A novel approach for cross-subject unfavorable driving state detection by cooperation between phase-based functional connectivity and convolutional neural network

Abstract

Driving under unfavorable driving state (UDS) is the primary factor inducing the soaring incidence of road accidents. Recently, Electroencephalography (EEG) with high time resolution is regarded as the “gold standard” for identifying drivers' UDS because it directly reflects the neural activity of human brain. However, EEG recordings are heavily influenced by individuals, resulting in poor generality and fair recognition performance on unseen subject. To handle the issue, an EEG-based cross-subject UDS detection framework is proposed, which combines model-driven and data-driven approaches. Concretely, EEG recordings collected from the driving simulation are first decomposed into six classical frequency bands. Interactive relation of all EEG channels is estimated by the phase transfer entropy (PTE). Subsequently, a novel meta-heuristic algorithm called equilibrium optimizer (EO) is employed as a PTE-based functional connectivity feature selection method. A customized 14-layer CNN model is further developed to extract hidden feature from PTE-EO-based functional connectivity and to perform UDS and NUDS classification tasks. Statistical analysis demonstrates that equilibrium optimizer significantly outperforms binary dragonfly algorithm (BDA) and whale optimization algorithm (WOA) in terms of UDS detection. The best recognition outcome is achieved using PTE-EO-CNN model, yielding a mean ACC of 90.19 %, a mean PRE of 89.20 %, a mean SEN of 91.75 %, and a mean SPE of 88.63 % on 16 subjects using LOSO-CV strategy. Conclusively, our findings suggest that PTE-EO-CNN is a promising framework with excellence reliability and generalizability, which has a new perspective and practical significance to solve the road safety issue.