Discovering Daily Activity Patterns from Sensor Data Sequences and Activity Sequences.

Mirjam Sepesy Maučec,Gregor Donaj

doi:10.3390/s21206920

Abstract

The necessity of caring for elderly people is increasing. Great efforts are being made to enable the elderly population to remain independent for as long as possible. Technologies are being developed to monitor the daily activities of a person to detect their state. Approaches that recognize activities from simple environment sensors have been shown to perform well. It is also important to know the habits of a resident to distinguish between common and uncommon behavior. In this paper, we propose a novel approach to discover a person’s common daily routines. The approach consists of sequence comparison and a clustering method to obtain partitions of daily routines. Such partitions are the basis to detect unusual sequences of activities in a person’s day. Two types of partitions are examined. The first partition type is based on daily activity vectors, and the second type is based on sensor data. We show that daily activity vectors are needed to obtain reasonable results. We also show that partitions obtained with generalized Hamming distance for sequence comparison are better than partitions obtained with the Levenshtein distance. Experiments are performed with two publicly available datasets.

Highlights

The number and proportion of elderly people in the population are increasing
Smart home environments are environments that attempt to make the life of their residents more comfortable by using technology that monitors the residents’ activities
The alternative is sensor-based approaches, in which home environments are equipped with several sensors and smart devices

Summary

Introduction

The number and proportion of elderly people in the population are increasing. The cost of caring for the elderly in nursing homes is much higher than the cost of in-home care All these facts forced the fast development of new technologies that can help seniors to stay at home and remain independent for longer [1,2]. Monitoring can be performed using video cameras—these approaches are called vision-based approaches [3]. They are problematic with regard to the security and privacy concerns of the residents. The approaches differ based on sensor deployment, which can be wearable or environmental [4,5]. The major problem with wearable sensors is that wearing a tag is sometimes not feasible [6]

Objectives

Methods

Results

Conclusion