An interpretable multi-task TabNet framework for predicting multidimensional railway accident severity
Authors:
- Mingyang JiMJMingyang Ji
- Wei ShangguanWSWei Shangguan
- Cong PengCong Peng
- Yuening ZhuYZYuening Zhu
- Feijie GongFGFeijie Gong
- 18 September 2026
- journal article
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 278
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (52272328)
- Beijing Municipal Outstanding Young Talents (JWZQ20240101010)
- Natural Science Foundation of Beijing Municipality
- Natural Science Foundation of Beijing Municipality (L231003)
This publication has 42 references indexed in Scilit:
- Evaluating crash risk factors of farm equipment vehicles on county and non-county roads using interpretable tabular deep learning (TabNet)Accident Analysis & Prevention, 2025
- A new procedure for assessing and predicting the severity of accidents: A case study on freight-train derailmentsJournal of Loss Prevention in the Process Industries, 2024
- Mitigating gradient conflicts via expert squads in multi-task learningNeurocomputing, 2024
- Multi-objective preventive maintenance strategy and optimization considering unavailability and cost: A case study on VOBCAlexandria Engineering Journal, 2024
- Railway accident causation analysis: Current approaches, challenges and potential solutionsAccident Analysis & Prevention, 2023
- Railway accident prediction strategy based on ensemble learningAccident Analysis & Prevention, 2022
- Tabular data: Deep learning is not all you needInformation Fusion, 2022
- An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factorsAccident Analysis & Prevention, 2021
- A deep learning based traffic crash severity prediction frameworkAccident Analysis & Prevention, 2021
- Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysisAccident Analysis & Prevention, 2020