Deep Learning in Transportation Cyber-Physical Systems

Abstract

Transportation Cyber-Physical Systems (TCPS) integrate the interaction between the connected transportation infrastructure, users, and computing and communication services to support the mobility of people and goods. TCPS is supported by many emerging technologies, among which Deep Learning (DL)-supported technology is a notable one. DL models closely mimic the functionality of human brains, and it can learn the relationship between inputs and outputs through data observations, thus facilitating different information extraction or decision-making functionalities of TCPS. In recent times, the availability of vast amounts of heterogeneous data from TCPS and the introduction of large-scale computing hardware have enabled the different applications of DL models. This chapter discusses early DL models, such as restricted Boltzmann machine, deep belief network, and deep Boltzmann machine, along with the recent ones including multilayer perceptron, autoencoder, convolutional neural network, recurrent neural networks, and deep reinforcement learning. The DL model development and testing considerations in the functioning of TCPS applications are discussed while pointing out the available hardware and software frameworks. Different types of cyberattacks that can occur on DL and the strategies protecting the DL against such cyberattacks are also presented. This chapter concludes with various applications of DL models in TCPS.