The master’s thesis of the student (Najat Muslim Ramadan) with a major in (Computer Engineering) was discussed on Thursday 6/10/2022 at the discussion room (Hall No. 9) in the Department of Control and Systems Engineering. The thesis title is “Design of power and Rate Control Strategy in wireless Sensor Network Using Event-Based PlD Controller”. The discussion committee consisted of:

1-Prof. Dr. Moayad Sadeq Krook / Chairman Asst.

2-Prof. Dr. Ikhlas Kadhum Hamza / Member

3-Asst. Prof. Dr. Mustafa Ismail Salman / Member

4-Prof. Dr. Safana Mudher Raafat / Member and Supervisor Asst.

5-Prof. Dr. Ali Majeed Mahmoud / Member and Supervisor

Power consumption is a common problem in wireless sensor networks that many researchers are working on. It represents one of the most serious challenges in wireless sensor networks, as reducing node power consumption can extend the life of the network to a longer time even in the presence of external disturbances. The goal is to reduce power consumption while maintaining the required data throughput in wireless sensor networks. In this thesis, the event-based proportional integral derivative (PID) controller is designed to reduce the power consumption of a wireless sensor network system. Two types of binding are adopted for the event-based PID controller design. The first type is based on the event-based PID controller implementation of a state feedback-controlled system. As for the second type, the PID controlled system has been applied. Initially, the parameters of all controllers were determined by a trial and error approach. Then, in order to improve the performance of the controlled system, the Gray Wolf Optimization (GWO) algorithm was applied to improve the selected control parameters depending on the appropriate performance function. The discussion was attended by the Assistant Head of the Department for Scientific Affairs and Graduate Studies in the department (Prof. Dr. Muhammad Youssef Hassan). On this occasion, we congratulate the student (Najat Muslim Ramadan) and wish her continued success.

The master's thesis of the student (Taha Shaker Mahmoud) with a major in (Mechatronics Engineering) was discussed on Tuesday 11/10/2022 at the discussion room (Hall No. 9) in the Department of Control and Systems Engineering. The thesis title is “An Intelligent Controller Design Based on Feedback linearization Using NARMA-L2 for Nonlinear Systems”

The discussion committee consisted of:

1-Prof. Dr. Ahmed Ibrahim Abdel Karim / Chairman Asst.

2-Prof. Dr. Wajdi Sadiq Abboud / Member Asst.

3-Prof. Dr. Bushra Kadhum Aliwi / Member

4-Prof. Dr. Omar Farouq Lutfy / Member and Supervisor

Feedback linearization provides applicable design tools for a wide variety of nonlinear systems. This thesis presents an intelligent feedback controller based on the feedback linearization approach to control nonlinear systems. In particular, the nonlinear autoregressive moving average (NARMA-L2) network is trained to reproduce the forward dynamics of the controlled system. Thus, the trained NARMA-L2 network can be immediately integrated into the inverse feedback control (IFC) structure. In order to improve the ability of the NARMA-L2 architecture to approximate nonlinear systems, the NARMA-L2 controller consists of two wavelet neural networks (WNNs). In addition, the RASP1 function was used as the wavelet mother function in the WNN architecture, where this function led to the best control accuracy compared to the more commonly used Mexican Hat, Gaussian, and Morlet functions. To avoid the limitations of the gradient descent (GD) methods, the artificial gorilla force optimization (GTO) algorithm is used to determine the optimal settings for the NARMA-L2 inverse control parameters. In particular, several evaluation tests are used to evaluate the efficacy of WNN-based NARMA-L2 in control accuracy and robustness against external disturbances in each system under study. These tests clearly demonstrated the effectiveness of the control system. Finally, a comparative study showed that the WNN-based NARMA-L2 controller achieved better control results compared to the Multilayer Perceptron (MLP), the NARMA-L2-based RBF, and the PID Controller. The discussion was attended by the Assistant Head of the Department for Administrative Affairs (Prof. Dr. Hazem Ibrahim Ali) and the Assistant Head of the Department for Scientific Affairs and Postgraduate Studies (Prof. Dr. Muhammad Youssef Hassan). On this occasion, we congratulate the student (Taha Shaker Mahmoud) and wish him continued success. 

The master’s thesis for the student (Mustafa Yassin Diab) was discussed with a major in (Computer Engineering) on Wednesday 10/12/2022 at the discussion room (Hall No. 9) in the Department of Control and Systems Engineering. The thesis is entitled “Cyber-Physical System for Dams Monitoring and Control”

The discussion committee consisted of:

1-Prof. Dr. Muhammad Ali Tawfiq / Chairman Asst.

2-Prof. Dr. Ayman Daoud Salman / Member Asst.

3-Prof. Dr. Ahmed Alaa Okla / Member Prof. Dr.

4-Moayad Sadiq Crook / Member and Supervisor

The water management system is nowadays an issue of increasing importance. In this thesis, a safe automated monitoring and control system for dams based on electronic physical systems (CPSs), which is a modern core technology in a complex and heterogeneous cyber world, is proposed. This system consists of three main parts: The physical WSN node, which is the physical world; Communication technologies such as communication protocols; Web-based servers like the world of the Internet. The first part consists of four nodes (NodeMCU8266) as a microcontroller distributed over the dam areas, a Raspberry pi4 as a central server, sensors of water level, temperature and air humidity, sensor of rain and temperature of the dam's water, and three actuators, representing the three gates of the dam. It has become vulnerable to many cyber-attacks. To secure the proposed system, two cyber security algorithms are proposed to detect and prevent cyber attacks. The first one is applied to a physical wireless sensor network (WSN) that adopts telemetry transfer protocol in message queue. The second addresses cyber-attacks on the cloud server side. These algorithms predict DoS attacks on nodes or DoS-HTTP flood attacks on the cloud. Dams are monitored and managed and threats are identified via the dashboard. The proposed system and algorithms were tested by nine case studies. The experimental results showed a high performance of the proposed methods to monitor and manage the dam as well as a high effectiveness of securing the CPS system by detecting and preventing cyber-attacks affecting WSN and cloud servers. The discussion was attended by the Assistant Head of the Department for Administrative Affairs (Prof. Dr. Hazem Ibrahim Ali) and the Assistant Head of the Department for Scientific Affairs and Graduate Studies (Prof. Dr. Muhammad Youssef Hassan). On this occasion, we congratulate the student (Mustafa Yassin Diab) for obtaining the master's degree and we wish him continued success.

The master's thesis for the student (Dina Mahdi Abdul-Hussein) was discussed with a major in (Computer Engineering) on Tuesday 4/10/2022 at the discussion room (Hall No. 9). The thesis title is “Object Features and Behavior Analysis using Deep Learning” This discussion committee consisted of:

1- Prof. Dr. Ashwaq Talib Hashem / Chairman

2- Asst. Prof. Dr. Intisar Abdul Majeed Al-Sayed / Member

3- Asst. Prof. Dr. Ahmed Raouf Nasser / Member

4- Asst. Prof. Dr. Laith Jassim Saud / Member and Supervisor

The exponential increase in the use of image processing and artificial intelligence in a very large number of applications in many fields makes it a stimulating field for education, business and research. Object detection and analysis is needed in most of these applications. This work is specifically concerned with the human face as an object. For years and still, different face detection methods with different approaches have been competing for better efficiency. Feature-based and image-based methods are the two main methods among these methods. In this work: A relatively extensive review of the methods used in face detection has been undertaken with an overview of their capabilities and limitations. • Two important face detection and analysis methods, one that uses Viola Jones' idea and belongs to the feature-based approach and the other is deep learning on CNN and belongs to the image-based approach, are implemented and analyzed, considering their structure, method of training and work, factors affecting their work, capabilities, limitations, and suitability for detection and analysis. • Ensures working with training as well as testing algorithms Working with algorithms included training as well as testing. The work is carried out on computing platforms (personal computers) with different capabilities, and as a programming environment, PyCharm is used as an integrated development environment with Python as a programming language as well as various libraries that support the construction of algorithms and support the best use of practical computing units. The data sets used in training or tests are taken from internet sources. When choosing the method to use for an application, it is important to consider, among many things, the purposes of the application in terms of accuracy, time, resources, and ability to use the GPU. The door is still open to effective new methods, as well as improving the efficiency of already existing methods. On this occasion, we congratulate the student (Dina Mahdi Abdul-Hussein) and wish her continued success.