance applications.


Article
An Imperialist Competitive Algorithm for Sitting and Sizing of Distributed Generation in Radial Distribution Network to Improve Reliability and Losses Reduction

Authors: Farzaneh Ostovar --- Mahdi Mozaffari Legha
Journal: Iraqi Journal for Electrical And Electronic Engineering المجلة العراقية للهندسة الكهربائية والالكترونية ISSN: 18145892 Year: 2013 Volume: 9 Issue: 2 Pages: 59-66
Publisher: Basrah University جامعة البصرة

Loading...
Loading...
Abstract

Distributed Generation (DG) can help in reducing the cost of electricity to the costumer, relieve network congestion and provide environmentally friendly energy close to load centers. Its capacity is also scalable and it provides voltage support at distribution level. Hence, DG placement and penetration level is an important problem for both the utility and DG owner. The Optimal Power Flow (OPF) has been widely used for both the operation and planning of a power system. The OPF is also suited for deregulated environment.Four different objective functions are considered in this study: (1) Improvement voltage profile (2) minimization of active power loss (3) maximum capacity of conductors (4) maximization of reliability level. The site and size of DG units are assumed as design variables. The results are discussed and compared with those of traditional distribution planning and also with Imperialist competitive algorithm (ICA).


Article
Multi-layer Multi-objective Evolutionary Algorithm for Adjustable Range Set Covers Problem in Wireless Sensor Networks
خوارزمية تطورية متعددة الطبقات و الأهداف لمشكلة تعديل نطاق مجموعة أغلفة في شبكات الأستشعار اللاسلكي

Authors: Bara'a Ali Attea براء علي عطية --- Dlsoz Abdalkarim Rashid دلسوز عبد الكريم رشيد
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2016 Volume: 57 Issue: 1C Pages: 755-767
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Establishing complete and reliable coverage for a long time-span is a crucial issue in densely surveillance wireless sensor networks (WSNs). Many scheduling algorithms have been proposed to model the problem as a maximum disjoint set covers (DSC) problem. The goal of DSC based algorithms is to schedule sensors into several disjoint subsets. One subset is assigned to be active, whereas, all remaining subsets are set to sleep. An extension to the maximum disjoint set covers problem has also been addressed in literature to allow for more advance sensors to adjust their sensing range. The problem, then, is extended to finding maximum number of overlapped set covers. Unlike all related works which concern with the disc sensing model, the contribution of this paper is to reformulate the maximum overlapped set covers problem to handle the probabilistic sensing model. The problem is addressed as a multi-objective optimization (MOO) problem and the well-known decomposition based multi-objective evolutionary algorithm (MOEA/D) is adopted to solve the stated problem. A Multi-layer MOEA/D is suggested, wherein each layer yields a distinct set cover. Performance evaluations in terms of total number of set covers, total residual energy, and coverage reliability are reported through extensive simulations. The main aspect of the results reveals that the network's lifetime (i.e. total number of set covers) can be extended by increasing number of sensors. On the other hand, the coverage reliability can be increased by increasing sensing ranges but at the expense of decreasing the network's lifetime.

في الأدبيات تم اقتراح العديد من خوارزميات جدولة أجهزة الأستشعار باعتبارها مشكلة أمتداد لما يسمى مشكلة (DSC) والغاية منها هو ترتيب أكبر عدد ممكن من المجموعات الفرعية المنفصلة لأجهزة الاستشعار. بعد ذلك يتم تعيين مجموعة فرعية واحدة فقط من أجهزة الاستشعار لتكون نشطة لأداء عملية التغطية، في حين يتم تسكين بقية المجموعات الفرعية. أحد أهم امتدادات هذه المشكلة هو تحديد العدد الأقصى من المجاميع الفرعية وبنفس الوقت تضبيط قابلية التغطية لكل مستشعر وعلى هذا الأساس ممكن أن تتحول المجاميع من مجاميع منفصلة الى مجاميع مركبة مؤدية في النهاية الى زيادة تعقيد المشكلة. هدف هذا البحث هو إعادة صياغة مشكلة العدد الأقصى من المجاميع المتراكبة آخذا بنظر الأعتبار القابلية الواقعية لتحسس المستشعرات. تم أعتماد الخوارزمية التطورية متعددة الأهداف المعروفة (MOEA / D) في حل المشكلة المذكورة. تم اقتراح تخطيط متعدد الطبقات لتصميم الخوارزمية ، حيث تنتج كل طبقة مجموعة متميزة من أجهزة الاستشعار النشطة. تم تقييم أداء النموذج المقترح من ثلاثة جوانب: من حيث العدد الإجمالي للمجاميع المتراكبة، ومجموع الطاقة المتبقية، وموثوقية التغطية من خلال محاكاة واسعة النطاق. النتائج المتوفرة تبين تأثير العوامل المختلفة بما في ذلك عدد أجهزة الاستشعار ونطاق التغطية للمستشعر. الجانب الرئيسي من النتائج تكشف عن أن عمر الشبكة (أي العدد الإجمالي للمجماميع المتراكبة) يتزايد مع تزايد عدد المستشعرات المتوفرة. من ناحية أخرى، يمكن زيادة موثوقية التغطية عن طريق زيادة نطاقات الاستشعار ولكن على حساب تناقص عمر الشبكة.


Article
Extractive Multi-Document Text Summarization Using Multi-Objective Evolutionary Algorithm Based Model
التلخيص الأقتطاعي للنصوص متعددة المستندات باستخدام نموذج مستند على الخوارزمية التطورية متعددة الاهداف

Authors: Hilal H. Saleh هلال هادي صالح --- Nasreen J. Kadhim نسرين جواد كاظم
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2016 Volume: 57 Issue: 1C Pages: 728-741
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Automatic document summarization technology is evolving and may offer a solution to the problem of information overload. Multi-document summarization is an optimization problem demanding optimizing more than one objective function concurrently. The proposed work considers a balance of two significant objectives: content coverage and diversity while generating a summary from a collection of text documents. Despite the large efforts introduced from several researchers for designing and evaluating performance of many text summarization techniques, their formulations lack the introduction of any model that can give an explicit representation of – coverage and diversity – the two contradictory semantics of any summary. The design of generic text summarization model based on sentence extraction is modeled as an optimization problem redirected into more semantic measure reflecting individually both content coverage and content diversity as an explicit individual optimization models. The proposed two models are then coupled and defined as a multi-objective optimization (MOO) problem. Up to the best of our knowledge, this is the first attempt to address text summarization problem as a MOO model. Moreover, heuristic perturbation and heuristic local repair operators are proposed and injected into the adopted evolutionary algorithm to harness its strength. Assessment of the proposed model is performed using document sets supplied by Document Understanding Conference 2002 (DUC 2002) and a comparison is made with other state-of-the-art methods using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit. Results obtained support strong proof for the effectiveness of the proposed model based on MOO over other state-of-the-art models.

تقنية التلخيص الأوتوماتيكي تطور وربما تقدم حل الى مشكلة الحمل الزائد للمعلومات. عملية التلخيص للنصوص متعددة المستندات تصنف على انها مشكلة أمثلية تتطلب الاستفادة المثلى من اكثر من دالة هدف في وقت واحد. العمل المقترح يأخذ بنظر الأعتبار تحقيق التوازن بين هدفين مهمين هما: تغطية المحتوى لمجموعة المستندات والتنوع عند توليد ملخص من مجموعة من المستندات النصية. على الرغم من الجهود القائمة على تصميم و تقييم أداء العديد من تقنيات تلخيص النصوص, تفتقر صياغات هذه التقنيات الى تقديم أي نموذج يمكن أن يعطي التمثيل الصريح – تغطية المحتوى والتنوع – وهما دلالتان متناقضتان في أي ملخص. أن تصميم نموذج يهدف الى تلخيص نص عام قائم على أقتطاع الجمل تمت أعادة توجيهه الى تدبير ذات دلالة اكبر يعكس بصورة مستقلة كلا من تغطية وتنوع المحتوى كنموذجي أمثلية صريحين. بعد ذلك تمت عملية اقتران النموذجين المقترحين وتعريفهما كمشكلة أمثلية تعدد الاهداف. حسب علمنا ، هذه هي المحاولة الأولى لمعالجة مشكلة تلخيص النصوص كنموذج أمثلية متعدد الأهداف. وعلاوة على ذلك ، تم أقتراح عامل توجيه اضطراب وعامل توجيه أصلاح محلي وحقنهما في الخوارزمية التطورية المعتمدة لتسخير قوتها . عملية تقييم النموذج المقترح تمت باستخدام مجموعة المستندات المجهزة من قبل مجموعة البيانات العالمية (Document Understanding Conference DUC 2002) وقد تمت مقارنة النتائج المتحصلة مع مجموعة من الانظمة الحديثة. قياس وتقييم الأداء للنموذج المقترح تم باستخدام أدوات (ROUGE). النتائج المتحصلة دعمت العمل بدليل قوي على فعالية النموذج المقترح المستند على أمثلية تعدد الاهداف نسبة الى النماذج الحديثة التي تمت المقارنة بها.


Article
Improving Extractive Multi-Document Text Summarization Through Multi-Objective Optimization

Authors: Nasreen J. Kadhim --- Hilal H. Saleh --- Bara’a Attea
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2018 Volume: 59 Issue: 4B Pages: 2135-2149
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Multi-document summarization is an optimization problem demanding optimization of more than one objective function simultaneously. The proposed work regards balancing of the two significant objectives: content coverage and diversity when generating summaries from a collection of text documents. Any automatic text summarization system has the challenge of producing high quality summary. Despite the existing efforts on designing and evaluating the performance of many text summarization techniques, their formulations lack the introduction of any model that can give an explicit representation of – coverage and diversity – the two contradictory semantics of any summary. In this work, the design of generic text summarization model based on sentence extraction is redirected into more semantic measure reflecting individually both content coverage and content diversity as two explicit optimization models. The problem is defined by projecting the first criterion, i.e. content coverage in the light of text similarity. The proposed model hypothesizes a possible decomposition of text similarity into three different levels of optimization formula. First, aspire to global optimization, the candidate summary should cover the summary of the document collection. Then, to attain, less global optimization, the sentences of the candidate summary should cover the summary of the document collection. The third level of optimization is content with local optimization, where the difference between the magnitude of terms covered by the candidate summary and those of the document collection should be small. This coverage model is coupled with a proposed diversity model and defined as a Multi-Objective Optimization (MOO) problem. Moreover, heuristic perturbation and heuristic local repair operators have been proposed and injected into the adopted evolutionary algorithm to harness its strength. Assessment of the proposed model has been performed using document sets supplied by Document Understanding Conference 2002 (DUC2002) and a comparison has been made with other state-of-the-art methods. Metric used to measure performance of the proposed work is Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit. Results obtained support strong proof for the effectiveness and the significant performance awarded to the proposed MOO model over other state-of-the-art models.

Listing 1 - 7 of 7
Sort by
Narrow your search

Resource type

article (7)


Language

English (7)


Year
From To Submit

2018 (3)

2016 (2)

2015 (1)

2013 (1)