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

Yisi, Liu; Trapsilawati, Fitri; Xiyuan, Hou; Olga, Sourina; Chen, Chun-Hsien; Pushparaj, Kiranraj; Wolfgang, Mueller-Wittig; Tech, Ang Wei · 2017 · Advances in transdisciplinary engineering

DOI: 10.3233/978-1-61499-779-5-357

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of evaluating human factors in future Air Traffic Control (ATC) systems, specifically focusing on the mental workload of Air Traffic Controllers (ATCOs). As air traffic density increases, automation aids such as Conflict Resolution Aids (CRA) and advanced display interfaces are being developed to mitigate safety risks. However, traditional evaluation methods, such as post-task questionnaires like the NASA Task Load Index (TLX), provide only retrospective, overall ratings and lack the temporal resolution required for time-critical tasks. To overcome this limitation, the authors propose an Electroencephalogram (EEG)-based neurocognitive tool capable of monitoring brain states and mental workload in real-time with high temporal resolution. The researchers conducted an experiment involving 36 participants, including controllers and students with ATC knowledge, who were divided into three groups based on display modes: Non-Display, Vertical Display, and Trajectory Prediction. Each group performed ATC tasks under three CRA conditions: Manual, Reliable, and Unreliable. EEG data were collected using a wireless Emotiv EPOC headset with 14 channels. A subject-dependent Support Vector Machine (SVM) classifier, trained on fractal dimension and statistical features extracted from calibration stimuli (Stroop Colour-Word Test), was used to recognize workload levels in real-time. Subjective workload was also measured via NASA-TLX and a 1–9 rating scale after each one-hour session. The results demonstrated a high correlation between EEG-based workload labels and NASA-TLX ratings, validating the reliability of the EEG system. Analysis of continuous workload data revealed that workload was significantly higher at the beginning of sessions and peaked in the middle, likely due to aircraft ramp-up and subsequent familiarity. The Trajectory Prediction group exhibited significantly higher workload compared to the other display groups, attributed to information overload and the complexity of interpreting the interface. In contrast, the type of CRA setting (Manual, Reliable, or Unreliable) had minimal effect on physiological workload, showing no significant differences across conditions. This finding contradicts some previous objective measures but aligns with subjective workload assessments. The study concludes that EEG-based monitoring provides a robust method for understanding real-time mental workload dynamics in ATC environments. The findings suggest that while CRA reliability does not significantly impact physiological workload, the Trajectory Prediction display increases cognitive load and requires redesign or extended training to reduce information overload. This approach enables more precise human factors evaluation for current and future ATC systems, facilitating the refinement of automation aids to better support controller performance.

Key finding

EEG-based mental workload recognition is highly correlated with subjective ratings and reveals that trajectory prediction displays impose significantly higher workload on air traffic controllers than other display modes, while conflict resolution aid reliability has minimal effect on physiological workload.

Methodology

lab_experiment

Sample size: 36

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via author_sweep_intake on 2026-05-28.

StageOutcomeToolModelPromptAttemptsCompleted
discover success author_sweep 2 2026-05-28
archive success canonical_url 5 2026-06-06
extract success cached 3 2026-06-10
clean success clean 1 2026-06-04
chunk success chunk 1 2026-06-04
embed success embed Qwen/Qwen3-Embedding-8B 1 2026-06-04
enrich success 1 2026-05-28
promote success 1 2026-06-04
summarize success llm qwen3.6-27b-prismaquant summ-v5 2 2026-06-10
tag success vector_similarity 15 2026-06-11
verify success 2 2026-06-10

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).