Indoor localization is a research domain that aims to locate mobile devices or users in the indoor environments. More and more research has investigated to acquire the location information based upon existing Wi-Fi infrastructure. A technique of using current Wi-Fi data and a fingerprint database containing Wi-Fi fingerprints of desired locations for localization is known as Wi-Fi fingerprinting. Most current approaches for Wi-Fi fingerprinting depend on labor-intensive and time-consuming site surveys by professional staff or users to generate a fingerprint database of desired locations. Moreover, these approaches are not satisfactory for long-term localization of mobile devices in practice due to the costly and continuous update of the fingerprint database. In this thesis, we propose an approach to the indoor localization problem, in which we combine the Wi-Fi fingerprinting technique and the place learning technique to learn and update the Wi-Fi fingerprints of significant locations in an unsupervised manner. Significant locations are locations a user spent at least for a while (e.g., 10 minutes) and are most important and highly frequented in people’s daily lives. The conventional approaches use labeled Wi-Fi data intentionally collected by professional staff or users and learn Wi-Fi fingerprints of desired locations. Instead, the proposed approach uses unlabeled Wi-Fi data collected in a user’s daily life and learns Wi-Fi fingerprints of significant locations related to user’s daily trajectory and activities. We implement an autonomous indoor localization system WHERE based on the proposed approach. The system can automatically learn and update Wi-Fi fingerprints of significant locations, and determine the location of the mobile device when it returns to the learned locations. Moreover, we evaluate various measures of performance, in term of the location accuracy, the computational time, the power consumption, the size of a fingerprint database, and the system reliability in a practical use. Performance evaluation shows that the proposed autonomous indoor localization system WHERE is a reliable system for efficient use – being very low-cost to set up and maintain, and showing satisfactory localization performance.

This book constitutes the proceedings of the 9th International and Interdisciplinary Conference on Modeling and Using Context, CONTEXT 2015, held in Larnaca, Cyprus, in November 2015. The 33 full papers and 13 short papers presented were carefully reviewed and selected from 91 submissions. The main theme of CONTEXT 2015 was "Back to the roots", focusing on the importance of interdisciplinary cooperations and studies of the phenomenon. Context, context modeling and context comprehension are central topics in linguistics, philosophy, sociology, artificial intelligence, computer science, art, law, organizational sciences, cognitive science, psychology, etc. and are also essential for the effectiveness of modern, complex and distributed software systems. CONTEXT 2015 embedded also a Doctoral Symposium, and three workshops; Smart University 3.0; CATI: Context Awareness and Tactile Design for Mobile Interaction; and SHAPES 3.0: The Shape of Things.

This book provides a comprehensive and in-depth understanding of wireless indoor localization for ubiquitous applications. The past decade has witnessed a flourishing of WiFi-based indoor localization, which has become one of the most popular localization solutions and has attracted considerable attention from both the academic and industrial communities. Specifically focusing on WiFi fingerprint based localization via crowdsourcing, the book follows a top-down approach and explores the three most important aspects of wireless indoor localization: deployment, maintenance, and service accuracy. After extensively reviewing the state-of-the-art literature, it highlights the latest advances in crowdsourcing-enabled WiFi localization. It elaborated the ideas, methods and systems for implementing the crowdsourcing approach for fingerprint-based localization. By tackling the problems such as: deployment costs of fingerprint database construction, maintenance overhead of fingerprint database updating, floor plan generation, and location errors, the book offers a valuable reference guide for technicians and practitioners in the field of location-based services. As the first of its kind, introducing readers to WiFi-based localization from a crowdsourcing perspective, it will greatly benefit and appeal to scientists and researchers in mobile and ubiquitous computing and related areas.

While GPS is the de-facto solution for outdoor positioning with a clear sky view, there is no prevailing technology for GPS-deprived areas, including dense city centers, urban canyons, buildings and other covered structures, and subterranean facilities such as underground mines, where GPS signals are severely attenuated or totally blocked. As an alternative to GPS for the outdoors, indoor localization using machine learning is an emerging embedded and Internet of Things (IoT) application domain that is poised to reinvent the way we navigate in various indoor environments. This book discusses advances in the applications of machine learning that enable the localization and navigation of humans, robots, and vehicles in GPS-deficient environments. The book explores key challenges in the domain, such as mobile device resource limitations, device heterogeneity, environmental uncertainties, wireless signal variations, and security vulnerabilities. Countering these challenges can improve the accuracy, reliability, predictability, and energy-efficiency of indoor localization and navigation. The book identifies severalnovel energy-efficient, real-time, and robust indoor localization techniques that utilize emerging deep machine learning and statistical techniques to address the challenges for indoor localization and navigation. In particular, the book: Provides comprehensive coverage of the application of machine learning to the domain of indoor localization; Presents techniques to adapt and optimize machine learning models for fast, energy-efficient indoor localization; Covers design and deployment of indoor localization frameworks on mobile, IoT, and embedded devices in real conditions.

This book first presents a systematic theoretical study of wireless localization techniques. Then, guided by the theoretical results, the authors provide design approaches for improving the performance of localization systems and making the deployment of the systems more convenient. The book aims to address the following issues: how reliable the wireless localization system can be; how the system can scale up with the number of users to be served; how to make key design decisions in implementing the system; and how to mitigate human efforts in deploying the wireless localization system. The book is relevant for researchers, academics, and students interested in wireless localization technology.

The four-volume set LNCS 11334-11337 constitutes the proceedings of the 18th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2018, held in Guangzhou, China, in November 2018. The 141 full and 50 short papers presented were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on Distributed and Parallel Computing; High Performance Computing; Big Data and Information Processing; Internet of Things and Cloud Computing; and Security and Privacy in Computing.

The advent of Internet of Things offers a scalable and seamless connection of physical objects, including human beings and devices. This, along with artificial intelligence, has moved transportation towards becoming intelligent transportation. This book is a collection of eleven articles that have served as examples of the success of internet of things and artificial intelligence deployment in transportation research. Topics include collision avoidance for surface ships, indoor localization, vehicle authentication, traffic signal control, path-planning of unmanned ships, driver drowsiness and stress detection, vehicle density estimation, maritime vessel flow forecast, and vehicle license plate recognition. High-performance computing services have become more affordable in recent years, which triggered the adoption of deep-learning-based approaches to increase the performance standards of artificial intelligence models. Nevertheless, it has been pointed out by various researchers that traditional shallow-learning-based approaches usually have an advantage in applications with small datasets. The book can provide information to government officials, researchers, and practitioners. In each article, the authors have summarized the limitations of existing works and offered valuable information on future research directions.