Ahmed Métwalli

Ahmed Métwalli is an Assistant Lecturer and PhD candidate at the Arab Academy for Science, Technology, and Maritime Transport (AASTMT) in Egypt, affiliated with the College of Artificial Intelligence. He also serves as a Graduate Teaching Assistant, instructing in advanced areas of Machine Learning, Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs), while maintaining a parallel role in industry as CTO at Accountants on Air.

Métwalli's contributions to polygraph science focus on applying machine learning and artificial intelligence to enhance deception detection accuracy. His 2025 study developed a new multimodal dataset with physiological data (heart rate, galvanic skin response, and body temperature), in addition to demographic data, collected from 49 unique subjects. The research demonstrated that Random Forest achieved an accuracy of 97%, outperforming Logistic Regression (58%), Support Vector Machine (58%), and k-Nearest Neighbor (83%) in polygraph-based deception detection using multimodal sensor fusion. The team also created and published the Polygraph-Based Truth Detection System Dataset on Mendeley Data in 2025, contributing valuable resources to the field.

Beyond polygraph research, Métwalli has 17+ publications spanning multidisciplinary AI applications in fields like agriculture, textiles, embedded systems, IoT, and RF/optical communication. His broader research program focuses on applying machine learning techniques to complex signal processing and pattern recognition problems across various domains, with his polygraph work representing an extension of these computational methods to psychophysiological detection.