1st Edition

Human Activity Recognition Using Wearable Sensors and Smartphones

    208 Pages 41 B/W Illustrations
    by Chapman & Hall

    Learn How to Design and Implement HAR Systems

    The pervasiveness and range of capabilities of today’s mobile devices have enabled a wide spectrum of mobile applications that are transforming our daily lives, from smartphones equipped with GPS to integrated mobile sensors that acquire physiological data. Human Activity Recognition: Using Wearable Sensors and Smartphones focuses on the automatic identification of human activities from pervasive wearable sensors—a crucial component for health monitoring and also applicable to other areas, such as entertainment and tactical operations.

    Developed from the authors’ nearly four years of rigorous research in the field, the book covers the theory, fundamentals, and applications of human activity recognition (HAR). The authors examine how machine learning and pattern recognition tools help determine a user’s activity during a certain period of time. They propose two systems for performing HAR: Centinela, an offline server-oriented HAR system, and Vigilante, a completely mobile real-time activity recognition system. The book also provides a practical guide to the development of activity recognition applications in the Android framework.

    Human Activity Recognition: Theory Fundamentals
    Introduction
    Human activity recognition approaches
    Human activity recognition with wearable sensors
    Human activity recognition problem
    Structure of the book

    Human Activity Recognition
    Design issues
    Activity recognition methods
    Evaluating HAR systems

    State of the Art in HAR Systems
    Evaluation of HAR systems
    Online HAR systems
    Supervised offline systems
    Semi-supervised approaches

    Incorporating Physiological Signals to Improve Activity Recognition Accuracy
    Description of the system
    Evaluation
    Concluding remarks

    Enabling Real-Time Activity Recognition
    Existing mobile real-time HAR systems
    Proposed system
    Evaluation
    Concluding remarks

    New Fusion and Selection Strategies in Multiple Classifier Systems
    Types of multiple classifier systems
    Classifier-level approaches
    Combination-level approaches
    Probabilistic strategies in multiple classifier systems
    Evaluation
    Concluding remarks

    Conclusions
    Summary of findings and results
    Future research considerations

    HAR in an Android Smartphone: A Practical Guide
    Introduction to Android
    Android platform
    Android application components

    Getting Ready to Develop Android Applications
    Installing the software development environment
    A Hello World application
    Skeleton of an Android application
    Running Android applications

    Using the Smartphone’s Sensors
    An example application

    Bluetooth Connectivity in Android
    Exchanging data with an external device via Bluetooth

    Saving and Retrieving Data in an Android Smartphone
    Shared preferences
    Working with files
    SQLite databases

    Feature Extraction
    Data representation
    Feature extraction computations

    Real-Time Classification in Smartphones Using WEKA
    A first look into Weka
    Weka API
    Enabling Weka in an Android smartphone
    Real-time activity recognition

    Bibliography

    Index

    Biography

    Miguel A. Labrador earned his M.Sc. in telecommunications and the Ph.D. degree in information science with concentration in telecommunications from the University of Pittsburgh, in 1994 and 2000, respectively. Since 2001, he has been with the University of South Florida, Tampa, where he is currently a full professor in the department of computer science and engineering, the director of the graduate programs, and the director of the research experiences for undergraduates program. His research interests are in ubiquitous sensing, location-based services, energy-efficient mechanisms for wireless sensor networks, and design and performance evaluation of computer networks and communication protocols. He has published more than 100 technical and educational papers in journals and conferences devoted to these topics. Dr. Labrador has served as technical program committee member of many IEEE conferences and is currently area editor of Computer Communications and editorial board member of the Journal of Network and Computer Applications, both Elsevier Science journals. Dr. Labrador is the lead author of Location-Based Information Systems: Developing Real-Time Tracking Applications, Taylor & Francis, and Topology Control in Wireless Sensor Networks, Springer. Dr. Labrador is senior member of the IEEE and a member of ACM, ASEE and Beta Phi Mu.

    Oscar D. Lara Yejas received his B.Sc. in systems engineering from Universidad del Norte, Barranquilla, Colombia, in 2007. He received his M.Sc. in computer science in 2010 and his Ph.D. in computer science and engineering in 2012, both from the University of South Florida. Dr. Lara Yejas has significant industry experience in the public utilities sector, leading projects related to mobile visualization of geographic and cartographic information, real-time tracking applications, and telemetry. He has also worked on intelligent transportation systems with the Center for Urban Transportation Research (CUTR) at the University of South Florida. He was part of the development team of the Travel Assistance Device (TAD), a mobile application for aiding cognitively disabled people to use public transportation. Dr. Lara Yejas’ dissertation on human activity recognition with wearable sensors under the advising of Dr. Labrador has given birth to this book. In 2012, Dr. Lara Yejas joined International Business Machines Corporation (IBM) within the InfoSphere BigInsights group. His current work focuses on large-scale analytics in distributed computing environments. Further research interests of his encompass but are not limited to machine learning, big data analytics, location-based systems, as well as multiobjective optimization using swarm intelligence methods.