Semantics in mobile sensing

Semantics in mobile sensing /

The dramatic progress of smartphone technologies has ushered in a new era of mobile sensing, where traditional wearable on-body sensors are being rapidly superseded by various embedded sensors in our smartphones. For example, a typical smartphone today, has at the very least a GPS, WiFi, Bluetooth,...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan, Zhixian (Computer scientist) (Author), Chakraborty, Dipanjan (Author)
Format: Electronic eBook
Language:English
Published: Cham, Switzerland : Springer, [2014]
Series:Synthesis lectures on the semantic web, theory and technology ; #8.
Subjects:
Mobile computing.
Sensor networks.
Smartphones.
Online Access:Connect to this title online
Table of Contents:
  • 1. Introduction
  • 1.1 Mobile sensing: definitions and scope
  • 1.1.1 Smartphone-based sensing
  • 1.1.2 Sensing architectures
  • 1.2 Semantics from sensors
  • 1.2.1 Semantic modeling of mobile sensors
  • 1.2.2 Semantic computation from mobile sensors
  • 1.3 Book structure.
  • 2. Semantic trajectories from positioning sensors
  • 2.1 The positioning sensor
  • 2.1.1 Sensor type and functionality
  • 2.1.2 Dealing with positioning data: technical summary
  • 2.1.3 From GPS to semantic trajectories
  • 2.2 Semantic trajectory modeling
  • 2.2.1 Semantic trajectory ontology
  • 2.2.2 Hybrid semantic trajectory model
  • 2.3 Semantic trajectory computation
  • 2.3.1 Data preprocessing layer
  • 2.3.2 Trajectory identification layer
  • 2.3.3 Trajectory structure layer
  • 2.4 Semantic trajectory annotation
  • 2.4.1 Annotation with semantic regions
  • 2.4.2 Annotation with semantic lines
  • 2.4.3 Annotation with semantic points
  • 2.5 Summary and outlook.
  • 3. Semantic activities from motion sensors
  • 3.1 The motion sensor
  • 3.1.1 Sensor functionality
  • 3.1.2 What can we learn from motion?
  • 3.1.3 Data collection
  • 3.2 Feature spaces
  • 3.2.1 Data processing
  • 3.2.2 Feature classes, an overview
  • 3.2.3 Feature computation and energy
  • 3.3 Activity learning techniques
  • 3.3.1 Learning models
  • 3.3.2 Choice of learning models
  • 3.3.3 Testing
  • 3.4 Case study: micro activity (MA) learning
  • 3.4.1 Data collection
  • 3.4.2 Feature vector representation
  • 3.4.3 Results of MA supervised learning
  • 3.5 Case study: complex activity learning
  • 3.5.1 User recruitment and data collection
  • 3.5.2 Data processing & sanitization
  • 3.5.3 Features for complex activities
  • 3.5.4 Complex activity learning approaches
  • 3.5.5 Learning performance
  • 3.6 Conclusions and summary.
  • 4. Energy-efficient computation of semantics from sensors
  • 4.1 Energy-efficient mobile sensing
  • 4.1.1 Smartphone battery limitations
  • 4.1.2 Energy-efficient sensing: hardware approaches
  • 4.1.3 Energy-efficient sensing: software approaches
  • 4.2 Model-based energy-efficient sensing
  • 4.2.1 Two-tier optimal sensing
  • 4.2.2 Model-based optimal segmentation
  • 4.2.3 Model-based optimal sensor sampling
  • 4.3 Energy-efficient semantic activity learning
  • 4.3.1 Classification accuracy vs. energy consumption
  • 4.3.2 A3R, a methodology for continuous adaptive sampling
  • 4.4 Concluding remarks.
  • 5. Conclusion
  • 5.1 Summary
  • 5.2 Challenges and opportunities
  • Bibliography
  • Authors' biographies.

Similar Items