Loading [a11y]/accessibility-menu.js
Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends | IEEE Journals & Magazine | IEEE Xplore

Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends


Abstract:

Transportation systems operate in a domain that is anything but simple. Many exhibit both spatial and temporal characteristics, at varying scales, under varying condition...Show More

Abstract:

Transportation systems operate in a domain that is anything but simple. Many exhibit both spatial and temporal characteristics, at varying scales, under varying conditions brought on by external sources such as social events, holidays, and the weather. Yet, modeling the interplay of factors, devising generalized representations, and subsequently using them to solve a particular problem can be a challenging task. These situations represent only a fraction of the difficulties faced by modern intelligent transportation systems (ITS). In this paper, we present a survey that highlights the role modeling techniques within the realm of deep learning have played within ITS. We focus on how practitioners have formulated problems to address these various challenges, and outline both architectural and problem-specific considerations used to develop solutions. We hope this survey can help to serve as a bridge between the machine learning and transportation communities, shedding light on new domains and considerations in the future.
Published in: IEEE Transactions on Intelligent Transportation Systems ( Volume: 21, Issue: 8, August 2020)
Page(s): 3152 - 3168
Date of Publication: 24 July 2019

ISSN Information:

Funding Agency:


I. Introduction

An incredible amount of data is created every day within transportation. Technology such as modern-day smartphones, for example, are carried by millions of people, and are often equipped to capture movement patterns through accelerometers, gyroscopes, or GPS traces. There are cameras that overlook street intersections, loop detectors embedded along roads, train stations that record entry and exit traffic, and logs of individuals requesting rides to and from specific locations in taxi or ride-sharing scenarios. Many modern transportation systems have begun to embrace the idea of data-driven paradigms as a means to obtain more accurate predictions or advanced control policies, by learning from this data [116].

References

References is not available for this document.