Workers Gaze dynamics in precision machining work process

Data Description Participants and Skill Levels The dataset includes performance data from three operators with distinct skill levels: jss (Level 1) – Less than 1 year of experience lhj (Level 2) – Approximately 2 years of experience smc (Level 3) – More than 10 years of experience Task Description All operators performed a standardized precision machining task involving handwork processes. The task was conducted under controlled conditions to minimize external variables and ensure consistency across trials. Data Collection Method Data was collected using Tobii Glasses 3 (eye-tracking device). The device provided detailed gaze and head movement data, which were used to assess visual attention, focus, and cognitive workload during the task. Data was preprocessed to remove noise and irrelevant artifacts, ensuring high-quality input for analysis. Notable Findings ✅ Performance Differences by Skill Level More experienced operators (smc) demonstrated higher accuracy, better consistency, and shorter completion times compared to less experienced operators. Novice operators (jss) showed more variability in gaze patterns and hand movements, suggesting higher cognitive load and less automation in task execution. ✅ Visual Attention Patterns Expert operators (smc) displayed more focused and predictable gaze patterns, indicating better situational awareness and motor control. Novice operators exhibited more scattered gaze patterns, reflecting increased difficulty in maintaining focus and task execution efficiency. ✅ Learning Curve and Task Adaptation How to Interpret and Use the Data This dataset can be used to develop predictive models for operator performance based on eye-tracking and task execution patterns. The data provides insights into how skill acquisition influences task efficiency, which can be applied to training program design and workflow optimization. Comparative analysis of gaze patterns and hand movement consistency can help identify key behavioral markers of expertise in precision machining. The findings can also support ergonomic improvements and process standardization to reduce errors and improve operator performance.