Ensemble Learning-Based Atrial Fibrillation Detection from Single Lead ECG Wave for Wireless Body Sensor Network

With the popularity of wireless techniques and portable devices, continuous and real-time monitoring patient's health status by collecting physiological signals is becoming more popular. Data mining of electrocardiograph (ECG) attracts widespread attention, where automatic atrial fibrillation (AF) detection has become a hot research field. In this paper, an ensemble learning algorithm is proposed for AF detection from single lead ECG recordings collected by wearable devices. This algorithm includes two modules. First, denoised 1-D time series (ECG), time-frequency spectrum and Poincare plot are used to train three component learners through a parallel style, respectively, and each component learner produces four probability values. Then, all the outputs are combined using a weighted matrix constructed by a Bayesian optimization algorithm, which is capable of producing the final classification result. Quantities of experiments have been implemented, and the results well prove the algorithm's effectiveness and its advantage over some state-of-the-art counterparts.