Predictive Model for Incident Severity at Railway Construction Site Using Rapid Miner

• Published in: International Journal of Sustainable Construction Engineering and Technology
• Main Author: Ngadiron Z.; Ganasan R.; Ramli M.F.; Mahyeddin M.E.; Luqman M.I.; Jiafu G.; Kamaluddin N.A.
• Format: Article
• Language: English
• Published: Penerbit UTHM 2024
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85215411387&doi=10.30880%2fijscet.2025.00.00.000&partnerID=40&md5=462555dc7a7613256d3e1c2706af1fe8

Railway construction sites are prone to accidents; to be worse, it involves fatality. This is because many factors cannot be controlled due to the hectic working environment. In order to forecast the severity of mishaps at railway construction sites, this study investigates past incidents using machine learning (ML). The study analyzes data from railway construction using k-Nearest Neighbors (k-NN), Decision Trees (DT), Deep Learning (DL), and Support Vector Machines (SVM) implemented in RapidMiner software. ML is used because of its capability to learn about the relationship between each factor and parameter of the incident, thus producing relevant predictions of severity incidents. Finding high-severity occurrences, creating a prediction model, and evaluating the effectiveness of the ML techniques using metrics like accuracy, precision, recall, and F1-score are the objectives. A 70:30 training-testing data split was used, and the results aim to identify the best ML method for predicting incident severity at railway construction sites. SVM and DL are better at predicting the severity of accidents due to their high precision, with both having a 0.91 score for precision. At the same time, DT is favourable for minimising missed critical accidents due to its high recall of 0.89. k-NN shows the most unfavourable performance among these machine learning. This study served as a benchmark for future railway projects, informed mitigation actions and procedures and provided a deeper understanding of potential incidents. © 2024, Penerbit UTHM. All rights reserved.