Classification of Faults in Power Transmission Lines Using Artificial Neural Networks

This paper shows a new approach to determine the presence of defects and to classify the defect type online based on Artificial Neural Networks (ANNs) in electrical power system transmission lines. This algorithm uses current and voltage signals sampled at 1 KHz as an input for the proposed ANNs without the involvement of a moving data window, so input data will be processed as a string of data. The model depends on three neural networks one for each phase and another fourth neural network for the involvement of the ground during the fault. Response time of the classifier is less than 5 ms. Moreover modern power system requires a fast, robust and accurate technique for online processing. Simulation studies show that the proposed technique is able to distinguish the fault type very accurate. Also this technique succeeded in determining of all defect types under all system conditions, so it is 100 percent accurate, so it is suitable for online application.

Pattern Analysis and detection in images using neural networks

A new face detection system is presented. The system combines several techniques for face detection to achieve better detection rates, a skin colormodel based on RGB color space is built and used to detect skin regions. The detected skin regions are the face candidate regions. Neural network is used and trained with training set of faces and non-faces that projected into subspace by principal component analysis technique. we have added two modifications for the classical use of neural networks in face detection. First, the neural network tests only the face candidate regions for faces, so the search space is reduced. Second, the window size used by the neural network in scanning the input image is adaptive and depends on the size of the face candidate region. This enables the face detection system to detect faces with any size.

استخدام الشبكات العصبونية للتنبؤ في الأسواق المالية تطبيق لتوقّع تغيّرات قيم الأسهم في سوق دمشق للأوراق المالية

This thesis focused on composing two models built by using Neural Networks techniques for increasing the accuracy of predicting result represented by stock value in stock market, where the proposed solution includes two modalities of processing: in first one, we build two neural networks which we want to compose, one of the two networks deals with previous stock’s prices and the other one with indecators of technical analysis, then we will compose the outputs of these two networks into third neural network which represents the second modality of processing.

Anti-Money Laundering using Data Mining techniques

This research presents literature review on using Artificial intelligence and Data Mining techniques in Anti Money Laundering systems. We compare many methodologies used in different research papers with the purpose of shedding some light on real life applications using Artificial intelligence

رفع دقة صورة باستخدام شبكة عصبونية خُصُومية

مهمة إنشاء صورة عالية الدقة من نظيرتها منخفضة الدقة تُدعى SR (Super-Resolution). تلقت الـ SR اهتماماً كبير ضمن مجتمع الباحثين في مجال الرؤية الحاسوبية، كما أنً لها مجال واسع من التطبيقات[1, 2, 3]، كتحسين دقة الفيديوهات القديمة، تحسين فيديوهات المراقبة حيث تكون دقة هذه الفيديوهات منخفضة بسبب أحجامها الكبيرة، كما أن لها أهمية كبيرة في مجال التشخيص الطبي حيث أن دقة الكميرات التي تدخل جسم الإنسان منخفضة و يتعثر على الأطباء في كثير من الحالات التشخيص بسبب انخفاض جودة الصور و لها تطبيقات عديدة أيضاً في مجال الصور القادمة من الأقمار الصناعية فهذه الصور كذلك تكون ذات دقة منخفضة في أغلب الأحيان.