Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification

TL;DR

This document surveys the CAS LaTeX class system for preparing Elsevier journal submissions, focusing on cas-sc.cls (single-column) and cas-dc.cls (double-column) and their associated templates. It explains how to manage complex front matter, including the long front matter option longmktitle, and how to annotate authors, affiliations, and corresponding notes with class-provided markers. The text provides practical guidance and examples for constructing title pages, abstracts, keywords, and other front matter elements within the Elsevier submission workflow. The emphasis is on formatting correctness and publisher compliance, offering a reference for authors to generate properly formatted front matter across different journal layouts.

Abstract

This research showcases the innovative integration of Large Language Models into machine learning workflows for traffic incident management, focusing on the classification of incident severity using accident reports. By leveraging features generated by modern language models alongside conventional data extracted from incident reports, our research demonstrates improvements in the accuracy of severity classification across several machine learning algorithms. Our contributions are threefold. First, we present an extensive comparison of various machine learning models paired with multiple large language models for feature extraction, aiming to identify the optimal combinations for accurate incident severity classification. Second, we contrast traditional feature engineering pipelines with those enhanced by language models, showcasing the superiority of language-based feature engineering in processing unstructured text. Third, our study illustrates how merging baseline features from accident reports with language-based features can improve the severity classification accuracy. This comprehensive approach not only advances the field of incident management but also highlights the cross-domain application potential of our methodology, particularly in contexts requiring the prediction of event outcomes from unstructured textual data or features translated into textual representation. Specifically, our novel methodology was applied to three distinct datasets originating from the United States, the United Kingdom, and Queensland, Australia. This cross-continental application underlines the robustness of our approach, suggesting its potential for widespread adoption in improving incident management processes globally.