Transcript CHI2005_EMG
Toward Subtle Intimate Interfaces for Mobile Devices Using an EMG Controller Enrico Costanza Media Lab Europe now at MIT Media Lab Samuel A. Inverso Media Lab Europe Rebecca Allen Media Lab Europe Outline • Motivation: Subtle and hands-free interaction • EMG as a solution • An EMG-based controller • Design approach • Formal user study • Conclusion Importance of Subtlety in Mobile Interfaces • Mobile interaction is often in public spaces • Subtle interfaces: do not disrupt the environment • Intimate interaction: only for the user • Ringing vs. vibrating alert Importance of Subtlety in Mobile Interfaces • Speech recognition and evident gesturing can be inappropriate Design for Hands-free Interaction Design for Hands-free Interaction Eyeglass displays Electromyogram (EMG) as a Novel Solution • Electrical signal from muscle activity • Can measure isometric activity: subtle or no movement • Surface Electrodes (EKG-like) • Non-contact sensing (future) EMG in CHI (Related Work) • Prosthesis control • Input devices for disabled users • Affect sensing • Music expression EMG and Movement Limitation or Advantage? • EMG and movement are not always related • Tanaka & Knapp report this as a limitation • We think it is an advantage! Motionless Gestures • EMG greatest potential for mobile HCI • Sense subtle gestures • Example: brief contraction of the bicep EMG-based Controller • Self-contained in armband • Integration with Bluetooth devices (e.g. Phones and PDAs) • No calibration for individual users Design Process The gesture should be: • Natural to perform • Different from normal muscle activity User centered iterative approach: 1. Select muscle & generic gesture definition (non-detailed description to subjects) 2. Definition refinement, model and algorithm 3. Tuning Formal User Study • Realistic controlled environment: subjects walked around obstacles in trafficked walkway • 10 subjects • Audio stimuli and feedback • Is training avoidable? (minimal feedback) • Push the limit: short and long contractions Results • 96% correct recognition • No false positives • No training necessary in 7 out of 10 cases • Cannot distinguish short and long contractions across different subjects Discussion • EMG can be successfully used (96%) • Generally no training required • No calibration across users Discussion • Cannot distinguish short and long contractions • Subjective definition of “short” and “long” Future Work • Test in more complex scenarios • Measure subtleness • Improve algorithm • Use more muscles (alphabet definition) Summary and Conclusion • Subtle interaction for mobile devices • New reason to use EMG in CHI • Motionless gestures • It works (96% correct recognition no false positives)