Increased Robustness in Context Detection and Reasoning using Uncertainty Measures - Concept and Application

In this paper we report on a novel recurrent fuzzy classification method for robust detection of context activities in an environment using either single or distributed sensors. The proposed method utilizes uncertainty measures for improvement of detection, fusion and aggregation of context knowledge. To calculate the uncertainty measure we propose the use of simple and recurrent fuzzy systems. We applied the method in a real application to recognize various applause (and non applause) situations, e.g. during a conference. Measurements were taken from mobile phone sensors (microphone, acceleration if available) and acceleration sensory attached to a board marker. We show that we are able to improve robustness of detection using our novel uncertainty measures by ~30% on average. We also show that the use of multiple phones and distributed recognition in most cases allows to achieve a recognition rate between 90% and 100%.