Design and assessment of the data analysis process for a wrist-worn smart object to detect atomic activities in the smart home

Abstract

The ability to accurately identify the different activities of daily living (ADLs) is considered as one of the basis to foster new technological solutions inside the smart home. Current ADL recognition proposals, still however, struggle to accurately and robustly identify the range of different activities that can be performed at home, namely static, dynamic and transient activities, and the high variety of technologies and data analysis possibilities to classify the information gathered by the sensors. In this paper, we describe the methodological approach that we have followed for the processing, analysis and classification of data obtained by a simple and non-intrusive smart object with the objective to detect atomic (i.e. non-divisible) activities inside the smart home. The smart object consists of a wrist-worn 3D accelerometer, which presents as its advantages its customizability and usability. We have performed a set of systematic experiments involving ten people and have followed the steps from data gathering to the comparison of different classification techniques, to find out that it is possible to select a complete succession of data processing steps in order to detect, with high accuracy, a set of atomic activities of daily life with the selected smart object, which performs well with different independent datasets besides ours.

Human Activity Recognition Based on Deep Learning Techniques

“…In the literature, it is possible to find several HAR studies using on on-body sensors [5] or smartphones [6]. The later have become popular all over the world and provide numerous sensors such as accelerometers and gyroscopes that allow acquiring data from people who continuously carry those every day in a less invasive way.…”