EEG-Based Mental Workload Recognition in Human Factors Evaluation of Future Air Traffic Control Systems

With growing air traffic density, air-traffic controllers (ATCOs) are facing more challenges in interpreting and analyzing air traffic information. As one of the solutions to this problem, automation supports such as tactile human computer interface, interactive 3D radar displays, and conflict resolution aid (CRA) are proposed for the enhancement of the current air traffic control (ATC) systems. To evaluate the proposed ATC systems, questionnaires are commonly used to get the feedback from ATCOs. However, the questionnaires are usually administered upon completion of each ATC simulation task thus provide only overall ratings towards the new ATC systems. In this paper, we propose and implement a novel Electroencephalogram (EEG)-based neurocognitive tools for evaluation of ATC systems. The nature of EEG-based technique is that the brain states can be monitored in a high resolution time, fitting the nature of time-critical ATC tasks. Thus, such EEG-based human factors study allows for real-time monitoring of ATCOs' mental workload during the task performance in ATC systems. We designed and conducted an experiment to evaluate the costs and benefits of the CRA and tactile user interface in future ATC systems. Thirty six participants participated in the experiment and were assigned into three groups of different display modes: Non-Display, Display, and Trajectory Prediction. In each group, three CRA conditions were given: Manual, Reliable and Unreliable. The EEG data were recorded during the tasks, and the traditional workload evaluation method NASA Task Load Index (TLX) was administered at the end of each task. The result shows that the ratings obtained from NASA TLX and from the EEG labeling are highly correlated. Thus, the EEG-based system is reliable to recognize workload during the task performance. With the proposed EEG-based system, we found that 1) relatively high workload was observed at the beginning of the experiment in each group which could be due to participants' unfamiliarity with the interfaces; 2) participants in the trajectory prediction group had much higher workload as compared to vertical display and non-display groups, which could be attributed to its complexity. The changes of workload are due to interaction between the type of display modes and time (p<0.05); 3) workload varied slightly with different CRA setting. The results show that the proposed EEG-based system for human factors study can provide better understanding of real-time mental workload changes during the task performance in new ATC systems, therefore enables the evaluation of current and future ATC systems.