Advanced Search
Volume 43 Issue 10
Oct.  2021
Turn off MathJax
Article Contents
Shuying YANG, Binbin GUI, Shengyong CHEN. Arrhythmia Detection Based on Wavelet Decomposition and 1D-GoogLeNet[J]. Journal of Electronics & Information Technology, 2021, 43(10): 3018-3027. doi: 10.11999/JEIT200774
Citation: Shuying YANG, Binbin GUI, Shengyong CHEN. Arrhythmia Detection Based on Wavelet Decomposition and 1D-GoogLeNet[J]. Journal of Electronics & Information Technology, 2021, 43(10): 3018-3027. doi: 10.11999/JEIT200774

Arrhythmia Detection Based on Wavelet Decomposition and 1D-GoogLeNet

doi: 10.11999/JEIT200774
Funds:  The National Natural Science Foundation of China(U1509207), Tianjin Virtual Simulation Experiment Teaching Construction Project Fund(JMEC[2019]69)
  • Received Date: 2020-08-31
  • Rev Recd Date: 2021-03-23
  • Available Online: 2021-04-14
  • Publish Date: 2021-10-18
  • The accurate classification of ElectroCardioGram (ECG) signals is essential for the automatic diagnosis of heart disease. In order to realize the intelligent classification of arrhythmia, an accurate classification method based on wavelet decomposition and 1D-GoogLeNet is proposed. In this method, Db6 wavelet is used to decompose the ECG signal in eight levels to obtain multi-dimensional data containing both time domain information and frequency domain information. Subsequently, Decomposed samples are used as input to 1D-GoogLeNet to train the model. In the proposed 1D-GoogLeNet model, using Inception's excellent performance in image feature extraction, the two-dimensional convolution is transformed into one-dimensional convolution to learn the features of ECG, and the structure of each Inception is simplified, and the model parameters are reduced. The deep learning classifier proposed in this paper can effectively alleviate the problems of low computational efficiency, difficulty in convergence and model degradation. In the experiment, the MIT-BIH arrhythmia dataset is used to test the performance of the proposed model. The experiment compares the detection results when different decomposition component combinations are used as input. When the input data is combined by {d2-d7}, the proposed 1D-GoogLeNet model can achieve an average accuracy of 96.58%. In addition, the performance of the model and the simple one-dimensional GoogLeNet without structural optimization on the data set is compared. The accuracy of the former is 4.7% higher than the latter, and the training efficiency is increased by 118%.
  • loading
  • [1]
    胡盛寿, 高润霖, 刘力生, 等. 《中国心血管病报告2018》概要[J]. 中国循环杂志, 2019, 34(3): 209–220. doi: 10.3969/j.issn.1000-3614.2019.03.001

    HU Shengshou, GAO Runlin, LIU Lisheng, et al. Summary of the 2018 report on cardiovascular diseases in China[J]. Chinese Circulation Journal, 2019, 34(3): 209–220. doi: 10.3969/j.issn.1000-3614.2019.03.001
    [2]
    HUANG Jingshan, CHEN Binqing, ZENG Nianyin, et al. Accurate classification of ECG arrhythmia using MOWPT enhanced fast compression deep learning networks[J]. Journal of Ambient Intelligence and Humanized Computing, To be published. doi: 10.1007/s12652-020-02110-y
    [3]
    RANGAYYAN R M. Biomedical Signal Analysis: A Case Study Approach[M]. New York: IEEE Press, 2002.
    [4]
    VELAYUDHAN A and PETER S. Noise analysis and different denoising techniques of ECG signal - a survey[J]. IOSR Journal of Electronics and Communication Engineering, 2016, 1(1): 40–44.
    [5]
    SLONIM T Y M, SLONIM M A, and OVSYSCHER E A. The use of simple FIR filters for filtering of ECG signals and a new method for post-filter signal reconstruction[C]. Computers in Cardiology Conference, London, UK, 1993: 871–873. doi: 10.1109/CIC.1993.378347.
    [6]
    THAKOR N V and ZHU Y S. Applications of adaptive filtering to ECG analysis: Noise cancellation and arrhythmia detection[J]. IEEE Transactions on Biomedical Engineering, 1991, 38(8): 785–794. doi: 10.1109/10.83591
    [7]
    KABIR M A and SHAHNAZ C. Denoising of ECG signals based on noise reduction algorithms in EMD and wavelet domains[J]. Biomedical Signal Processing and Control, 2012, 7(5): 481–489. doi: 10.1016/j.bspc.2011.11.003
    [8]
    WANG Ze, WAN Feng, WONG C M, et al. Adaptive Fourier decomposition based ECG denoising[J]. Computers in Biology and Medicine, 2016, 77: 195–205. doi: 10.1016/j.compbiomed.2016.08.013
    [9]
    WANG Ge, YANG Lin, LIU Ming, et al. ECG signal denoising based on deep factor analysis[J]. Biomedical Signal Processing and Control, 2020, 57: 101824. doi: 10.1016/j.bspc.2019.101824
    [10]
    YÜCELBAŞ Ş, YÜCELBAŞ C, TEZEL G, et al. Pre-determination of OSA degree using morphological features of the ECG signal[J]. Expert Systems with Applications, 2017, 81: 79–87. doi: 10.1016/j.eswa.2017.03.049
    [11]
    INAN O T, GIOVANGRANDI L, and KOVACS G T A. Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features[J]. IEEE Transactions on Biomedical Engineering, 2006, 53(12): 2507–2515. doi: 10.1109/TBME.2006.880879
    [12]
    LINH T H, OSOWSKI S, and STODOLSKI M. On-line heart beat recognition using Hermite polynomials and neuro-fuzzy network[C]. The 19th IEEE Instrumentation and Measurement Technology Conference, Anchorage, USA, 2002: 165–170. doi: 10.1109/IMTC.2002.1006834.
    [13]
    MARTIS R J, ACHARYA U R, and MIN L C. ECG beat classification using PCA, LDA, ICA and discrete wavelet transform[J]. Biomedical Signal Processing and Control, 2013, 8(5): 437–448. doi: 10.1016/j.bspc.2013.01.005
    [14]
    ALQURAN H, ALQUDAH A M, ABU-QASMIEH I, et al. ECG classification using higher order spectral estimation and deep learning techniques[J]. Neural Network World, 2019, 29: 207–219. doi: 10.14311/NNW.2019.29.014
    [15]
    LYON A, MINCHOLÉ A, MARTÍNEZ J P, et al. Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances[J]. Journal of the Royal Society Interface, 2018, 15(138): 20170821. doi: 10.1098/rsif.2017.0821
    [16]
    LLAMEDO M and MARTÍNEZ J P. Heartbeat classification using feature selection driven by database generalization criteria[J]. IEEE Transactions on Biomedical Engineering, 2011, 58(3): 616–625. doi: 10.1109/TBME.2010.2068048
    [17]
    NASIRI J A, NAGHIBZADEH M, YAZDI H S, et al. ECG arrhythmia classification with support vector machines and genetic algorithm[C]. The 3rd UKSim European Symposium on Computer Modeling and Simulation, Athens, Greece, 2009: 187–192. doi: 10.1109/EMS.2009.39.
    [18]
    CASAS M M, AVITIA R L, GONZALEZ-NAVARRO F F, et al. Bayesian classification models for premature ventricular contraction detection on ECG traces[J]. Journal of Healthcare Engineering, 2018, 2018: 2694768. doi: 10.1155/2018/2694768
    [19]
    KUMAR G R and KUMARASWAMY D Y S. Investigating cardiac arrhythmia in ECG using random forest classification[J]. International Journal of Computer Applications, 2012, 37(4): 31–34. doi: 10.5120/4599-6557
    [20]
    RAJPURKAR P, HANNUN A Y, HAGHPANAHI M, et al. Cardiologist-level arrhythmia detection with convolutional neural networks[EB/OL]. https://arxiv.org/abs/1707.01836,2017.
    [21]
    MOSTAYED A, LUO Junye, SHU Xingliang, et al. Classification of 12-lead ECG signals with Bi-directional LSTM network[EB/OL]. https://arxiv.org/abs/1811.02090,2018.
    [22]
    SINGH S, PANDEY S K, PAWAR U, et al. Classification of ECG arrhythmia using recurrent neural networks[J]. Procedia Computer Science, 2018, 132: 1290–1297. doi: 10.1016/j.procs.2018.05.045
    [23]
    MOODY G B and MARK R G. The impact of the MIT-BIH arrhythmia database[J]. IEEE Engineering in Medicine and Biology Magazine, 2001, 20(3): 45–50. doi: 10.1109/51.932724
    [24]
    GOLDBERGER A L, AMARAL L A, GLASS L, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23): e215–e220. doi: 10.1161/01.cir.101.23.e215
    [25]
    MAHMOODABADI S Z, AHMADIAN A, and ABOLHASANI M D. ECG feature extraction using Daubechies wavelets[C]. Visualization, Imaging, and Image Processing, Benidorm, Spain, 2005.
    [26]
    SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, USA, 2015: 1–9. doi: 10.1109/CVPR.2015.7298594.
    [27]
    WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]. The 15th European Conference on Computer Vision, Munich, Germany, 2018: 3–19. doi: 10.1007/978-3-030-01234-2_1.
    [28]
    IOFFE S and SZEGEDY C. Batch Normalization: Accelerating deep network training by reducing internal covariate shift[C]. The 32nd International Conference on International Conference on Machine Learning, Lille, France, 2015: 448–456.
    [29]
    SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 2818–2826. doi: 10.1109/CVPR.2016.308.
    [30]
    SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning[C]. The 31st AAAI Conference on Artificial Intelligence, San Francisco, USA, 2017: 4278–4284.
    [31]
    KINGMA D P and BA J. Adam: A method for stochastic optimization[C]. The 3rd International Conference on Learning Representations (ICLR), San Diego, USA, 2015.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(6)  / Tables(5)

    Article Metrics

    Article views (911) PDF downloads(109) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return