INVITED SPEAKER

Dr. Fadel M. Megahed is a Miami University Faculty Scholar and the Endres Associate Professor of Information Systems & Analytics. He received his Ph.D. and M.S. in Industrial and Systems Engineering from Virginia Tech and a B.S. in Mechanical Engineering from the American University in Cairo.

Dr. Megahed is the Editor of the Case Study Section for the Journal of Quality Technology. He has received numerous research and teaching awards. He was named a Miami University Faculty Scholar in 2023. He is currently the Endres Associate Professor (2022-2025) and an FSB Research Fellow (2023-2025).  He also received the Student Recognition of Teaching Excellence Award (Fall 2020) and 27 faculty commendations for impacting students' learning and development (2018-2023). Before joining Miami University, he received the Career Development Award from the NIOSH Deep South Center for Occupational Health and Safety (2013), and the Mary G. and Joseph Natrella Scholarship from the Quality and Productivity Section of the American Statistical Association (2012).

Up to now, he has 52 peer-reviewed journal papers, 3 invited editorials, and 12 conference proceedings. His research findings and views have been covered in over 50 media articles. 

He is also the PhD Advisor for 8 PhD recipients (all from Auburn University).

Title: AI and the Future of Work in Statistical Quality Control: Insights from a First Attempt to Augmenting ChatGPT with an SQC Knowledge Base (ChatSQC)

Abstract: 

We introduce ChatSQC, an innovative chatbot system that combines the power of OpenAI's Large Language Models (LLM) with an extensive knowledge base in Statistical Quality Control (SQC). Our research focuses on enhancing LLMs using specific SQC references, shedding light on how data preprocessing parameters and LLM selection impact the quality of generated responses. By illustrating this process, we hope to motivate wider community engagement to refine LLM design and output appraisal techniques. We also highlight potential research opportunities within the SQC domain that can be facilitated by leveraging ChatSQC, thereby broadening the application spectrum of SQC. A primary goal of our work is to equip practitioners with a tool capable of generating precise SQC-related responses, thereby democratizing access to advanced SQC knowledge. To continuously improve ChatSQC, we introduce a crowdsourcing approach to accumulate further SQC references, thereby enhancing the contextual understanding of the chatbot. A dedicated web platform has been created for the SQC community to contribute, and we commit to vetting these contributions and updating ChatSQC on a quarterly basis. Overall, ChatSQC serves as a testament to the transformative potential of AI within SQC, and we hope it will spur further advancements in the integration of AI in this field.