REAL TIME ATTENTION MONITORING IN MECHANICAL WORKSHOPS USING WEARABLE DEVICES

Abstract

Industry 4.0 is gathering momentum, and cognitive preparedness is required for human workers working in tandem with intelligent machines. Neurocognitive markers of attention and engagement in factory environments are investigated in this study through a multimodal biosensing framework. Observational techniques are not timely enough, and this research combines wearable EEG, HRV, and eye-tracking sensors to record cognitive states dynamically. Run with 20 subjects in a simulated innovative factory environment, the experiment simulated realistic tasks under long focus and stress-induced decision-making. Analysis of data confirmed that EEG frontal theta power and HRV measures were valid indicators of cognitive load, and eye-tracking measures were valid to detect attention patterns. Cross-modal analysis validated the complementarity of the tools for adaptive human-machine interface design. The work presents industrial applications like real-time workload monitoring, dynamic assignment of tasks, and adaptive responsiveness of the interfaces. Ethical issues of user permission and data privacy are brought into the limelight. Scaling with deployability and personalization by machine learning for human-driven automation is a direction for the future.