Activity recognition using a hierarchical model

Abstract

Abstract-In this paper, we propose a human daily activity recognition method that is used for Ambient Assisted Living. The proposed system is able to learn a user's activities using the data from motion and door sensors. We extract low level features from the sensor data and feed the features to a model that combines support vector machines (SVMs) and conditional random fields (CRFs) to give accurate recognition results. We propose to combine SVM and CRF classifiers in a hierarchical model which results in better accuracies and can also make use of high level features. We conducted experiments and presented the effectiveness and accuracies of the proposed method.

Monitoring Daily Routine Anomalies in Assisted Living Environments

“…The increasing costs of our health care and social systems due to the changing population age structure in the western world pose a serious threat to our way of living [3]. One way to oppose these issues are domestic living environments with activity recognition [18,19]. These systems monitor environments and user activities, which allows, for example, the elderly to stay at their homes for as long as possible.…”

“…One type of such systems features domestic living environments with activity recognition [18,19]. These systems monitor surrounding environments and user activities in order to ensure that the elderly are living safely and independently in their own homes.…”