Machine Learning: Foundations, Methodologies, and Applications: Construction, Representation and Application

Li, Yong; Liu, Yu; Zhou, Zhilun

The development of smart cities relies on the growing research in data-driven urban intelligence, driven by the tremendous accumulation in urban data and advancements in artificial intelligence. However, current research faces issues of robustness and explainability. To overcome these obstacles and foster the growth of smart cities, the emergence of robust and explainable urban knowledge is important. Building urban knowledge graph (UrbanKG) offers a tailored solution for urban environments. This comprehensive book serves as a roadmap to UrbanKG, beginning with a foundational understanding of knowledge graphs and delving into the methods of constructing UrbanKG from diverse urban data sources. It explains methodologies for learning representations of UrbanKG, enabling the extraction of semantic and structural information. Furthermore, it explores a range of UrbanKG applications, including urban mobility, user behavior modelling, recommender systems, and mobile networks. Finally, it concludes and discusses future directions of UrbanKG. This book caters to a broad audience, including students, researchers, and professionals in fields such as urban computing, machine learning, and data mining. By offering both theoretical insights and practical applications, it not only enriches understanding but also presents a potential solution to challenges in the landscape of smart cities

Details

Published by: Springer

Publication Date: 2026-08-09

Format: Hardcover

ISBN-13: 9789819221196

DOI:

Dimensions: 235cm x155cm

Pages: