Atrial Fibrillation Detection and ECG Classification based on CNN-BiLSTM

• DOI: 10.48550/arxiv.2011.06187
• Publication Date: 2020-01-01
• Authors: Jiacheng Wang; Weiheng Li
• Keywords: Signal Processing (eess.SP); FOS: Computer and information sciences; Computer Science - Machine Learning; 0202 electrical engineering, electronic engineering, information engineering; FOS: Electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Electrical Engineering and Systems Science - Signal Processing; Machine Learning (cs.LG)

It is challenging to visually detect heart disease from the electrocardiographic (ECG) signals. Implementing an automated ECG signal detection system can help diagnosis arrhythmia in order improve accuracy of diagnosis. In this paper, we proposed, implemented, and compared using two different frameworks combination convolutional neural network (CNN) long-short term memory (LSTM) for classifying normal sinus signals, atrial fibrillation, other noisy The dataset used MIT-BIT Arrhythmia Physionet. Our approach demonstrated that cascade deep learning has higher performance than concatenation them, achieving a weighted f1 score 0.82. experimental results have successfully validated CNN LSTM achieve satisfactory on discriminating