Detecting Pedestrian Situation Awareness in Real-Time: Algorithm Development Using Heart Rate Variability and Phone Position. (September 2018)

• Record Type: Journal Article
• Authors: Tong, Yourui; Jia, Bochen; Wang, Yi; Yang, Si
• Is Part Of: Proceedings of the Human Factors and Ergonomics Society ... Annual Meeting. Volume 62:Part 1(2018)
• Page Start: 1579
• Page End: 1583
• Publication Date: 2018-09
• Subjects: Human engineering -- Congresses; 620.8205
• DOI: 10.1177/1541931218621357
• Languages: English
• ISSNs: 1541-9312

Abstract

To help automated vehicles learn surrounding environments via V2X communications, it is important to detect and transfer pedestrian situation awareness to the related vehicles. Based on the characteristics of pedestrians, a real-time algorithm was developed to detect pedestrian situation awareness. In the study, the heart rate variability (HRV) and phone position were used to understand the mental state and distractions of pedestrians. The HRV analysis was used to detect the fatigue and alert state of the pedestrian, and the phone position was used to define the phone distractions of the pedestrian. A Support Vector Machine algorithm was used to classify the pedestrian's mental state. The results indicated a good performance with 86% prediction accuracy. The developed algorithm shows high applicability to detect the pedestrian's situation awareness in real-time, which would further extend our understanding on V2X employment and automated vehicle design.