Improving activity recognition using temporal coherence.

Assessment of daily physical activity using data from wearable sensors has recently become a prominent research area in the biomedical engineering field and a substantial application for pattern recognition. In this paper, we present an accelerometer-based activity recognition scheme on the basis of a hierarchical structured classifier. A first step consists of distinguishing static activities from dynamic ones in order to extract relevant features for each activity type. Next, a separate classifier is applied to detect more specific activities of the same type. On top of our activity recognition system, we introduce a novel approach to take into account the temporal coherence of activities. Inter-activity transition information is modeled by a directed graph Markov chain. Confidence measures in activity classes are then evaluated from conventional classifier's outputs and coupled with the graph to reinforce activity estimation. Accurate results and significant improvement of activity detection are obtained when applying our system for the recognition of 9 activities for 48 subjects.

Estimation of physical activity monitored during the day-to-day life by an autonomous wearable device (SVELTE project).

Physical activity (PA) and the energy expenditure it generates (PAEE) are increasingly shown to have impacts on everybody's health (e.g. development of chronic diseases) and to be key factors in maintaining the physical autonomy of elderlies. The SVELTE project objective was to develop an autonomous actimeter, easily wearable and with several days of autonomy, which could record a subject's physical activity during his/her daily life and estimate the associated energy expenditure. A few prototypes and dedicated algorithms were developed based on laboratory experiments. The identification of physical activity patterns algorithm shows good performances (79% of correct identification), based on a trial in semi-free-living conditions. The assessment of the PAEE computation algorithm is under validation based on a clinical trial.

Classification of periodic activities using the Wasserstein distance.

In this paper, we introduce a novel nonparametric classification technique based on the use of the Wasserstein distance. The proposed scheme is applied in a biomedical context for the analysis of recorded accelerometer data: the aim is to retrieve three types of periodic activities (walking, biking, and running) from a time-frequency representation of the data. The main interest of the use of the Wasserstein distance lies in the fact that it is less sensitive to the location of the frequency peaks than to the global structure of the frequency pattern, allowing us to detect activities almost independently of their speed or incline. Our system is tested on a 24-subject corpus: results show that the use of Wasserstein distance combined with some supervised learning techniques allows us to compare with some more complex classification systems.