research centers


Search results: Found 23

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

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.


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
The method of Weighted Multi objective Fractional Linear Programming Problem (MOFLPP)
طريقة الاوزان لمسائل البرمجة الخطية الكسرية المتعددة

Authors: Waleed Khalid Jaber وليد خالد جابر --- Zeanab k. jabar زينب كاظم جبار
Journal: Journal of university of Anbar for Pure science مجلة جامعة الانبار للعلوم الصرفة ISSN: ISSN: 19918941 Year: 2013 Volume: 7 Issue: 2
Publisher: University of Anbar جامعة الانبار

Loading...
Loading...
Abstract

More theories and algorithms in non-linear programming with titles convexity (Convex). When the objective function is fractional function, will not have to have any swelling, but can get other good properties have a role in the development of algorithms decision problem.In this work we focus on the weights method- (one of the classical methods to solve Multi objective convex case problem). Since we have no convex or no concave objective functions, and this condition is essential part on this method implementation, we these valid conditions under method as generator sets efficient and weakly efficient this problem. This raises the need to a detailed study of pseudoconvex idea, cause convex idea, Invex, pseudoinvex idea,…, etc. concepts. Offer a numerical example to show the valid by the conditions previously set generate all weakly efficient set our problem.

أكثر النظريات والخوارزميات في البرمجة غير الخطية تحمل عناوين التحدب (Convex). عندما تكون دالة الهدف دالة كسرية ، سوف لن يكون لدينا أي انتفاخ ، ولكن يمكن الحصول على خصائص جيدة أخرى يكون لها دور في تطوير خوارزميات مشكلة القرار. في هذا البحث نركز على طريقة الأوزان، وتكون دالة الهدف غير محدبة او غير مقعرة ، وهذا الشرط هو جزء أساسي في طريقة التنفيذ ، لدراسة هذه الطريقة بعمق ، لاثبات صحة هذا الشرط لابد من دراسة مفصلة لفكرة التحدب (Convex)، والـ Invex function ... الخ من المفاهيم.


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
A Multi-Objective Evolutionary Algorithm based Feature Selection for Intrusion Detection
اختيار الميزة المعتمد على الخوارزمية التطورية متعددة الاهداف لكشف التطفل

Authors: Dhuha I. Mahmood ضحى عماد محمود --- Sarab M. Hameed سراب مجيد حميد
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2017 Volume: 58 Issue: 1C Pages: 536-549
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

Nowad ays, with the development of internet communication that provides many facilities to the user leads in turn to growing unauthorized access. As a result, intrusion detection system (IDS) becomes necessary to provide a high level of security for huge amount of information transferred in the network to protect them from threats. One of the main challenges for IDS is the high dimensionality of the feature space and how the relevant features to distinguish the normal network traffic from attack network are selected. In this paper, multi-objective evolutionary algorithm with decomposition (MOEA/D) and MOEA/D with the injection of a proposed local search operator are adopted to solve the Multi-objective optimization (MOO) followed by Naïve Bayes (NB) classifier for classification purpose and judging the ability of the proposed models to distinguish between attack network traffic and normal network traffic. The performance of the proposed models is evaluated against two baseline models feature vitality based reduction method (FVBRM) and NB. The experiments on network security laboratory-knowledge discovery and data mining (NSL-KDD) benchmark dataset ensure the ability of the proposed MOO based models to select an optimal subset of features that has a higher discriminatory power for discriminating attack from normal over the baselines models. Furthermore, the proposed local search operator ensures its ability to harness the performance of MOO model through achieving an obvious feature reduction on average from 16.83 features to 8.54 features (i.e., approximately 50%) in addition to the increase in NB classifier accuracy from 98.829 to 98.859 and detection rate from 98.906 to 99.043.

في الوقت الحاضر، مع تطور الاتصالات عبر الانترنيت والتي تقدم العديد من التسهيلات للمستخدم يؤدي ذلك بدوره الى تزايد الوصول غير المصرح به. ونتيجة لذلك، اصبح نظام كشف التطفل ضروري لتوفير مستوى عالي من الأمن لكمية كبيرة من المعلومات المنقولة في الشبكة لحمايتها من التهديدات. واحدة من التحديات الرئيسية لكشف التطفل هي الأبعاد العالية من فضاء الميزة وكيفية تحديد الميزات ذات الصلة لتمييز حركة المرور الطبيعية على الشبكة من الهجوم. في هذا البحث، اعتمدت الخوارزمية التطورية متعددة الاهداف مع التحلل (MOEA/D) و (MOEA/D) مع حقن مشغل البحث المحلي المقترح لحل مشكلة امثلية تعدد الاهداف يليه المصنف نيف بايز (NB) لغرض التصنيف والحكم على قدرة النماذج المقترحة للتمييز بين حركة المرور الطبيعية على الشبكة من الهجوم. اداء النماذج المقترحة تم تقييمه بالمقارنة مع نموذجين من النماذج الاساسية وهي (FVBRM) و NB. تضمن التجارب على البيانات القياسية (NSL-KDD) قدرة النماذج المقترحة المعتمدة على امثلية تعدد الاهداف على اختيار امثل مجموعة فرعية من الميزات التي لديها اعلى طاقة تمييزية لتمييز الهجوم من الطبيعي بالمقارنة مع النماذج الاساسية. وعلاوة على ذلك، ان مشغل البحث المحلي المقترح يضمن قدرته على الاستفادة من اداء نموذج امثلية تعدد الاهداف الذي حقق تقليل واضح للميزات بمعدل من 16.83 الى 8.54 ميزة (اي مايقارب %50) بالأضافة الى زيادة دقة مصنف نيف بايز (NB) من 98.829 الى 98.859 ومعدل الكشف من 98.906 الى 99.043.


Article
Multi-Objective GA-Based Optimization to Maximize Sustainability for Product Design and Manufacturing

Authors: Halla Atiyab --- Luma Adnan Al-Kindia
Journal: Anbar Journal of Engineering Sciences مجلة الأنبار للعلوم الهندسية ISSN: 19979428 Year: 2018 Volume: 7 Issue: 3 Pages: 195-201
Publisher: University of Anbar جامعة الانبار

Loading...
Loading...
Abstract

Responding quickly and economically to the diversification of customer needs has forced manufacturing companies adopting approaches to delivering low cost, high quality sustainable products based on finding a link between the design or the manufacturing processes and other key elements of sustainability; economic, environmental, and social. However, these approaches had limited success. The most likely reason for the lack of integration between the design and manufacturing stages of the product and complexity of addressing the above mentioned three key elements of sustainability due to existing of many variables in relation to design, manufacturing, locations, logistic operations and so on. Taking into account the required integration as well as the associated complexity of considering sustainability elements can lead to large space alternative solutions and it is more difficult to use only exact methods to the optimization of such problem. This paper presents a genetic algorithm (GA) approach aiming to optimize a high sustainability performance by designing a product and the corresponding manufacturing processes for that product. Process optimization is carried out in terms of the highest fitness function achieved where different objectives are to be optimized simultaneously. The proposed GA approach is applied to the industrial case example. The proposed approach can assist decision makers to help explain when justifying their decision on what are the best product design and its manufacturing processes to obtain high sustainability performance.


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
Genetic Algorithm Based Load Flow Solution Problem in Electrical Power Systems

Authors: Samir Sami Mahmood --- Hassan A. Kubba
Journal: Journal of Engineering مجلة الهندسة ISSN: 17264073 25203339 Year: 2009 Volume: 15 Issue: 4 Pages: 4142-4162
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

In this paper, a proposed method based on real-coded genetic algorithm is presented and applied to solve multiple load flow solution problem. Genetic algorithm is a kind of stochastic search algorithm based on the mechanics of natural selection and natural genetics. They combine the concepts of survival of the fittest with genetic operators such as selection, crossover and mutation abstracted from nature to form a surprisingly robust mechanism that has been successfully applied to solve a variety of search and optimization problems. Elitist method is also used in this research, and blending models are implemented for crossover operator. In the proposed work, five busbars typical test system and 362-bus Iraqi National Grid are used to demonstrate the efficiency and performance of the proposed method. The results show that, genetic algorithm is on-line load flow solution problem for small-scale power systems, but for large-scale power systems, it is recommended that the load flow solution using genetic algorithm is for planning studies. The main important feature of the purposed method is to give high accurate solution with respect to the conventional methods.

في هذه البحث، تقدم طريقة مقترحة مبنية على اساس خوارزمية جينية مشفرة بالاعداد الحقيقية لحل مسألة سريان الحمل متعددة الحلول. تعتبر الخوارزمية الجينية احدى طرق البحث العشوائية القائمة على تقنيات الانتخاب (الانتقاء) الطبيعي و الجينات الطبيعية. تجمع الخوارزمية الجينية مبادئ (بقاء الاصلح) مع عوامل جينية كالانتخاب (الانتقاء)، العبور و التغيار الاحيائي (الطفرة) المستخلصة من الطبيعة لتكوين تقنية متينة استخدمت بنجاح في حل مختلف مسائل البحث و ايجاد القيم المثلى. تم في هذا البحث استخدام طريقة انتخاب الامثل بالاضافة الى استخدام نماذج الخلط في عملية العبور. لتبيان كفاءة و مدى فعالية الخوارزمية الجينية في حل مسائل سريان الحمل متعددة الحلول، تم تطبيق الطريقة المقترحة على منظومة قدرة كهربائية قياسية. تبين النتائج كون الطريقة المقترحة ملائمة للحل اللحظي لمسائل سريان الحمل و بالتالي التطبيق العملي اثناء التشغيل لمنظومات القدرة صغيرة الحجم. أما بالنسبة لمنظومات القدرة كبيرة الحجم، فيوصي الباحث باستخدام الطريقة المقترحة لاغراض التصميم و التخطيط. اهم خواص الطريقة المقترحة هي الحصول على نتائج و حلول لمسألة سريان الحمل بقيم عالية الدقة.


Article
On Multi-Objective Geometric Programming Problems with a Negative Degree of Difficulty
البرمجة الهندسية متعددة الأهداف مع درجة الصعوبة السالبة

Authors: ¬Abbas Y. Al-Bayati --- Huda E. Khalid
Journal: IRAOI JOURNAL OF STATISTICAL SCIENCES المجلة العراقية للعلوم الاحصائية ISSN: 1680855X Year: 2012 Volume: 12 Issue: 21 Pages: 1-14
Publisher: Mosul University جامعة الموصل

Loading...
Loading...
Abstract

تعد درجة الصعوبة مبدأ مهماً في نظرية البرمجة الهندسية الكلاسيكية. والمسألة المقابلة غالبا ما تكون غير مقبولة عند درجة الصعوبة السالبة وبما أن البحوث المنشورة في هذا المجال قليلة جدا.فان هذا البحث سيقدم الأفكار والمبادئ الأساسية للبرمجة الهندسية متعددة أهداف؛ فقد تم تطوير إجراء عددي لحل مسألة البرمجة الهندسية متعددة الأهداف ذات درجة الصعوبة السالبة مستخدمين طريقة الأوزان للحصول على حل بمستوى مقبول واستخدام تقنية المبسطة للتأكد من معقولية المسألة المقابلة؛ وذلك بإضافة حد ثابت لدالة الهدف الأساسية.

Degree of difficulty is an important concept in the classical Geometric Programming (GP) theory. The dual problem is often infeasible when the degree of difficulty is negative and very little subjects have been published on this topic. This paper presents the basic concepts and principles of multiple-objective geometric programming model, and developed a numerical procedure to solve multi-objective Geometric Programming Problems (GPP) having a negative degree of difficulty using weighted method to obtain the non-inferior solution and using Brickers simple technique to ensure the dual feasibility; namely the addition of a constant term to the primal objective function

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

Resource type

article (23)


Language

English (19)

Arabic and English (3)

Arabic (1)


Year
From To Submit

2018 (9)

2017 (1)

2016 (4)

2015 (2)

2014 (1)

More...