Application of Convolutional Neural Network in Automatic Classification of Arrhythmia

摘要：

　　As a typical disease,heart disease seriously threatens human health,and its suddenness has hindered the diagnosis and treatment for the patients.Therefore,a fast and accurate real-time analysis method is useful to assist doctors in disease diagnosis.In this paper,we mainly design three different automatic classification algorithms to classify the heart beats of electroencephalography.The algorithm is mainly based on one-dimensional convolutional neural network(CNN),and the appropriate network structure is found by comparing the classification performance of different structural models.We also use the support vector machine(SVM)and stacking methods to improve the CNN network.The data used in this paper are all from the MIT-BIH Arrhythmia Database.We use the ten-core cross-validation method to classify the four types of heart beats.The results show that among the three types of algorithms,the stacking algorithm works best and the classification accuracy is as high as 99.1%.

关键词： Convolutional neural network electroencephalography support vector machine stacking algorithm

作者: Jian Liu Mingxuan Fu Shasha Zhang

作者单位: University of Science and Technology Beijing Haidian Qu,Beijing,China School of Software,Beijing University of Posts and Telecommunications Beijing 100876,China

会议类型: 国际会议

会议名称: 2019国图灵大会(ACM Turing Celebration conference-China 2019 )

会议地点: 成都

会议语种:英文

页码: 785-792

在线出版日期: 2019-05-17（万方平台首次上网日期，不代表论文的发表时间）