A deep learning approach towards railway safety risk assessment

Alawad, H, Kaewunruen, S and An, M ORCID: https://orcid.org/0000-0002-1069-7492 2020, 'A deep learning approach towards railway safety risk assessment' , IEEE Access, 9 (2020) , pp. 1-23.

PDF - Published Version
Available under License Creative Commons Attribution 4.0.

Download (2MB) | Preview


Railway stations are essential aspects of railway systems, and they play a vital role in public daily life. Various types of AI technology have been utilised in many fields to ensure the safety of people and their assets. In this paper, we propose a novel framework that uses computer vision and pattern recognition to perform risk management in railway systems in which a convolutional neural network (CNN) is applied as a supervised machine learning model to identify risks. However, risk management in railway stations is challenging because stations feature dynamic and complex conditions. Despite extensive efforts by industry associations and researchers to reduce the number of accidents and injuries in this field, such incidents still occur. The proposed model offers a beneficial method for obtaining more accurate motion data, and it detects adverse conditions as soon as possible by capturing fall, slip and trip (FST) events in the stations that represent high-risk outcomes. The framework of the presented method is generalisable to a wide range of locations and to additional types of risks.

Item Type: Article
Schools: Schools > School of the Built Environment > Centre for Urban Processes, Resilient Infrastructures & Sustainable Environments
Journal or Publication Title: IEEE Access
Publisher: IEEE Access
ISSN: 2169-3536
Related URLs:
Funders: European Commission for the financial sponsorship of the H2020-RISE Project
Depositing User: Professor Min An
Date Deposited: 05 Jun 2020 10:06
Last Modified: 16 Feb 2022 04:47
URI: https://usir.salford.ac.uk/id/eprint/57175

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)


Downloads per month over past year