Intelligent Wearable Interfaces (eBook)

Yangsheng Xu, PhD, is Chair Professor of Mechanical and Automation Engineering in The Chinese University of Hong Kong (CUHK). Before joining CUHK, he was a faculty member at the Robotics Institute, School of Computer Science, Carnegie Mellon University. His research interests include robotics, intelligent systems, human-machine interface, and hybrid electric vehicles. Wen Jung Li, PhD, is a Professor in the Department of Mechanical and Automation Engineering and the Director of the Centre for Micro and Nano Systems at The Chinese University of Hong Kong (CUHK). Before joining CUHK, he held R&D positions at the NASA Jet Propulsion Laboratory (Pasadena), the Aerospace Corporation (El Segundo), and Silicon Microstructures, Inc. (Fremont). His research interests include micro-electro-mechanical systems and nano-scale sensing and manipulation. Ka Keung Lee, PhD, is a Lecturer in the Department of Mechanical Engineering at The Hong Kong Polytechnic University (PolyU). Before joining PolyU, he was a postdoctoral fellow at The Chinese University of Hong Kong. His research interests include robotics, intelligent systems, human modeling, andintelligent surveillance.

List of Figures.

List of Tables.

Preface.

1. Introduction.

2. Network Architecture for Wearable Robots.

2.1 Introduction.

2.2 Wearable Robots and Interactions.

2.3 Wearable Robot Design.

2.4 Distributed Service-based Architecture.

2.4.1 Extension to the Jini Model.

2.4.2 The Matching Service.

2.5 Application Scenario.

2.6 Related Works.

2.7 Conclusion.

3. Wearable Interface for Automatic LanguageTranslation.

3.1 Introduction.

3.2 System Architecture.

3.3 Text Detection Algorithm.

3.3.1 Demands of Text Detection Algorithm.

3.3.2 Intrinsic Characteristic of a Character.

3.3.3 CIC-based Text Detection Algorithm.

3.3.4 Combine Line Segments into a Character.

3.4 Image Cutting, Rotation & Binarization.

3.4.1 Image Cutting and Rotation.

3.4.2 Image Binarization.

3.5 Real-Time Translation.

3.6 Conclusion.

4. Intelligent Cap Interface for Wheelchair Control.

4.1 Introduction.

4.2 Electromyography and Electrooculopraghy.

4.3 Approach.

4.4 Interface.

4.4.1 Hardware.

4.4.2 Implementation.

4.5 Experimental Study.

4.5.1 Doorways (A-B).

4.5.2 U-turning (B-C-B).

4.5.3 General Path (C-D).

4.6 Conclusion.

5. Intelligent Shoes for Human-Computer Interface.

5.1 Introduction.

5.2 Hardware Design.

5.2.1 Sensing the Parameters inside the Shoe.

5.2.2 Gathering Information from the Sensors.

5.2.3 Wireless Communication.

5.2.4 Data Visualization.

5.3 Three Applications of the Intelligent Shoes.

5.3.1 Intelligent Shoes for Human-Computer Interface:Shoe-Mouse.

5.3.2 Intelligent Shoes for Pressure Measurement.

5.3.3 Intelligent Shoes for Human Identification.

5.4 Conclusion.

6. Finger-Tip Human-Computer Interface.

6.1 Introduction.

6.2 Hardware Design.

6.2.1 MEMS Accelerator for Motion Detection.

6.2.2 Signal Processing and Analysis.

6.2.3 RF Wireless System.

6.2.4 System Evaluation.

6.3 Specific Applications.

6.3.1 Human-Robotic-Hand Interaction Using MIDS.

6.3.2 Computer Mouse on a Finger Tip (MIDS-VM).

6.3.3 Computer Game Interaction Using MIDS.

6.3.4 MIDS for PDA Interaction (Embedded-MIDS: E-MIDS).

6.4 Conclusion.

7. Ubiquitous 3D Digital Writing Instrument.

7.1 Introduction.

7.2 Hardware Design.

7.3 Signal Processing and Analysis.

7.3.1 Kalman Filtering for MEMS Sensors.

7.4 Time Update Model.

7.4.1 Attitude Strapdown Theory for a Quaternion.

7.4.2 Error Model for Time Update.

7.5 Measurement Update Model.

7.6 Testing.

7.6.1 Simulation Test.

7.6.2 Experiment Test.

7.7 Writing Application based on Attitude EKF Compensation.

7.8 Experimental Results of Integrated System.

7.9 Conclusion.

8. Intelligent Mobile Human Airbag System.

8.1 Introduction.

8.2 Hardware Design.

8.2.1 µIMU System Design.

8.2.2 Mechanical Release Mechanism.

8.2.3 Minimization of Airbag Inflation Time.

8.2.4 The Punch Test for the Second Mechanism.

8.2.5 System Integration.

8.3 Support Vector Machine for Human Motion Determination.

8.3.1 Principal Component Analysis for Feature Generation.

8.3.2 Support Vector Machine Classifier.

8.4 Experimental Results.

8.4.1 Motion Detection Experiments and Database Forming.

8.4.2 SVM Training and Falling-Down Recognition.

8.5 Conclusion.

Topic Index.