Recent years have witnessed the flourish of Internet-of-Things (IoT), in which sensors connect spatial entities to constitute complex Cyber-Physical Systems (CPSs). In this setting, spatial-temporal data becomes increasingly available. Mining spatial-temporal data can reveal holistic user and system structures, dynamics, and semantics of the underlying CPSs, including identifying trends, forecasting future behavior, and detecting anomalies. However, obtaining effective representations over spatial-temporal data remains a big challenge for the following reasons: (1) on the one hand, traditional manual feature design is labor-intensive and time-consuming facing the complex and huge volumes of spatial-temporal data; (2) on the other hand, as an emerging automatic feature generation technique, representation learning cannot be directly adopted to spatial-temporal data because of the unique data characteristics. Therefore, in this dissertation, I propose to study the problem of automated learning effective representations from spatial-temporal data with considering unique characteristics. Specifically, the dissertation consists of three thrusts: (i) collective representation learning, which considers the multi-view setting for driving behavior analysis; (2) structure-aware representation learning, which considers the rich semantics for mobile user profiling; and (3) interactive representation learning, which considers the dynamics for modeling human-environment interaction. Finally, I conclude the dissertation with a discussion of potential future topics.
If this is your thesis or dissertation, and want to learn how to access it or for more information about readership statistics, contact us at STARS@ucf.edu.
Doctor of Philosophy (Ph.D.)
College of Engineering and Computer Science
Length of Campus-only Access
Doctoral Dissertation (Open Access)
Wang, Pengyang, "Spatial-Temporal Representation Learning: Concepts, Algorithms and Applications" (2021). Electronic Theses and Dissertations, 2020-. 580.