Publications
カンファレンス (国際) Servo-Gaussian Model to Predict Success Rates in Manual Tracking: Path Steering and Pursuit of 1D Moving Target
Shota Yamanaka, Hiroki Usuba (Meiji University), Haruki Takahashi (Meiji University), Homei Miyashita (Meiji University)
The ACM Symposium on User Interface Software and Technology (UIST 2020)
2020.10.20
Success rate prediction models have mainly focused on a single selection task.However, models for continuous movements are also important for interactive systems.We propose the Servo-Gaussian model to predict success rates in manual tracking tasks.Two studies were conducted to validate this model: one on path steering and the other on the pursuit of a 1D moving target.We hypothesized that (1) users' hand movements follow the servo-mechanism model, (2) submovement endpoints form a bivariate Gaussian distribution, thus enabling us to predict the success rate at which a submovement endpoint falls inside the tolerance, and (3) the success rate for a whole trial can be predicted if the number of submovements is known.Shuffle-split cross-validation with various sizes of training and test datasets showed R^2>0.92 and MAE<4.9% for steering and R^2>0.95 and MAE<6.5% for pursuit tasks.These results demonstrate that our proposed model delivers high prediction accuracy even for unknown (test) datasets.