Bayesian Real-Time QRS Complex Detector for Healthcare System

An efficient algorithm for the heartbeat detection in the Internet of Things (IoT) health-care system remains a challenging issue due to incurred random variations. The QRS complex reflects the electrical activity within the heart during the ventricular contraction. Although recently many QRS complex detection methods have been proposed with different features, their real-time implementations in low-cost portable platforms are still problems due to limited hardware resources. As a result, it is difficult to provide the accuracy level required for medical applications. By contrast, this paper focuses on developing a new method based on the Bayesian framework to provide a realtime and accurate QRS complex detector. More specifically, we propose a new algorithm with two stages, i.e., variance-based detection (VBD) and maximum-likelihood estimation (MLE), to detect QRS complexes. Furthermore, simulations with the benchmark MIT-BIH arrhythmia and QT databases verify the advantage of being easily portable to different databases using the proposed approach.