Xiaogang Wang

This book offers a systematic view of data services in heterogeneous wireless networks, from the perspectives of cause, governing rules, and impact of data’s mobility on such networks. Specifically, it covers application requirements break-down, network modeling, performance analysis and evaluation by examining mobile data dynamics that are particularly important to data service provisioning. Additionally, application prospects such as information dissemination, fog computing, Internet-of-Things and dynamic spectrum access are discussed on the basis of these dynamics. Theoretic analysis, example illustrations, and algorithms are also presented to provide a concise coverage of this important area of networking. Mobile data dynamics refers to the stochastic processes of information, geographical coverage and spectrum, which accompanies the movements of data across wireless networks. Owing to the challenge raised by a high level of network heterogeneity, and the innate requirement on scalability, knowledge on the evolution of mobile data dynamics is essential to the design and deployment of emerging data services and applications, such as Internet-of-Things, data/task offloading and edge-based machine learning/inference. This book is designed for researchers and advanced-level students in the field of wireless networking and edge computing, who seek to understand the models and evolutions of mobile data dynamics for future edge applications. Practitioners, who specialize in the design, operation and maintenance of edge computing systems will also want to purchase this book as a reference.

As a major breakthrough in artificial intelligence, deep learning has achieved impressive success on solving grand challenges in many fields including speech recognition, natural language processing, computer vision, image and video processing, and multimedia. This monograph provides a historical overview of deep learning and focuses on its applications in object recognition, detection, and segmentation, which are key challenges of computer vision and have numerous applications to images and videos. Specifically the topics covered under object recognition include image classification on ImageNet, face recognition, and video classification. In detection, the monograph covers general object detection on ImageNet, pedestrian detection, face landmark detection (face alignment), and human landmark detection (pose estimation). Finally, within segmentation, it covers the most recent progress on scene labeling, semantic segmentation, face parsing, human parsing, and saliency detection. Concrete examples of these applications explain the key points that make deep learning outperform conventional computer vision systems. Deep Learning in Object Recognition, Detection, and Segmentation provides a comprehensive introductory overview of a topic that is having major impact on many areas of research in signal processing, computer vision, and machine learning. This is a must-read for students and researchers new to these fields.