Open AccessArrhythmia Disease Classification and Mobile Based System Design
Author(s) -
Soha Samir AbdElMoneem,
Hany Said,
Abeer A. Saad
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1447/1/012014
Subject(s) - oversampling , random forest , support vector machine , cardiac arrhythmia , heart rate variability , classifier (uml) , computer science , artificial intelligence , heart disease , pattern recognition (psychology) , medicine , heart rate , bandwidth (computing) , blood pressure , telecommunications , atrial fibrillation
Heart Rate Variability (HRV) is a measure of variation in the time interval between consecutive heart beats.HRV analysis is highly sensitive for risks linked with cardiovascular diseases which are main causes of death in Egypt and all over the Middle East. Early detection of cardiac arrhythmia diseases achieves effective treatment by making it easy to choose appropriate anti-arrhythmic drugs, also very important for improving arrhythmia therapy and preventing number of death in individuals. In this paper, an efficient cardiac arrhythmia detection algorithm is introduced. Different classifiers are deployed and examined on ECG signals. Various oversampling techniques are investigated to handle imbalanced dataset. The ensemble classifier; support vector machine and Random forest with random sampling show accuracy of 98.18 % in 0.145 sec which is the best accuracy among all other classifiers. In addition, this paper also proposes a mobile based system architecture integrated with the algorithm for diagnosis and classification of cardiac arrhythmia diseases. The proposed system can be easily used by patients to check their heart health remotely and easily.