Subject-Dependent Physical Activity Recognition Model Framework with a Semi-supervised Clustering Approach

Activity recognition systems have been found to bevery effective for tracking users´ activities in research areas like healthcare and assisted living. Wearable accelerometers that can help in classifying Physical Activities (PA) have been made available by MEMS technology. State-of-the-art PAclassification systems use threshold-based techniques and Machine Learning (ML) algorithms. Each PA may exhibitinter-subject and intra-subject variability which is a major drawback for threshold and machine learning based techniques. Due to lack of empirical data in order to train classifier for ML clustering algorithms, there is a need to develop a mechanism which requires less training data for PA clustering. This paper describes a novel personalized PArecognition model framework based on a semi-supervised clustering approach to avoid fixed threshold techniques and traditional clustering methods by using a single accelerometer. The proposed methodology requires limited amount of data to compute (initial) centroids for PA clusters and achieved an accuracy of about 93% on average, moreover it has the potential capability of recognizing subjects´ behavioral shifts and exceptional events, falls, etc.