Impact of Measurement Duration on the Identification of Touchscreen Biodynamic Feedthrough Models

Abstract

Touchscreens are used increasingly in moving environments, where they can in fact be very difficult to use. A key issue is biodynamic feedthrough (BDFT): perturbing finger movements induced by feedthrough of motion accelerations (e.g., turbulence) through users' outstretched arms. Modeling the BDFT dynamics allows such erroneous components of touchscreen inputs to be computationally removed. Estimating accurate BDFT models using system identification methods traditionally requires experiments with prolonged measurement times. However, for touchscreen BDFT measurements, where participants generally keep their arms outstretched for the full measurement duration, long measurements lead to muscle fatigue, which impacts data quality. By means of a dedicated human-in-the-loop simulator experiment, this paper shows that reducing the measurement duration to around 30 s does not significantly affect participants BDFT dynamics, or our ability to model them. As a result, these experimental findings enable future investigations to use shorter measurement times to increase participant comfort without compromising BDFT model quality.