计算机科学 ›› 2020, Vol. 47 ›› Issue (7): 118-124.doi: 10.11896/jsjkx.190600161

• 计算机图形学&多媒体 • 上一篇    下一篇

基于堆叠式双向LSTM的心电图自动识别算法

王文刀, 王润泽, 魏鑫磊, 漆云亮, 马义德   

  1. 兰州大学信息科学与工程学院 兰州730000
  • 收稿日期:2019-06-26 出版日期:2020-07-15 发布日期:2020-07-16
  • 通讯作者: 马义德(mayide510510@qq.com)
  • 作者简介:897675693@qq.com
  • 基金资助:
    国家自然科学基金(61175012,60872109,60572011);甘肃省自然科学基金(18JR3RA288);中央高校基本科研业务费专项资金(lzujbky-2017-it72)

Automatic Recognition of ECG Based on Stacked Bidirectional LSTM

WANG Wen-dao, WANG Run-ze, WEI Xin-lei, QI Yun-liang, MA Yi-de   

  1. School of Information Science and Engineering,Lanzhou University,Lanzhou 730000,China
  • Received:2019-06-26 Online:2020-07-15 Published:2020-07-16
  • About author:WANG Wen-dao,born in 1995,postgraduate.His main research interests include in-depth study and processing of medical signals.
    MA Yi-de,born in 1963,Ph.D,professor,is a member of China Computer Federation.His main research interests include digital image processing,biomedical engineering and artificial neural network.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61175012,60872109,60572011),Natural Science Foundation of Gansu Province,China(18JR3RA288) and Fundamental Research Funds for the Central Universities of Ministry of Education of China (lzujbky-2017-it72)

摘要: 针对日趋增长的心电图数据分析需求,提出了一种新的心电图分类算法。首先对原始数据进行截断固定长度、样本均衡、求取信号的瞬时频率和光谱熵等预处理操作,数据经过预处理后模型能够更好地从其中提取特征进行学习;在训练过程中采用两个双向LSTM(BILSIM)网络堆叠组成的模型,堆叠式的双向LSTM(BILSIM)模型是一种改进的循环神经网络模型,相较于卷积神经网络,循环神经网络更加适合用来处理像心电图这样的序列数据。该模型在Windows下的MATLAB2018b上进行训练和测试,CUDA版本为9.0,采用分类准确率作为衡量模型性能的指标在两个数据集上进行了测试,一个是2017年生理信号挑战赛的数据(下文简称2017数据集),该模型在此数据集上最终分类准确率为97.4%;另一个是2018年生理信号挑战赛的数据(下文简称2018数据集),最终的分类准确率为77.6%,并在所属的MATLAB组获得了第三名的成绩。该算法与传统LSTM网络的结果相比,在2017数据集上提升了5.6%的准确率,在2018数据集上提升了7.6%的准确率;与单层的双向LSTM网络的结果相比,在2017数据集上提升了4.2%的准确率,在2018数据集上提升了5.7%的准确率,这充分验证了该算法的可行性和优势。

关键词: 堆叠式双向LSTM网络, 心律失常, 心电图分类, 深度学习

Abstract: For the growing demand of ECG data analysis,a new ECG classification algorithm is proposed.Firstly,the original data are truncated by fixed length,sample equilibrium is obtained,and the pre-processing operations such as instantaneous frequency and spectral entropy of the signal are obtained.After the data is preprocessed,the model can better extract features from the data for learning.In training progress,a two-way LSTM network stacking model is adopted.The stacked two-way LSTM model is an improved cyclic neural network model.Compared with convolutional neural networks,the cyclic neural network is more sui-table for processing sequence data such as electrocardiogram.The experiment is conducted using MATLAB2018b under Windows for training and testing.The CUDA version is 9.0.The classification accuracy rate is used as an indicator to measure the performance of the model.The model is tested on two data sets,one is the data of the 2017 Physiological Signal Challenge(hereinafter referred to as the 2017 dataset),the final classification accuracy rate is 97.4%;the other is the data of the 2018 Physiological Signal Challenge (hereinafter referred to as the 2018 dataset),and the final classification accuracy rate is 77.6% on this dataset.The MATLAB group to which it belongs has achieved the third place.This algorithm improves the accuracy of 5.6% in the 2017 dataset and 7.6% in the 2018 dataset compared to the results of the traditional LSTM network.Compared to the results of a single-layer bidirectional LSTM network,in the 2017 data set,the accuracy rate improves 4.2%,and the accuracy rate improves 5.7% in the 2018 data set,which fully verifies the feasibility and advantages of the algorithm.

Key words: Stacked bidirectional LSTM network, Arrhythmia, Electrocardiogram classification, Deep learning

中图分类号: 

  • TP274
[1] MEMBERS W G,MOZAFFARIAN D,BENJAMIN E J,et al.Executive Summary:Heart Disease and Stroke Statistics--2016 Update:A Report from the American Heart Association[J].Circulation,2016,127(1):143-152.
[2] 何方田.临床心电图详解与诊断[M].杭州:浙江大学出版社,2010.
[3] ENGIN M.ECG Beat Classification Using Neuro-Fuzzy Net-work[J].Pattern Recognition Letters,2004,25(15):1715-1722.
[4] YU S N,CHEN Y H.Electrocardiogram Beat ClassificationBased on Wavelet Transformation and Probabilistic Neural Network[J].Pattern Recognition Letters,2007,28(10):1142-1150.
[5] GRAVES A.Long Short-Term Memory[J].Neural Computation,1997,9(8):1735-1780.
[6] TEIJEIRO T,GARCIA C A,CASTRO D,et al.ArrhythmiaClassification from the Abductive Interpretation of Short Single-Lead ECG records[J/OL].http://www.cinc.org/archives/2017/pdf/166-054.pdf.
[7] 陈新.临床心律失常学[M].北京:人民卫生出版社,2009.
[8] LECUNY Y,BENGIO Y,HINTON G.Deep Learning[J].Nature,2015,521 (7553):365-436.
[9] MA Y H.Review of in-depth study [J].Reading Abstracts(Middle),2017,804(6):594-628.
[10] OUYANG K.Biomedical Signal Processing [J].Beijing Biomedi-cal Engineering,2006,445(9):655-720.
[11] JIN L P,DONG J.Deep Learning Algorithms for Clinical ECG Analysis [J].Chinese Science:Information Science,2015,45(3):398-416.
[12] LIPTON Z C,KALE D C,ELKAN C,et al.Learning to Diagnose with Lstm Recurrent Neural Networks[J].ComputerScie-nce,2015,123(4):223-268.
[13] ZIHLMANN M,PEREKRESTENKO D,TSCHANNEN M.Convolutional Recurrent Neural Networks for Electrocardiogram Classification[J].Computer Science,2017,57(12):148-205.
[14] RAJPURKAR P,HANNUN A Y,HAGHPANAHI M,et al.Cardiologist - level Arrhythmia Detection with Convolutional Neural Networks [J].Computer Science,2017,225(5):308-374.
[15] GRAVES A,SCHMIDHUBER J.Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures[J].Neural Networks,2005,18(5/6):602-610.
[16] PRAKASH A,HASAN S A,LEE K,et al.Neural Paraphrase Generation with Stacked Residual Lstm Networks[J].2016,65(8):439-512.
[17] GRAVES A.Supervised Sequence Labelling with RecurrentNeural Networks[J].Studies in Computational Intelligence,2008,552(35):385-443.
[18] DONGHYUN.Long Short-Term Memory Recurrent NeuralNetwork - based Acoustic Model Using Connectionist Temporal Classification on a Large-scale Training Corpus[J].China Communications,2017,14(9):23-31.
[19] MIKOLOV T,ZWEIG G.Context Dependent Recurrent Neural Network Language Model[C]//Spoken Language Technology Workshop.2013.
[20] GRAVES A,MOHAMED A R,HINTON G.Speech Recognition with Deep Recurrent Neural Networks[C]//2013 IEEE International Conference on Acoustics,Speech and Signal Proces-sing.IEEE,2013.
[21] YUANFANG R,CHONG T,FEI L I,et al.Relation Classification Via Sequence Features and Bi-directional LSTMs[J].Wuhan University Journal of Natural Sciences,2017,22(6):489-497.
[22] SENNRICH R,HADDOW B,BIRCH A.Neural MachineTranslation of Rare Words with Subword Units[J].Computer Science,2015,27(5):224-245.
[23] PONS J,LIDY T,SERRA X.Experimenting with MusicallyMotivated Convolutional Neural Networks[C]//2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI).IEEE,2016.
[24] WANG D L.Deep Learning Reinvents the Hearing Aid[J].IEEE Spectrum,2017,54(3):32-37.
[25] GRAVES A.Supervised Sequence Labelling with RecurrentNeural Networks[J].Studies in Computational Intelligence,2008,385(6):57-128.
[26] SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:A Simple Way to Prevent Neural Networks from Overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.
[27] MULVEY J M,RUSZCZYNSKI A.A New Scenario Decompo-sition Method for Large-scale Stochastic Optimization[J].Opera-tions Research,1995,43(3):477-490.
[28] HE K,ZHANG X,REN S,et al.Delving Deep Into Rectifiers:Surpassing Human-level Performance on Imagenet Classification[J].Computer Science,2015,246(12):450-480.
[29] TOWNSEND J T.Theoretical Analysis of an Alphabetic Confusion Matrix[J].Perception & Psychophysics,1971,9(1):40-50.
[1] 王瑞平, 贾真, 刘畅, 陈泽威, 李天瑞. 基于DeepFM的深度兴趣因子分解机网络[J]. 计算机科学, 2021, 48(1): 226-232.
[2] 于文家, 丁世飞. 基于自注意力机制的条件生成对抗网络[J]. 计算机科学, 2021, 48(1): 241-246.
[3] 仝鑫, 王斌君, 王润正, 潘孝勤. 面向自然语言处理的深度学习对抗样本综述[J]. 计算机科学, 2021, 48(1): 258-267.
[4] 丁钰, 魏浩, 潘志松, 刘鑫. 网络表示学习算法综述[J]. 计算机科学, 2020, 47(9): 52-59.
[5] 何鑫, 许娟, 金莹莹. 行为关联网络:完整的变化行为建模[J]. 计算机科学, 2020, 47(9): 123-128.
[6] 叶亚男, 迟静, 于志平, 战玉丽, 张彩明. 基于改进CycleGan模型和区域分割的表情动画合成[J]. 计算机科学, 2020, 47(9): 142-149.
[7] 邓良, 许庚林, 李梦杰, 陈章进. 基于深度学习与多哈希相似度加权实现快速人脸识别[J]. 计算机科学, 2020, 47(9): 163-168.
[8] 暴雨轩, 芦天亮, 杜彦辉. 深度伪造视频检测技术综述[J]. 计算机科学, 2020, 47(9): 283-292.
[9] 袁野, 和晓歌, 朱定坤, 王富利, 谢浩然, 汪俊, 魏明强, 郭延文. 视觉图像显著性检测综述[J]. 计算机科学, 2020, 47(7): 84-91.
[10] 刘燕, 温静. 基于注意力机制的复杂场景文本检测[J]. 计算机科学, 2020, 47(7): 135-140.
[11] 张志扬, 张凤荔, 谭琪, 王瑞锦. 基于深度学习的信息级联预测方法综述[J]. 计算机科学, 2020, 47(7): 141-153.
[12] 蒋文斌, 符智, 彭晶, 祝简. 一种基于4Bit编码的深度学习梯度压缩算法[J]. 计算机科学, 2020, 47(7): 220-226.
[13] 陈晋音, 张敦杰, 林翔, 徐晓东, 朱子凌. 基于影响力最大化策略的抑制虚假消息传播的方法[J]. 计算机科学, 2020, 47(6A): 17-23.
[14] 程哲, 白茜, 张浩, 王世普, 梁宇. 使用深层卷积神经网络提高Hi-C 数据分辨率[J]. 计算机科学, 2020, 47(6A): 70-74.
[15] 赫磊, 邵展鹏, 张剑华, 周小龙. 基于深度学习的行为识别算法综述[J]. 计算机科学, 2020, 47(6A): 139-147.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .