Design and Efficient Implementation of Deep Learning Algorithm for ECG Classification

Please enable javascript in your browser.

Oveisi, Mohammad Hossein | 2017

576 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 50079 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Hashemi, Matin
Abstract:
Cardiovascular diseases are the leading cause of death globally so early diagnosis of them is important. Many researchers focused on this field. First signs of cardiac diseases appear in the electrocardiogram signal. This signal represents the electrical activity of the heart so it’s primarily used for the detection and classification of cardiac arrhythmias. Permanent monitoring of this signal is not possible for specialists so we should do this by means of Artificial Intelligence. In this thesis, we use recurrent neural networks to classify electrocardiogram’s arrhythmias. This deep learning method, use two sources of data to learn from. The first part of data is global for everyone and the second part is 5 minutes of the personal signal. This research shows that we can classify ventricular arrhythmias and atrial arrhythmias with 99.4% and 98.1% respectively. In order to implement this algorithm on a variety of gadgets from PCs to wearable health gadgets, we considered existing limitations in memory and processing power. So we can run this method at the real-time speed on all of them
Keywords:
Electrocardiogram ; Deep Learning ; Signal Classification ; Signal Classification ; Heart Diseases