Device-Free Daily Life (ADL) Recognition for Smart Home Healthcare using a low-cost (2D) Lidar
Device-free or off-body sensing methods such as Lidar can be used for location-related Activities during Daily Life (ADL) recognition without the need for the subject to carry less accurate on-body sensors and because some subjects may forget to carry them or maintain them to be operational (powered up), i.e., users can be device free and the method still works. Hence, this paper proposes an innovative method for recognizing daily activities using a state-of-art seq2seq Recurrent Neural Network (RNN) model to classify centimeter level accurate location data from a 360-degree rotating 2D Lidar device. We deployed and validated the system. The results indicate that our method can provide a centimeter-level localization accuracy of 88% when recognizing seventeen targeted location-related daily activities.