Self-Supervised Evolutionary Learning of Neurodynamic Progression and Identity Manifolds from EEG During Safety-Critical Decision Making

2026-03-07

AI Summary

This work addresses the challenge that existing EEG-based human-vehicle interaction methods struggle to simultaneously enable user authentication and continuous modeling of cognitive states, while lacking effective capture of individual-specific neural dynamic trajectories. To overcome this, we propose a self-supervised evolutionary learning framework that, for the first time, integrates population-based evolutionary algorithms into the non-differentiable space of EEG segment partitioning, enabling label-free discovery of individualized neural dynamic stage progressions and identity manifolds. By jointly optimizing temporal predictability, segment boundary contrast, cross-trial alignment, and sparsity of feature weights, our method significantly enhances segment boundary clarity and cross-trial generalization in a simulated street-crossing decision-making task, yielding highly interpretable sparse neural features that effectively support precise user authentication and cognitive anomaly detection.

Technology Category

• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Evolutionary Computation

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Human-vehicle interaction in safety-critical traffic environments increasingly incorporates neural sensing to infer user intent and cognitive state, yet most existing approaches either treat electroencephalography (EEG) as a static biometric credential or train task-specific decoders that ignore long-term neurodynamic trajectories, lacking mechanisms for secure user identity and continual modeling of evolving cognitive states. This work proposes a self-supervised evolutionary learning (SSEL) framework that discovers individualized neurodynamic progressions and intrinsic identity manifolds directly from continuous EEG, without external labels or predefined cognitive stage models. SSEL jointly optimizes within-stage temporal predictability, boundary contrast, cross-trial alignment, and sparse stage-specific feature weights, while a population-based evolutionary search enables direct optimization in the discrete, non-differentiable space of candidate segmentations. We validate the framework on EEG recorded from participants performing a simulated road-crossing decision task, a canonical safety-critical scenario in which perceptual assessment, risk evaluation, and decision commitment unfold over time. The learned segmentations reveal stable, person-specific stage structures and neurodynamic signatures that support authentication and anomaly detection. Compared to inference-based segmentation baselines, SSEL achieves orders-of-magnitude higher boundary contrast, substantial gains in cross-trial generalization of intention boundaries, and more interpretable, sparse stage-wise feature attributions. Beyond performance, the framework advances a progression-aware perspective on cognitive neurodynamics, where security, resilience, and personalization emerge from the intrinsic temporal structure of brain activity, with implications for next-generation smart urban and transportation infrastructures.

Problem

• EEG
• neurodynamic progression
• user identity
• cognitive state modeling
• safety-critical decision making

Innovation

• Self-Supervised Evolutionary Learning
• Neurodynamic Progression
• Identity Manifolds
• EEG Segmentation
• Cognitive Stage Discovery