On-body wearable device localization with a fast and memory efficient SVM-kNN using GPUs

Abstract

Abstract Biomedical and inertial sensors can be used to generate a complete view of complicated physiological changes in a continuous, real-time, and non-invasive manner. As inappropriate on-body attachments may result in errors, the localization information requires calibration. In most previous studies of on-body wearable device localization, the run-time performance was not evaluated in terms of execution time and memory usage. Recently, smartphones have been used as data processing centers and recognition systems for wearable devices. However, the hardware disadvantages of phone devices have a negative effect on both real-time response and system accuracy. In this study, we focus on a high-performance localization system for the mobile environment and propose a memory efficient algorithm that is accelerated by using graphics processing units (GPUs). The algorithm combines a k-nearest neighbor classifier with a support vector machine (SVM)-based decision-maker to refine the classification outcome. This contributes to a faster and more accurate on-body localization for wearable devices. Experiment results demonstrated that the proposed method achieves an accuracy of 92.94%% and is faster than Serial-SVM and GPU-SVM by a factor of 6.81×and 3.87×, respectively. Therefore, the proposed technique can offer a comparable accuracy to SVM-based methods with faster recognition in the mobile environment.