Cardiovascular diseases are the leading cause of death in the devel- oped world. Preventing these deaths, require long term monitoring and manual inspection of ECG signals, which is a very time consum- ing process. Consequently, a wearable system that can automatically categorize beats is essential.Neuromorphic machines have been introduced relatively recently in the science community. The aim of these machines is to emulate the brain. Their low power design makes them an optimal choice for a low power wearable ECG classifier. As features are crucial in any machine learning system, this thesis aims at proposing an energy efficient feature extraction algorithm for ECG arrhythmia classification using neuromorphic machines.

Electrocardiogram (ECG) has been widely used in the clinical environment to diagnose heart diseases. It provides information about the patients’ heart electrical activities in the heartbeats. Usually, ECG is collected by electrodes placed on patients’ skin which record the electrical changes during the cardiac cycles, from cardiac muscle depolarization to repolarization. ECG signal mainly includes three consecutive entities: the P wave, QRS complex, and T wave as shown in the sample ECG beat. The P wave is a summation wave generated by the depolarization front representing atrial depolarization. The QRS complex is usually the central and obvious wave representing ventricular depolarization. According to heart diseases classification method introduced by Association for the Advancement of Medical Instrumentation (AAMI) in 1998 [1], [2], the heartbeats are labeled into four major classes, namely normal (N), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), and fusion (F).

With the ubiquity of wearable ECG devices such as the Apple Watch and Xiaomi’s Mi Bunny Smart Watch, the possibility of real-time heart disease detection is now made available. To enable this as an “always-on” feature requires low energy ECG classification. Apart from the ability to distinguish abnormal from normal heartbeats, as found in the Apple Watch, we believe that the ability to do more detailed classification should help with first-aid and medical responses.

Journal of Cardiac and Pulmonary Rehabilitation aims to disseminate knowledge and promote discussion through the publication of peer-reviewed, high quality research papers on all topics related to Cardiac and Pulmonary Rehabilitation. The Journal emphasizes high-level research and education. Original research articles, reviews, short communications, and letters to the editors in the fields of Cardiac and Pulmonary Rehabilitation are welcome. Every effort is made to have a speedy and critical peer-review process. Instruction to authors

Editorial Tracking System is an online submission and review system, where authors can submit manuscripts and track their progress. Reviewers can download manuscripts and submit their opinions. Editors can manage the whole submission/review/revise/publish process. Publishers can see what manuscripts are in the pipeline awaiting publication. E-mail is sent automatically to concerned persons when significant events occur.
 

Thanks and regards
Editorial Office
Cardiac and Pulmonary Rehabilitation