Multi-Modal Data-Driven Solutions for Validating Policies in Transportation Systems

本博士项目的主要目标是：以道路收费为例，开发能够整合和处理交通运输中大量多样的多模式复杂数据集的机器学习技术，以验证政策并设计新的有效政策。考虑到从交通网络收集的大量数据，哪些数据类型与政策或干预相关？2.什么机器学习技术适合组合多模态数据集、处理数据和验证干预措施？3.这些多模态数据集和机器学习技术能否用于设计新的有效道路定价政策和/或验证当前政策？

This PhD project will be focused on the following aim:develop machine learning techniques that can integrate and deal with large diverse multi-modal complex datasets in transportation for validating policies and for designing novel efficient policies with road pricing as a case study.In order to achieve the aim of this PhD project, we identified the following research questions:1. Given the large volume of data gathered from the transportation network, what data types are relevant to a policy or intervention?2. What machine learning techniques are suitable for combining multi-modal datasets, processing the data, and validating an intervention?3. Could these multi-modal datasets and machine learning techniques be used for designing novel effective road pricing policies and/or validating current policies?