Loading...

Implementation of Deep Machine Learning Algorithm for Cardiac Arrhythmias Detection and Study of the Motion Artifact Effect on Electrode-skin Impedance

Khodami, Farnaz | 2021

333 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54388 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Fotowat Ahmady, Ali; Sarvari, Reza; Hossein Khalaj, Babak
  7. Abstract:
  8. In recent years, machine learning methods have been widely used in various applications. In particular, using machine learning techniques in the healthcare area has had significant benefits for both physicians and patients. Since we live in the big data era, and at any given moment we leave a lot of information on websites, mobile phones, etc., deep learning methods are more important than ever.One of the most important applications of machine learning in medicine area is assisting cardiologists for cardiac arrhythmias detection. Some of these arrhythmias may only occur once a week, so a portable ECG recorder should be placed on the chest of people to record their electrocardiogram signal. It is very time consuming for the cardiologist to analyze this amount of data.In this research, we first preprocessed cardiac signals and corrected or eliminated adverse effects such as noise and loss. After preprocessing the cardiac signals, by using deterministic algorithms and machine learning concepts, we were able to identify 5 categories of cardiac arrhythmias with more than 92% accuracy. Due to the limited data volume, we used computational methods to diagnose some arrhythmias such as tachycardia and bradycardia, but other arrhythmias were identified using machine learning methods. In order to identify occurrence of motion artifacts, which are part of the destructive signals of the ECG, an electrical circuit was proposed and we were able to prove the effect of this destructive signal on the electrode-skin impedance during various movements
  9. Keywords:
  10. Cardiac Arrhythmia ; Motion Artifacts ; Deep Learning ; Neural Networks ; Electrode-Tissue Impedance ; Portable ECG Recorder ; Deterministic Algorithms

 Digital Object List

 Bookmark

No TOC