---

This book explores the application of machine learning techiques to problems of classification, showing how they can be decomposed into much simpler sub-problems, and demonstrating how this approach often leads to improved classification performance.

---

Mobile context-awareness is a popular research trend in the field of ubiquitous computing. Advances in mobile device sensory hardware and the rise of ´virtual´ sensors such as web application programming interfaces (APIs) mean that the mobile user is exposed to a vast range of data that can be used for new advanced applications. Mobile Context Awareness presents work from industrial and academic researchers, focusing on novel methods of context acquisition in the mobile environment - particularly through the use of physical and virtual sensors - along with research into new applications utilising this context. In addition, the book provides insights into the technical and usability challenges involved in mobile context-awareness, as well as observations on current and future trends in the field.

---

Foreword.- Introduction.- Modeling Success, Failure, and Intent of Multi-Agent Activities Under Severe Noise.- Energy Accuracy Trade-offs of Sensor Sampling in Smart Phone based Sensing Systems.- Acceleration Noise Correction for Transfer Inference Using Accelerometers on Mobile Devices.- Mobile Sensing of User´s Motion and Position Context for Automatic Check-in Suggestion and Validation.- The Case for Context-Aware Resources Management in Mobile Operating Systems.- A Scalable Sensor Middleware for Social End-User Programming.- Mobile Context-Aware Support for Public Transportation Systems.- Quality Sensitive Web Service Profiling and Discovery: In support of Mobile and Pervasive Applications.- A Middleware Supporting Adaptive and Context-Aware Mobile Applications.

---