Machine Learning for Transportation Research and Applications

Transportation is a combination of systems that presents a variety of challenges often too intricate to be addressed by conventional parametric methods. Increasing data availability and recent advancements in Machine Learning provide new methods to tackle challenging transportation problems. This textbook is designed for college or graduate-level students in transportation or closely related fields to study and understand fundamentals in Machine Learning (ML). Readers will learn how to develop and apply various types of Machine Learning models to transportation-related problems. Example applications include traffic sensing, data-quality control, traffic prediction, transportation asset management, traffic-system control and operations, and traffic-safety analysis. Designing and applying proper Machine Learning algorithms to problems of different domains, including transportation problems, require a comprehensive understanding of every corner of machine learning techniques and basic theories. The Chapter 2 introduces a spectrum of key concepts in the field of Machine Learning, starting with the definition and categories of Machine Learning, and then covering the basic building blocks of advanced Machine Learning algorithms. The theory behind the common regressions, including linear regression and logistic regression, gradient descent algorithms, regularization, and other key concepts of Machine Learning are discussed. Additionally, this chapter introduces representative Machine Learning tools to fulfill data preprocessing, training, and testing procedures. Recently, classical ML methods have been overshadowed by Deep Learning (DL) in many fields, partially because of the end-to-end structure of the DL methods with good adaptability and without the need for feature engineering. However, classical ML methods are the building blocks of DL methods, and the overall training and testing process of ML and DL are the same. Meanwhile, classical methods with simpler model structure work well with small data. The interpretability of classical ML methods may be even better than most of the so-called “black-box” DL methods. Classical ML methods are still broadly adopted in transportation applications, e.g., transportation-mode recognition, road surface-condition detection, congestion detection, driver behavior classification, passenger number estimation, bottleneck identification, and vehicular network faulty detection. Thus, this chapter introduces the most important Machine Learning basics before presenting more advanced models. Introduces fundamental Machine Learning theories and methodologies Presents state-of-the-art Machine Learning methodologies and their incorporation into transportation domain knowledge Includes case studies or examples in each chapter that illustrate the application of methodologies and techniques for solving transportation problems Provides practice questions following each chapter to enhance understanding and learning Includes class projects to practice coding and the use of the methods