Detecting Swipe Errors on Touchscreens using Grip Modulation
summary
Prototype phone with 20 back-of-device capacitive sensors plus the built-in accelerometer and a Random Forest classifier detects unintentional swipes from three cognitive tasks, reporting a mean AUC 0.96 and false accept/reject rates under 10% when combining grip and movement features. Data come from 20 participants performing simulated Flanker/STROOP/SART swipes, recorded on a Nokia N9 prototype, and errors become classifiable within 200 ms after feedback.
AI-written summary · about
chapters (10)
- 0:00Introduction to swipe errors
- 2:11Why detect swipe errors
- 4:21Hypothesis on grip modulation
- 6:06Experiment design and tasks
- 8:00Sensor data collection setup
- 9:03Feature extraction from sensors
- 10:30Machine learning for error detection
- 13:42Generalization across users and tasks
- 14:50Summary of findings
- 15:34Q&A session
related talks
16mUnderstanding Grip Shifts: How Form Factors Impact Hand Movements on Mobile Phones
06mScraTouch: Extending Interaction Technique Using Fingernail on Unmodified Capacitive Touch Surfaces
19mDesigning Multi-Touch Gestures Using the Space around the Smartwatch as Continuous Input Space
21mPorous Interfaces for Small Screen Multitasking using Finger Identification
24mFrom Touch To Code: Gestures and Beyond
19mBackHand: Sensing Hand Gestures via Back of the Hand
15mTip-Tap: Battery-free Discrete 2D Fingertip Input
18mEvaluating the Disruptiveness of Mobile Interactions: A Mixed-Method Approach