26 January، 2025
PhD thesis by Samah Fakhry Aziz
Defense of the doctoral thesis in the College of Computer Science and Mathematics – Department of Computer Science
Entitled (Predicting small loads in a cloud based distributed system for issuing traffic violations)
In continuation of the scientific research movement and the follow-up and presence of the Dean of the College of Computer Science and Mathematics, Prof. Dr. Duha Bashir Abdullah
Discussed in the discussion hall of the College of Computer Science and Mathematics at the University of Mosul on 26- 1- 2025 , PhD thesis by Samah Fakhry Aziz and supervised by Prof. Dr. Manar Younis Ahmed
The thesis presented by the student dealt with the traffic violation registration system, the techniques associated with it that enhance its performance, and the implemented aspects used to enhance the performance of the network system, starting with data analysis, data preparation, spatial aggregation, predicting the expected number of violations in the future, and deploying edge computing. As well as the results and results that answer the question of the study.
The study touched on the use of machine learning and deep learning algorithms, which included long-term memory algorithm (LSTM), spatial aggregation algorithm (K-means) and edge computing deployment to achieve decentralization of service in order to reduce network traffic and improve system performance.
The study aims to improve the performance of recording traffic violations and balancing small loads using various aspects such as edge computing and spatial distribution of the service to avoid or reduce the latency of the network system. By analyzing the available data sets of traffic violation systems to create ideal spatial groups and build a time series representing the traffic violations newly recorded during the past three years in order to predict the number of violations for the coming years at the same work site, as well as designing a reliable network system that meets the requirements of the coming years and measuring the performance of the system designed during special scenarios based on the arrival time obtained.
The discussion committee was headed by Prof. Dr. Abbas Mohsen Abdel Hussein as Chairman
Prof. Dr. Shahba Ibrahim Khalil, Member
Assist. Prof. Roaa Boutros Boulos, Member
Assist. Prof. Mohamed Zaki Hassan Member
Assist. Prof. Aws Khazal Ali, Member
Prof. Dr. Manar Younis Ahmed, Member and Supervisor
