Author(s): Ploetz T, Hammerla N, Rozga A, Reavis A, Call N, Abowd G
Abstract: Severe behavior problems of children with developmental disabilities often require intervention by specialists. These specialists rely on direct observation of the behavior, usu- ally in a controlled clinical environment. In this paper, we present a technique for using on-body accelerometers to as- sist in automated classification of problem behavior during such direct observation. Using simulated data of episodes of severe behavior acted out by trained specialists, we demon- strate how machine learning techniques can be used to seg- ment relevant behavioral episodes from a continuous sensor stream and to classify them into distinct categories of se- vere behavior (aggression, disruption, and self-injury). We further validate our approach by demonstrating it produces no false positives when applied to a publically accessible dataset of activities of daily living. Finally, we show promis- ing classification results when our sensing and analysis sys- tem is applied to data from a real assessment session con- ducted with a child exhibiting problem behaviors.
|
Dr Thomas Ploetz
|
|