People are subjected to a multitude of interruptions. In order to manage these interruptions it is imperative to predict a person's interruptability – his/her current readiness or inclination to be interrupted. This paper aims to introduce the approach of direct interruptability inference from sensor streams (accelerometer and audio data) in a ubiquitous computing setup and to show that it provides highly accurate and robust predictions.
The authors argue that scenarios are central for evaluating the performance of ubiquitous computing devices (and interruptability predicting devices in particular) and prove this on the setup employed, which was based on that of Kern and Schiele.
The paper demonstrates that scenarios provide the foundation for avoiding misleading results, and provide the basis for a stratified scenario‐based learning model, which greatly speeds up the training of such devices.
The direct prediction seems to be competitive or even superior to indirect prediction methods and no drawbacks have been observed yet.
The paper introduces a method for accurately predicting a person's interruptability directly from simple sensors without any intermediate steps/symbols.
