Research On Arrhythmia Detection Based On Neural Networks

Heart arrhythmia is a common cardiovascular disease,which easily causes many complications and poses a great threat to human health.Clinically,the diagnosis of arrhythmia diseases mainly relies on doctors’ observation of electrocardiogram,which undoubtedly increases the workload of doctors.Therefore,there is a need for a reliable and accurate method for automatic detection of arrhythmia,so as to realize early detection and early treatment of the disease and avoid serious consequences caused by the aggravation of the disease.Deep learning has developed rapidly in recent years and has shown excellent performance in many fields.In this context,this paper proposes an automatic detection method for arrhythmia based on deep learning.The method uses Convolutional Neural Network and Bi-directional Long and Short-term Memory Network to build a deep neural network model which called CNN-Bi LSTM.The paper researches deeply on the recognition of arrhythmia signals by CNN-Bi LSTM.The main research content includes three aspects:(1)The related knowledge of electrocardiogram and the clinical features of some arrhythmia diseases are introduced.Extract raw data from the MIT-BIH arrhythmia database and preprocess it.(2)On the basis of the current research status,a deep neural network model based on convolutional neural network and bidirectional long and short-term memory network is proposed to identify arrhythmia signals.The network can autonomously mine and learn the deep-level features of ECG signals,and has better feature extraction capabilities and generalization capabilities.(3)This study uses overall accuracy,precision,specificity and sensitivity to evaluate the experimental results.The experiments have proved that the deep neural network model we proposed can significantly improve the accuracy and has an ideal ability to recognize electrocardiogram samples with arrhythmia.In summary,the CNN-Bi LSTM network model proposed in this paper can be used for the identification and classification of arrhythmia signals.This method can be used as an auxiliary tool for clinical diagnosis and has high practical significance in practical applications.