Inferring Micro-Activities Using Wearable Sensing for ADL Recognition of Home-Care Patients

In this study, we propose a novel, context-based, location-aware algorithm for identifying low-level micro-activities that can be used to derive complex activities of daily living (ADL) performed by home-care patients. This identification is achieved by gathering the location information of the target user by using a wearable beacon embedded with a magnetometer and inertial sensors. The shortcomings of beacon-signal stability and mismatch issues in magnetic-field sequences are overcome by adopting a hybrid, three-phase approach for deducing the locus of micro-activities and their associated zones in a smart home environment. The suggested approach is assessed in two different test environments, where the main intention is to map the location of a person performing an activity with pre-defined house landmarks and zones in the offline labeled database. In addition to the recognition of low-level activities, the proposed method also identifies the person's walking trajectory within the same zone or between different zones of the house. The experimental results demonstrate that it is possible to achieve centimeter-level accuracy for the recognition of micro-activities and to achieve the classification accuracy of 85% for trajectory prediction. These results are encouraging and imply that the collection of accurate low-level information for ADL recognition is possible using integration of inertial sensors, magnetic field and Bluetooth low energy (BLE) technologies from the wearable beacon without relying on other infrastructural sensors.