基于深度长短时记忆神经网络模型的心律失常检测算法
|
摘要
针对传统基于形态特征的心电检测算法存在特征提取不准确和高复杂性等问题,提出了一种多层的长短时记忆(LSTM)神经网络结构。结合传统LSTM模型在时序数据处理上的优势,该模型增加了反向和深度计算,避免了人工提取波形特征,提高了网络的学习能力。通过给定心拍序列和分类标签进行监督学习,然后实现对未知心拍的心律失常检测。通过对MIT-BIH数据库中的心律失常数据集进行实验验证,模型的总体准确率为98.34%。相比支持向量机(SVM),该模型的准确率和F1值均有提高。
Aiming at the problems of inaccurate feature extraction and high complexity of traditional ElectroCardioGram(ECG) detection algorithms based on morphological features, an improved Long Short-Term Memory(LSTM) neural network was proposed. Based on the advantage of traditional LSTM model in time series data processing, the proposed model added reverse and depth calculations which avoids extraction of waveform features artificially and strengthens learning ability of the network. And supervised learning was performed in the model according to the given heart beat sequences and category labels, realizing the arrhythmia detection of unknown heart beats. The experimental results on the arrhythmia datasets in MIT-BIH database show that the overall accuracy of the proposed method reaches 98.34%. Compared with support vector machine, the accuracy and F1 value of the model are both improved.
Aiming at the problems of inaccurate feature extraction and high complexity of traditional ElectroCardioGram(ECG) detection algorithms based on morphological features, an improved Long Short-Term Memory(LSTM) neural network was proposed. Based on the advantage of traditional LSTM model in time series data processing, the proposed model added reverse and depth calculations which avoids extraction of waveform features artificially and strengthens learning ability of the network. And supervised learning was performed in the model according to the given heart beat sequences and category labels, realizing the arrhythmia detection of unknown heart beats. The experimental results on the arrhythmia datasets in MIT-BIH database show that the overall accuracy of the proposed method reaches 98.34%. Compared with support vector machine, the accuracy and F1 value of the model are both improved.
引文
[1] ELHAJ F A, SALIM N, HARRIS A R, et al. Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals [J]. Computer Methods and Programs in Biomedicine, 2016, 127(C): 52-63.
[2] YASMEEN F, MALLICK M A, KHAN Y U. A review on analysis of electrocardiogram signal (MIT-BIH arrhythmia database) [J]. International Journal of Electronics, Electrical and Computational System, 2017, 6(9): 588-591.
[3] CHANG K M. Arrhythmia ECG noise reduction by ensemble empirical mode decomposition [J]. Sensors, 2010, 10(6): 6063-6080.
[4] SAVITHA R V, BREESHA S R, JOSEPH X F. Preprocessing the abdominal ECG signal using combination of FIR filter and principal component analysis [C]// ICCPCT 2015: Proceedings of the 2015 International Conference on Circuit, Power and Computing Technologies. Piscataway, NJ: IEEE, 2015: 1-4.
[5] ALFAOURI M, DAQROUQ K. ECG signal denoising by wavelet transform thresholding [J]. American Journal of Applied Sciences, 2008, 5(3): 276-281.
[6] KORüREK M, NIZAM A. Clustering MIT-BIH arrhythmias with ant colony optimization using time domain and PCA compressed wavelet coefficients [J]. Digital Signal Processing, 2010, 20(4): 1050-1060.
[7] RAJPURKAR P, HANNUN AY, HAGHPANAHI M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks [EB/OL]. [2017- 07- 06]. https://arxiv.org/abs/1707.01836.
[8] MOODY G B, MARK R G. The impact of the MIT-BIH arrhythmia database [J]. IEEE Engineering in Medicine and Biology Magazine, 2002, 20(3): 45-50.
[9] 叶裕雷,戴文战.一种基于新阈值函数的小波信号去噪方法[J].计算机应用,2006,26(7):1617-1619.(YE Y L, DAI W Z. Signal de-noising in wavelet based on new threshold function [J]. Journal of Computer Applications, 2006, 26(7): 1617-1619.)
[10] SAINI I, SINGH D, KHOSLA A. QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases [J]. Journal of Advanced Research, 2013, 4(4): 331-344.
[11] 褚晶辉,卢莉莉,吕卫,等.循环谱分析在心律失常分类中的应用研究[J].计算机科学与探索,2017,11(11):1783-1791.(CHU J H, LU L L, LYU W, et al. ECG arrhythmias classification with cyclic spectral analysis [J]. Journal of Frontiers of Computer Science and Technology, 2017, 11(11): 1783-1791.)
[12] 滕飞,郑超美,李文.基于长短期记忆多维主题情感倾向性分析模型[J].计算机应用,2016,36(8):2252-2256.(TENG F, ZHENG C M, LI W. Multidimensional topic model for oriented sentiment analysis based on long short-term memory [J]. Journal of Computer Applications, 2016, 36(8): 2252-2256.)
[13] SCHMIDHUBER J. Deep learning in neural networks: an overview [J]. Neural Networks, 2015, 61: 85-117.
[14] SALLOUM R, KUO C J. ECG-based biometrics using recurrent neural networks [C]// ICASSP 2017: Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2017: 2062-2066.
[15] QU X, JIAN C W, FEI G D. ECG signal classification based on BPNN [C]// ICEICE 2011: Proceedings of the International Conference on Electric Information and Control Engineering. Piscataway, NJ: IEEE, 2011: 1362-1364.
[16] ACHARYA U R, OH S L, HAGIWARA Y, et al. A deep convolutional neural network model to classify heartbeats [J]. Computers in Biology and Medicine, 2017, 89: 389-396.
[17] KARPAGACHELVI D S. Classification of ECG signals using particle swarm optimization and extreme learning machine [J]. International Journal of Engineering Sciences and Research Technology, 2014, 3(7): 95-102.YANG Shuo, born in 1993, M. S. candidate. His research interests include signal processing, machine learning.PU Baoming, born in 1966, M. S., research fellow. His research interests include signal processing, artificial intelligence. LI Xiangze, born in 1981, Ph. D. candidate, lecturer. His research interests include signal processing.WANG Shuai, born in 1990, Ph. D. candidate. His research interests include computer vision, machine learning, signal processing.CHANG Zhanguo, born in 1992, M. S. candidate. His research interests include machine learning, artificial intelligence.
[2] YASMEEN F, MALLICK M A, KHAN Y U. A review on analysis of electrocardiogram signal (MIT-BIH arrhythmia database) [J]. International Journal of Electronics, Electrical and Computational System, 2017, 6(9): 588-591.
[3] CHANG K M. Arrhythmia ECG noise reduction by ensemble empirical mode decomposition [J]. Sensors, 2010, 10(6): 6063-6080.
[4] SAVITHA R V, BREESHA S R, JOSEPH X F. Preprocessing the abdominal ECG signal using combination of FIR filter and principal component analysis [C]// ICCPCT 2015: Proceedings of the 2015 International Conference on Circuit, Power and Computing Technologies. Piscataway, NJ: IEEE, 2015: 1-4.
[5] ALFAOURI M, DAQROUQ K. ECG signal denoising by wavelet transform thresholding [J]. American Journal of Applied Sciences, 2008, 5(3): 276-281.
[6] KORüREK M, NIZAM A. Clustering MIT-BIH arrhythmias with ant colony optimization using time domain and PCA compressed wavelet coefficients [J]. Digital Signal Processing, 2010, 20(4): 1050-1060.
[7] RAJPURKAR P, HANNUN AY, HAGHPANAHI M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks [EB/OL]. [2017- 07- 06]. https://arxiv.org/abs/1707.01836.
[8] MOODY G B, MARK R G. The impact of the MIT-BIH arrhythmia database [J]. IEEE Engineering in Medicine and Biology Magazine, 2002, 20(3): 45-50.
[9] 叶裕雷,戴文战.一种基于新阈值函数的小波信号去噪方法[J].计算机应用,2006,26(7):1617-1619.(YE Y L, DAI W Z. Signal de-noising in wavelet based on new threshold function [J]. Journal of Computer Applications, 2006, 26(7): 1617-1619.)
[10] SAINI I, SINGH D, KHOSLA A. QRS detection using K-Nearest Neighbor algorithm (KNN) and evaluation on standard ECG databases [J]. Journal of Advanced Research, 2013, 4(4): 331-344.
[11] 褚晶辉,卢莉莉,吕卫,等.循环谱分析在心律失常分类中的应用研究[J].计算机科学与探索,2017,11(11):1783-1791.(CHU J H, LU L L, LYU W, et al. ECG arrhythmias classification with cyclic spectral analysis [J]. Journal of Frontiers of Computer Science and Technology, 2017, 11(11): 1783-1791.)
[12] 滕飞,郑超美,李文.基于长短期记忆多维主题情感倾向性分析模型[J].计算机应用,2016,36(8):2252-2256.(TENG F, ZHENG C M, LI W. Multidimensional topic model for oriented sentiment analysis based on long short-term memory [J]. Journal of Computer Applications, 2016, 36(8): 2252-2256.)
[13] SCHMIDHUBER J. Deep learning in neural networks: an overview [J]. Neural Networks, 2015, 61: 85-117.
[14] SALLOUM R, KUO C J. ECG-based biometrics using recurrent neural networks [C]// ICASSP 2017: Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ: IEEE, 2017: 2062-2066.
[15] QU X, JIAN C W, FEI G D. ECG signal classification based on BPNN [C]// ICEICE 2011: Proceedings of the International Conference on Electric Information and Control Engineering. Piscataway, NJ: IEEE, 2011: 1362-1364.
[16] ACHARYA U R, OH S L, HAGIWARA Y, et al. A deep convolutional neural network model to classify heartbeats [J]. Computers in Biology and Medicine, 2017, 89: 389-396.
[17] KARPAGACHELVI D S. Classification of ECG signals using particle swarm optimization and extreme learning machine [J]. International Journal of Engineering Sciences and Research Technology, 2014, 3(7): 95-102.YANG Shuo, born in 1993, M. S. candidate. His research interests include signal processing, machine learning.PU Baoming, born in 1966, M. S., research fellow. His research interests include signal processing, artificial intelligence. LI Xiangze, born in 1981, Ph. D. candidate, lecturer. His research interests include signal processing.WANG Shuai, born in 1990, Ph. D. candidate. His research interests include computer vision, machine learning, signal processing.CHANG Zhanguo, born in 1992, M. S. candidate. His research interests include machine learning, artificial intelligence.