OSAMA ELSARRAR

Passionate professor with broad experience in curriculum development, student mentoring, and interdisciplinary collaboration. Strengths lie in ability to foster engaging learning environments that inspire critical thinking and active participation. Proven track record of scholarly publications and thought leadership within the field. Significant contributions made to previous institutions through strategic program development and implementation.

• Provide academic teaching, supervision, administration, and other services.
• Teach advanced and high-level Math. courses for undergraduate students.
• Revamp and develop new curriculum for the major and minor Math. Programs.
• Plan for future growth of the Math. program and improvement of the Students' retention.
• Participate in decision making regarding academic improvements at the global level of the university.
• Provide instructions and guidelines for introductory teachings in the university.
• Act as a member of the online programming committee and contributes to the quality of the online teachings.
• Provide student advising and plan the teaching schedules and graduation fulfillment.
• Conduct research on system dependability and contribute to the software technology innovations.
• Supervise students' graduation projects and guide their research and accomplishments.
• Work with accreditation organizations to prepare the Math. program for accreditation.
• Taught introductory courses for early undergraduate students.
• Participated in departmental meetings and decisions.

My research develops and tests a new method of embedding pre-knowledge into the Dynamic Cell Structure (DCS) neural network. The DCS is a type of self-organizing map neural network that has been used for many purposes, including classification. The method used for embedding pre-knowledge into the neural network is to start by converting the knowledge to a set of IF/THEN rules, that can be easily understood and/or validated by a human expert. Once the rules are constructed and validated, then they are converted to a beginning neural network structure. This allows pre-knowledge to be embedded before training the neural network. This conversion and embedding process is called Rule Insertion. In order to determine whether this process improves performance, the neural network was trained with and without preknowledge embedded. After the training, the neural network structure was again converted to rules, Rule Extraction, and then the neural network accuracy and the rule accuracy were computed. Also, the agreement between the neural network and the extracted rules was computed. The findings of this research show that using Rule Insertion to embed preknowledge into a DCS neural network can increase the accuracy of the neural network. An expert can create the rules to be embedded and can also examine and validate the rules extracted to give more confidence in what the neural network has learned during training. The 2 extracted rules are also a refinement of the inserted rules, meaning the neural network was able to improve upon the expert knowledge based on the data presented.

• Numerical Analysis
• Machine Learning and Neural Networks
• Data Analysis
• Applied Mathematics
• Linear Algebra

• Ph.D. Dissertation: "Rule Extraction and Insertion to Improve the performance of a Dynamic Cell Structure Neural Network", 05/2019
• Master's Thesis: "Eigenvalue Problems in Linear Algebra Stability Under Linear Perturbations and Bound for Eigenvalues of Matrix Polynomials", 05/2018
• Analysis of Forest Fire Data Using Neural Network Rule Extraction with Human Understandable Rules. Published in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), 2019
• Rule Insertion Technique for a Dynamic Cell Structure Neural Network to Improve Performance Published in 2020 Computer Science, World Academy of Science, Engineering and Technology, International Journal of Computer and Information Engineering, 2020
• Improving Performance by Embedding Expert Knowledge in a Self-Organizing Map Neural Network

• Dr. Marjorie Darrah, Department of Mathematics, West Virginia University, Morgantown, WV 26506-6310, Marjorie.darrah@mail.wvu.edu
• Dr. Adam Halasz, Department of Mathematics, West Virginia University, Morgantown, WV 26506-6310, halasz@math.wvu.edu
• Prof. Hany H. Ammar, Department of Computer Sc. and Electrical Engineering, West Virginia University, Morgantown, WV 26506-6310, hammar@wvu.edu