Cross-subject Brain Functional Connectivity Analysis for Multi-task Cognitive State Evaluation

TL;DR

The study addresses real-time cross-subject cognitive-state evaluation in aviation by leveraging EEG-based brain functional connectivity (FC) during multi-task flight scenarios in a VR platform. It constructs subject-, task-, and gender-aware FC embeddings using Pearson correlations across 20 EEG channels and labels cognitive states by integrating NASA-TLX, performance, and physiological cues, then evaluates multi-class states (low, high, transition). A novel Multi-head Attention EEGNet (MHA-EEGNet) is proposed for cross-subject, three-class classification, achieving up to $0.9583$ accuracy using eight left-hemisphere electrodes, outperforming baseline classifiers and full-channel inputs. The findings illuminate task- and gender-specific FC patterns, notably left-hemisphere engagement and delta-band prominence in negative correlations, and offer a practical path toward efficient, real-time cognitive monitoring for aviation safety, while acknowledging limitations such as task-wise treatment of negative correlations and a homogeneous subject pool.

Abstract

Cognition refers to the function of information perception and processing, which is the fundamental psychological essence of human beings. It is responsible for reasoning and decision-making, while its evaluation is significant for the aviation domain in mitigating potential safety risks. Existing studies tend to use varied methods for cognitive state evaluation yet have limitations in timeliness, generalisation, and interpretability. Accordingly, this study adopts brain functional connectivity with electroencephalography signals to capture associations in brain regions across multiple subjects for evaluating real-time cognitive states. Specifically, a virtual reality-based flight platform is constructed with multi-screen embedded. Three distinctive cognitive tasks are designed and each has three degrees of difficulty. Thirty subjects are acquired for analysis and evaluation. The results are interpreted through different perspectives, including inner-subject and cross-subject for task-wise and gender-wise underlying brain functional connectivity. Additionally, this study incorporates questionnaire-based, task performance-based, and physiological measure-based approaches to fairly label the trials. A multi-class cognitive state evaluation is further conducted with the active brain connections. Benchmarking results demonstrate that the identified brain regions have considerable influences in cognition, with a multi-class accuracy rate of 95.83% surpassing existing studies. The derived findings bring significance to understanding the dynamic relationships among human brain functional regions, cross-subject cognitive behaviours, and decision-making, which have promising practical application values.

Figures (14)

• Figure 1: $2017$-$2023$ aircraft accidental rates and corresponding occurrence stages (Adapted from ASN2023).
• Figure 2: Flight simulation platform and the multi-screen cognitive task interface.
• Figure 3: Cognitive task experiment setup.
• Figure 4: Utilised $20$-lead EEG electrode system.
• Figure 5: EEG signals and brain electrical activity maps before and after the pre-processing steps.