Detecting Swipe Errors on Touchscreens using Grip Modulation

摘要: We show that when users make errors on mobile devices they immediate and distinct physical responses can be observed with standard sensors. used three cognitive tasks (Flanker, Stroop SART) to induce from 20 participants. Using simple low-resolution capacitive touch sensors placed around a device the built-in accelerometer, we demonstrate predicted at low error rates micro-adjustments hand grip movement in period shortly after swiping touchscreen. Specifically, combining features derived obtain mean AUC of 0.96 (with false accept reject both below 10%). Our results provide strong latency evidence for mistakes. The ability detect user this way could valuable component future interaction systems, allowing interfaces it easier correct erroneous inputs.