A novel framework for the assessment of public-transport drivers' well-being and satisfaction based on physiological data
This paper presents a novel framework for data collection and fusion, for better analysis and assessment of public transportation (PT) drivers' well-being and satisfaction using physiological data. The goal of this framework, when combined with machine learning (ML) and discrete choice models (...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Journal of Public Transportation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1077291X25000141 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper presents a novel framework for data collection and fusion, for better analysis and assessment of public transportation (PT) drivers' well-being and satisfaction using physiological data. The goal of this framework, when combined with machine learning (ML) and discrete choice models (DCMs) to predict drivers' physiological states based on fleet management data, is to improve service reliability and assess the drivers' well-being and satisfaction. A case study based on different ML models and data collected from available physiological indicators was conducted to demonstrate the framework's ability to predict such features as Heart Rate (HR) and Electrodermal Activity (EDA) based on Automatic Vehicle Location (AVL) and Automatic Fare Collection (AFC) systems. The results indicate a significant correlation between service measures (e.g., layover duration, route characteristics and complexity) and the drivers' well-being. Our framework offers practical guidance for decision-makers to enhance operational planning, leading to improved efficiency and healthier working conditions for drivers. Future research should expand the application of the framework to different areas and branches of PT, incorporate additional physiological sensors, and integrate more ML models and DCMs for extensive analysis. |
|---|---|
| ISSN: | 2375-0901 |