Spatio-Temporal Data Analytics for Intelligent Transportation Systems: An Overview

This study addresses the significance of spatio-temporal data analytics in Intelligent Transportation Systems (ITS), the various sources of spatio-temporal data, and the different technologies used to deploy ITS. It examines the body of research, points out shortcomings, and talks about new developments in the machine learning techniques for ITS. It discusses a variety of state-of-the-art methods used for data analytics in ITS. Following a study of the most recent research, we also list and evaluate the primary challenges faced in ITS. Future directions for ITS research and various ITS applications are also covered in this study. The paper addresses the challenges of security, privacy, and scalability while processing and analyzing massive amounts of spatiotemporal data. The potential of ITS to enhance sustainability, safety, and efficiency of transportation systems is also covered in this study.

I. Introduction

Data analytics has become a prominent topic both in academia and industry and with the advancement of learning algorithms, there has been a significant increase in the interest shown towards the field [1]. Spatio-temporal data analytics refers to the analysis of data that has both temporal and spatial properties, i.e. the data that varies along both space and time, or in other words, the data is collected across time as well as space, and each data point has at least one spatial (location) and one temporal (time) property [2]. It's used in various domains including biology, ecology, meteorology, medicine, epidemiology, forestry, and transportation [3], [4].