Safety in aviation is very important in today's air transportation systems. Human factors like fatigue, stress, and cognitive overload can have a big impact on how well pilots do their jobs. This study examines the amalgamation of machine learning methodologies with psychophysiological data to improve aviation safety and decision-making processes. The suggested system gathers physiological signals from pilots, like heart rate, brain activity, and eye movement, using sensors and monitoring devices that they wear. Machine learning algorithms process and analyse these signals to find patterns that are linked to stress, fatigue, and lower cognitive performance. The system guesses what might happen that could be dangerous and gives early warnings to help make flying safer. Experimental evaluation shows that the suggested method can find unusual pilot states and make safety monitoring better. The findings indicate that the integration of physiological monitoring with artificial intelligence establishes a dependable framework for enhancing aviation safety and mitigating incidents associated with human error.
Jiwani et al. (Wed,) studied this question.