Abnormal behaviours identification for an elder's life activities using dissimilarity measurements

Abstract

Identifying abnormal behaviour is an important factor in activity recognition. The aim of this paper is to design a system able to detect the abnormal behaviours of daily activity living in an intelligent environment. We approach this by applying dissimilarity (distance) measures on data collected from a single inhabitant environment. The data are acquired from occupancy sensors such as a door and motion sensors. Since the data is collected from these sensors has a discrete value either on or off, only the binary dissimilarity measures are considered in this paper. There are several distance measurements which find the mismatching bits of two binary data sets. In this paper, two major dissimilarity measures, which include hamming distance and fuzzy hamming distance, are used and compared. These measures can help in distinguishing between normal and abnormal behaviour patterns in order to improve the quality of elderly people's lives. Two case studies where the inhabitants suffer from dementia are used to verify the accuracy of the results. The experimental results demonstrate that fuzzy hamming distance gives a smaller distance than classic hamming distance in the case of motion sensors over door sensors.