Anomaly detection from linguistic summaries

Linguistic summaries of sensor data have been shown to be valuable as a communication tool with health care providers in an eldercare environment. Additionally, we have developed a metric distance for our particular form of linguistic protoform summaries (LPS). This has allowed the creation of linguistic prototypes from clusters of summaries over some temporal range. Using that, we present a method for detecting anomalies, as observations considerably different from the linguistic prototypes in a moving temporal window. Two case studies from an eldercare environment demonstrate the utility of this approach.