Data pertaining to Chapter 2 "Driving Heterogeneity Identification using Machine Learning: A Review and Framework for Analysis"

This dataset supports the paper <em>“Driving Heterogeneity Identification using Machine Learning: A Review and Framework for Analysis”</em> (Chapter 2 of the PhD dissertation). The research provides a systematic review of existing machine learning (ML)-based approaches for identifying driving heterogeneity. The review organises key concepts and categorisations of driving heterogeneity, highlights strengths and drawbacks of various methods, and outlines applications of identification analysis. Based on the literature review, a structured framework that guides the ML-based identification process is proposed, including data collection and pre-processing, feature selection, ML model training, and performance evaluation. The dataset includes summary statistics on data collection methods over time and an overview of traffic variables used in the reviewed literature. It is provided as a zipped folder containing files in <code>.ipynb</code> and <code>.xlsx</code> formats, along with a <code>ch2_Readme.txt</code> file that explains the dataset structure and provides usage instructions.

本数据集支持论文《基于机器学习的驾驶异质性（Driving Heterogeneity）识别：综述与分析框架》（博士学位论文第2章）。本研究对现有基于机器学习（Machine Learning, ML）的驾驶异质性识别方法进行了系统性综述。该综述梳理了驾驶异质性的核心概念与分类体系，阐明了各类方法的优势与局限，并概述了识别分析的应用场景。基于本次文献综述，本研究提出了一套指导基于机器学习的识别流程的结构化框架，涵盖数据采集与预处理、特征选择、机器学习模型训练以及性能评估环节。本数据集包含随时间变化的数据采集方法的汇总统计信息，以及综述文献中所使用的交通变量概览。本数据集以压缩文件夹形式提供，内含.ipynb、.xlsx格式文件，以及一份用于说明数据集结构与使用方法的ch2_Readme.txt文件。