Unobtrusive Monitoring to Detect Depression for Elderly with Chronic Illnesses

Mental health related disorders are common diseases, especially among the elder. Among the various mental health diseases, one potential threat to ageing-in-place is the risk of depression. In this paper, we propose a simple unobtrusive sensing system using passive infra-red motion sensors to monitor the activities of daily living of elderly, who are living alone. A feature extraction module comprising of three layers-states, events, and activities, and the corresponding algorithms are proposed to extract features. Four popular classification models-neural network, C4.5 decision tree, Bayesian network, and support vector machine are then applied to detect the severity of depression. We implement and test the algorithms on sensor data collected over three months from 20 elderly, each in different daily living conditions. Our evaluation shows that the proposed algorithms are effective in detecting both normal condition and mild depression with up to 96% accuracy, using neural network as the classification algorithm. The sensing system is non-intrusive and cost-effective, with the potential of use for long-term depression monitoring and detection of early symptoms of mental related disorders. This enables caregivers to provide timely interventions to elderly, who are at risk of depression.