Crash Severity Analysis of Child Bicyclists using Arm-Net and MambaNet

2025-03-14

AI Summary

This study addresses the critical traffic safety problem of predicting injury severity among bicyclists aged ≤14 years. Leveraging 2,394 real-world collision records from Texas (2017–2022), we developed and comparatively evaluated two deep tabular learning models—ARM-Net and MambaNet—specifically adapted for injury classification. To our knowledge, this is the first application of the state-space model MambaNet to traffic injury severity classification; we further integrated SMOTEENN to mitigate class imbalance across the three injury categories: fatal/severe (KA), minor (BC), and no injury (O). Experimental results demonstrate that MambaNet achieves F1-scores exceeding 0.89 for both KA and O classes, with an overall accuracy of 85.3%, significantly outperforming ARM-Net. Notably, BC classification remains challenging due to feature overlap, underscoring the importance of balanced sampling and advanced sequential modeling for enhancing risk identification among vulnerable road users.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Child bicyclists (14 years and younger) are among the most vulnerable road users, often experiencing severe injuries or fatalities in crashes. This study analyzed 2,394 child bicyclist crashes in Texas from 2017 to 2022 using two deep tabular learning models (ARM-Net and MambaNet). To address the issue of data imbalance, the SMOTEENN technique was applied, resulting in balanced datasets that facilitated accurate crash severity predictions across three categories: Fatal/Severe (KA), Moderate/Minor (BC), and No Injury (O). The findings revealed that MambaNet outperformed ARM-Net, achieving higher precision, recall, F1-scores, and accuracy, particularly in the KA and O categories. Both models highlighted challenges in distinguishing BC crashes due to overlapping characteristics. These insights underscored the value of advanced tabular deep learning methods and balanced datasets in understanding crash severity. While limitations such as reliance on categorical data exist, future research could explore continuous variables and real-time behavioral data to enhance predictive modeling and crash mitigation strategies.

Problem

• Analyzing crash severity in child bicyclists using deep learning models.
• Addressing data imbalance with SMOTEENN for accurate severity predictions.
• Improving crash severity prediction accuracy with MambaNet over ARM-Net.

Innovation

• Used ARM-Net and MambaNet for crash analysis
• Applied SMOTEENN to balance datasets
• MambaNet outperformed ARM-Net in accuracy