The master thesis of the graduate Sarah Iyad Rabi, a candidate for a master’s degree, was defended on Sunday morning on February 23, 2025, at Al-Khwarizmi Central Hall and Professor Dr. Ali Hussein Murri, college of AL-Khwarizmi, Mechatronics Engineering department, at Baghdad University, was chaired the thesis committee that consisted of professor Dr. Qusay Salim Tawfiq, Technology university, Communication engineering department, Dr. Ahmed Rahman Jasim, Baghdad university, Mechatronics engineering department and supervised by Professor Dr. Yarub Omer Naji, Al-Khwarizmi college at Baghdad university. After the candidate had finished the defense, the chair of the committee announced the degree of) pass with merit (, awarded to the candidate for her research findings which are summarized:
This thesis discusses the development of a multi-camera surveillance system for real-time violence prediction using deep learning techniques. The system is based on the integration of convolutional neural networks (CNN) and recurrent neural networks (RNN) with support vector machines (SVM), in addition to using gamma correction to improve frame quality. The model was tested on two datasets: hockey matches and real-world violence situations, where the CNN-SVM hybrid model achieved 99% accuracy on the real-world violence set, and the RNN-SVM model achieved 96% accuracy on the hockey set. The results confirm the importance of integrating temporal and spatial information in violence prediction, and demonstrate the effectiveness of the system in modern security applications.
