A touch interface for soft data modeling in Bayesian estimation
Siddhartha S. Mehta, Michael McCourt, Emily A. Doucette, J. Willard Curtis · 2014
A novel approach for human-generated “soft information” modeling and Bayesian fusion using touch interface devices is presented. The human-generated soft information can be encoded using a combination of single, multiple, and overlapping strokes that represent arbitrary measurement likelihood functions which can be approximated using non-parametric density estimators. The proposed interface offers a flexible and natural medium to encode a large class of qualitatively distinct types of information for both positive and negative observations. The touch interface naturally provides robustness with respect to human variability in terms of psycho-physiological and environmental parameters without the need for offline training. An urban-target tracking example is provided to illustrate fusion of soft information (generated using the proposed soft sensor model) with measurements from traditional automated sensors.