This book offers a clear understanding of the concept of context-aware machine learning including an automated rule-based framework within the broad area of data science and analytics, particularly, with the aim of data-driven intelligent decision making. Thus, we have bestowed a comprehensive study on this topic that explores multi-dimensional contexts in machine learning modeling, context discretization with time-series modeling, contextual rule discovery and predictive analytics, recent-pattern or rule-based behavior modeling, and their usefulness in various context-aware intelligent applications and services. The presented machine learning-based techniques can be employed in a wide range of real-world application areas ranging from personalized mobile services to security intelligence, highlighted in the book. As the interpretability of a rule-based system is high, the automation in discovering rules from contextual raw data can make this book more impactful for the application developers as well as researchers. Overall, this book provides a good reference for both academia and industry people in the broad area of data science, machine learning, AI-Driven computing, human-centered computing and personalization, behavioral analytics, IoT and mobile applications, and cybersecurity intelligence.

This book presents a review of traditional context-aware computing research, identifies its limitations in developing social context-aware pervasive systems, and introduces a new technology framework to address these limitations. Thus, this book provides a good reference for developments in context-aware computing and pervasive social computing. It examines the emerging area of pervasive social computing, which is a novel collective paradigm derived from pervasive computing, social media, social networking, social signal processing and multimodal human-computer interaction. This book offers a novel approach to model, represent, reason about and manage different types of social context. It shows how users' social context information can be acquired from different online social networks such as Facebook, LinkedIn, Twitter and Google Calendar. It further presents the use of social context information in developing innovative smart mobile applications to assist users in their daily life. The mix of both theoretical and applied research results makes this book attractive to a variety of readers from both academia and industry. This book provides a new platform for implementing different types of socially-aware mobile applications. The platform hides the complexity of managing social context, and thus provides essential support to application developers for the development of socially-aware applications. The book contains detailed descriptions of how the underlying platform has been implemented using available technologies such as ontology and rule engines, and how this platform can be used to develop socially-aware mobile applications using two exemplar applications. The book also presents evaluations of the proposed platform and applications using real-world data from Facebook, LinkedIn and Twitter. Therefore, this book is a syndication of scientific research with practical industrial applications, making it useful to researchers as well as to software engineers.

This book presents a review of traditional context-aware computing research, identifies its limitations in developing social context-aware pervasive systems, and introduces a new technology framework to address these limitations. Thus, this book provides a good reference for developments in context-aware computing and pervasive social computing. It examines the emerging area of pervasive social computing, which is a novel collective paradigm derived from pervasive computing, social media, social networking, social signal processing and multimodal human-computer interaction. This book offers a novel approach to model, represent, reason about and manage different types of social context. It shows how users' social context information can be acquired from different online social networks such as Facebook, LinkedIn, Twitter and Google Calendar. It further presents the use of social context information in developing innovative smart mobile applications to assist users in their daily life. The mix of both theoretical and applied research results makes this book attractive to a variety of readers from both academia and industry. This book provides a new platform for implementing different types of socially-aware mobile applications. The platform hides the complexity of managing social context, and thus provides essential support to application developers for the development of socially-aware applications. The book contains detailed descriptions of how the underlying platform has been implemented using available technologies such as ontology and rule engines, and how this platform can be used to develop socially-aware mobile applications using two exemplar applications. The book also presents evaluations of the proposed platform and applications using real-world data from Facebook, LinkedIn and Twitter. Therefore, this book is a syndication of scientific research with practical industrial applications, making it useful to researchers as well as to software engineers.

This book offers a clear understanding of the concept of context-aware machine learning including an automated rule-based framework within the broad area of data science and analytics, particularly, with the aim of data-driven intelligent decision making. Thus, we have bestowed a comprehensive study on this topic that explores multi-dimensional contexts in machine learning modeling, context discretization with time-series modeling, contextual rule discovery and predictive analytics, recent-pattern or rule-based behavior modeling, and their usefulness in various context-aware intelligent applications and services. The presented machine learning-based techniques can be employed in a wide range of real-world application areas ranging from personalized mobile services to security intelligence, highlighted in the book. As the interpretability of a rule-based system is high, the automation in discovering rules from contextual raw data can make this book more impactful for the application developers as well as researchers. Overall, this book provides a good reference for both academia and industry people in the broad area of data science, machine learning, AI-Driven computing, human-centered computing and personalization, behavioral analytics, IoT and mobile applications, and cybersecurity intelligence.

This volume is composed of four major in-depth yet pedagogic review chapters on the subject of star formation, written by the foremost researchers in the field. Recent infrared and millimeter radio observations are respectively reviewed by Charlie Lada and Phil Myers, both of Harvard-Smithsonian Center for Astrophysics. The theoretical work is reviewed by Frank Shu of UC-Berkeley on the gravitational collapse of dense cores in a giant molecular cloud to form sunlike stars and Bruce Elmegreen of IBM-Watson on the gravitational instability, leading to large-scale star formation. They have written at a level most suitable for graduate students or young researchers who want to develop their research interest in the field, with the most complete literature survey to date. This volume is not an ordinary conference proceedings, but a textbook to be used in graduate study in astrophysics. The volume also includes other short and interesting contributions from Doug Lin of UC-Santa Cruz, Paul Ho of Harvard-Smithsonian, Masa Hayashi of Tokyo University, Debra Elmegreen of Vassar, Jing-Yao Hu of Beijing Observatory, Guo-Xuan Sung of Shanghai Observatory, Chi Yuan of CCNY and ASIAA, and Wen-Ping Chen of Central University, Taiwan.