A neurophysiological training evaluation metric for air traffic management

Area of Science:

• Neuroscience
• Human Factors Engineering
• Cognitive Science

Background:

• Air Traffic Controllers (ATCos) require extensive training to manage complex Air Traffic Management (ATM) tasks.
• Objective metrics are needed to evaluate training effectiveness and cognitive load during skill acquisition.
• Neuroelectrical signals offer a promising avenue for assessing cognitive states during demanding tasks.

Purpose of the Study:

• To investigate the application of neuroelectrical cognitive metrics for evaluating subject training levels in an ATM task.
• To correlate neuroelectrical data with subjective task difficulty assessments.
• To identify specific neuroelectrical patterns indicative of training improvement.

Main Methods:

• Collected Electroencephalogram (EEG), Electrocardiogram (ECG), and Electrooculogram (EOG) signals from students performing an ATM task at varying difficulty levels.
• Analyzed neuroelectrical data, including Power Spectral Density (PSD) of EEG, Heart Rate (HR), and Eye-Blink Rate (EBR).
• Compared neuroelectrical findings with subjective difficulty ratings from NASA-TLX questionnaires.

Main Results:

• Integration of EEG-PSD, HR, and EBR provided quantitative insights into subject training levels.
• Specific correlations were observed between frontal theta PSD and HR with mental/emotive engagement.
• Parietal alpha PSD and EBR showed correlations with engagement, indicating training progress.

Conclusions:

• Neuroelectrical metrics, specifically EEG-PSD, HR, and EBR, can effectively evaluate training levels in ATM task learning.
• Analysis of frontal theta and parietal alpha bands, alongside HR and EBR, offers valuable data on cognitive and emotional engagement.
• These findings suggest a potential for objective, real-time assessment of training improvement in high-demand professions like air traffic control.