Mining Life Styles from Wearable Sensors Data for Elderly Anomaly Detection

Abstract

Life patterns can represent an individual’s life style and they can help people understand what they do in a certain time as well as the regular habits The discovery of life patterns has a manifold of application scenarios which can be embedded into location-based recommender systems precise advertising computer-aided scheduling and care/alert systems In this thesis we propose an approach for life style mining with applications on elderly anomaly detection Although there are existing works for discovering life styles they are based on single sensor environment traditionally Consequently it cannot completely represent an individual’s lifestyle due to the lack of sufficient information and related applications like anomaly detection cannot reach high accuracy To deal with above-mentioned problems we mine an individual’s life pattern from wearable-devices-based environment with multiple kinds of sensors When we apply the life patterns to elderly anomaly detection multiple-sensors-based elderly’s conditions such as physical condition and locations are taken into considerations at the same time for anomaly detection Once an anomaly is detected it is further evaluated to distinguish whether the anomaly is urgent For experimental evaluations we design a data simulator to generate sensors data of elderly’s daily life based on which the effectiveness of our proposed framework is verified

Date of Award	2016 Jul 4
Original language	English
Supervisor	Sun-Yuan Hsieh (Supervisor)