Passenger overall comfort in high-speed railway environments based on EEG: Assessment and degradation mechanism. (15th February 2022)

• Record Type: Journal Article
• Authors: Peng, Yong; Lin, Yating; Fan, Chaojie; Xu, Qian; Xu, Diya; Yi, Shengen; Zhang, Honghao; Wang, Kui
• Is Part Of: Building and environment. Volume 210(2022)
• Publication Date: 2022-02-15
• Subjects: High-speed railway environment -- Passenger overall comfort -- Neural signature -- Current source density -- Machine learning -- Field test; Buildings -- Environmental engineering -- Periodicals; Building -- Research -- Periodicals; Constructions -- Technique de l'environnement -- Périodiques; Electronic journals; 696
• DOI: 10.1016/j.buildenv.2021.108711
• Languages: English
• ISSNs: 0360-1323

Abstract

Abstract: The overall comfort of train passenger is influenced by many environmental factors such as vibration, noise and pressure. However, the couple effect of these influencing factors causes the difficulty in evaluating the overall comfort. This study revealed the potential comfort degradation mechanisms in high-speed railway environments and proposed a machine learning evaluation model to assess passenger comfort. Here, the subjective overall comfort ratings and the electroencephalography (EEG) of twenty passengers were collected in the field tests. Compared with passengers who were in a state of comfort, the brain areas (BA6/13/20/24/31/40/47) of passengers who felt uncomfortable were all significantly activated in the beta band. Based on the neural signature above, three related human reactions when passengers feel uncomfortable were recognized, including perceiving the environment, inducing negative emotions, and finally producing body movement intention. To assess the overall comfort of train passengers, six kinds of features extracted from EEG signals were used to train an evaluation model based on the LightGBM algorithm. This work offers a neurological explanation for the mechanisms of degradation of overall comfort and provides a novel and effective method to assess it. Highlights: Carried out a field test in high-speed railway operating environments. Collect the EEG signals and questionnaires to assess passenger overall comfort. Establish a machine learning model for overall comfort evaluation. First-of-its-kind that reveal the discomfort mechanism based on neural signatures. Prove that the emotional regulation has a great influence on passenger comfort.