Physiological Reactions Profiling in Polygraph Testing: Insights from Fuzzy C-Means Clustering Analysis

Abstract

The polygraph test, which is frequently employed for deception detection and truth verification, evaluates the accuracy of people's assertions by analyzing their physiological reactions. This study investigates the variety of physiological responses detected during polygraph tests using fuzzy C-means clustering analysis. 400 individuals undergoing polygraph testing provided a dataset containing physiological parameters, such as assessments of autonomic arousal, cardiovascular activity, respiration patterns, and electrodermal responses. Participants' varied patterns of physiological reaction were revealed using fuzzy clustering, which distinguished different physiological groupings among them. Cluster analysis revealed the physiological profiles linked to various levels of deception. Performance metrics, including cluster silhouette coefficient and within-cluster heterogeneity, were utilized to validate the clustering results. The findings provide valuable implications for improving the accuracy and reliability of polygraph testing, with potential applications in forensic investigations, law enforcement, and security screenings. This study contributes to the advancement of polygraph test interpretation techniques and underscores the importance of considering individual differences in physiological responses during deception detection.