Abstract
Cardiovascular disease is one of the important diseases endangering human health. Arrhythmia is an important symptom of cardiovascular disease, and ECG is the main diagnostic basis of arrhythmia. At present, in the algorithm research of ECG classification and recognition, due to the small number of samples collected from abnormal signals, the characteristics of abnormal ECG signals can not be well learned, resulting in the low recognition accuracy. This paper proposes an improved Generative Adversarial Network model to enhance the data of a few categories of ECG signals, and then constructs Resnet-seq2seq classification model for classification and recognition. The Generative Adversarial Network uses the game between generator and discriminator to learn the characteristics of a small number of samples. When the Nash equilibrium is reached, the generator automatically generate ECG samples with high similarity to the original data. Resnet network structure learns the features of the ECG signal after data enhancement, and then sends the feature vectors into the seq2seq model for classification and recognition. This paper uses the pattern between patients to divide the data set, and takes the data set after data enhancement as the training set. The results show that the data enhancement based on GAN can effectively improve the classification effect of ECG signals, and the overall classification accuracy is 98.09%, especially in S and F categories.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sun, L., Wang, Y., Qu, Z., Xiong, N.N.: BeatClass: a sustainable ecg classification system in iot-based ehealth. IEEE Internet Things J. 9(10), 7178–7195 (2022). https://doi.org/10.1109/JIOT.2021.3108792
Alqudah, A.M., Qazan, S., Al-Ebbini, L., Alquran, H., Qasmieh, I.A.: ECG heartbeat arrhythmias classification: a comparison study between different types of spectrum representation and convolutional neural networks architectures. J. Ambient. Intell. Humaniz. Comput. 2021, 1–31 (2021)
Ge, Z., Zhu, Z., Feng, P., Zhang, S., Wang, J., Zhou, B.: ECG-signal classification using svm with multi-feature. In: 2019 8th International Symposium on Next Generation Electronics (ISNE), pp. 1–3 (2019)
Aamir, K.M., Ramzan, M., Skinadar, S., Khan, H.U., Tariq, U.: Automatic heart disease detection by classification of ventricular arrhythmias on ecg using machine learning. Comput. Mater. Continua 71(1), 17–33 (2022)
Subashini, A., Sairamesh, L., Raghuraman, G.: Identification and classification of heart beat by analyzing ecg signal using naive bayes. In: 2019 Third International Conference on Inventive Systems and Control (ICISC), pp. 691–694 (2019)
Kh-Madhloom, J., Khanapi, M., Baharon, M.R.: Ecg encryption enhancement technique with multiple layers of aes and DNA computing. Intell. Autom. Soft Comput. 28(2), 493–512 (2021)
Dias, F.M., Monteiro, H.L., Cabral, T.W., Naji, R., Kuehni, M., Luz, E.J.D.S.: Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm. Comput. Methods Prog. Biomed. 202, 105948 (2021)
Thilagavathy, R., Srivatsan, R., Sreekarun, S., Sudeshna, D., Priya, P.L., Venkataramani, B.: Real-time ecg signal feature extraction and classification using support vector machine. In: 2020 International Conference on Contemporary Computing and Applications (IC3A), pp. 44–48 (2020)
Bhattacharyya, S., Majumder, S., Debnath, P., Chanda, M.: Arrhythmic heartbeat classification using ensemble of random forest and support vector machine algorithm. IEEE Trans. Artif. Intell. 2(3), 260–268 (2021). https://doi.org/10.1109/TAI.2021.3083689
Bouaziz, F., Boutana, D., Oulhadj, H.: Diagnostic of ecg arrhythmia using wavelet analysis and k-nearest neighbor algorithm. In: 2018 International Conference on Applied Smart Systems (ICASS), pp. 1–6 (2018)
Oliveira, L.S.C.D., Andreao, R.V., Filho, M.S.: Bayesian network with decision threshold for heart beat classification. IEEE Lat. Am. Trans. 14(3), 1103–1108 (2016)
Guo, L., Sim, G., Matuszewski, B.: Inter-patient ECG classification with convolutional and recurrent neural networks. Biocybern. Biomed. Eng. 39(3), 868–879 (2019)
Niu, J., Tang, Y., Sun, Z., Zhang, W.: Inter-patient ecg classification with symbolic representations and multi-perspective convolutional neural networks. IEEE J. Biomed. Health Inform. 24(5), 1321–1332 (2020)
Karthik, S., Santhosh, M., Kavitha, M.S., Paul, A.C.: Automated deep learning based cardiovascular disease diagnosis using ecg signals. Comput. Syst. Sci. Eng. 42(1), 183–199 (2022)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
Harada, S., Hayashi, H., Uchida, S.: Biosignal generation and latent variable analysis with recurrent generative adversarial networks. IEEE Access 7, 144292–144302 (2019)
Zheng, Z., Chen, Z., Hu, F.: An automatic diagnosis of arrhythmias using a combination of cnn and LSTM technology. Electronics 9(1), 121 (2020)
Bridgman, E.: Aami: Association for the Advancement of Medical Instrumentation completes recommended practice on decontamination. J. Healthc. Mater. Manage. 9(1), 78 (1991)
Song, X., Yang, G., Wang, K., Huang, Y., Yuan, F., Yin, Y.: Short term ECG classification with residual-concatenate network and metric learning. Multim. Tools Appl. 79(31), 22325–22336 (2020)
Mangathayaru, N., Rani, P., Janaki, V., Srinivas, K., Bai, B.M.: An attention based neural architecture for arrhythmia detection and classification from ecg signals. Comput. Mater. Continua 69(2), 2425–2443 (2021)
Vensko, G., Lieu, K.B., Meloche, S.A., Potter, J.C.: ITT Corp, dynamic time warping (DTW) apparatus for use in speech recognition systems. U.S. Patent 5,073,939 (1991)
Ranjeet, K.: Retained signal energy based optimal wavelet selection for denoising of ecg signal using modifide thresholding. In: 2011 International Conference on Multimedia, Signal Processing and Communication Technologies, pp. 196–199. IEEE (2011)
Sharma, L.N., Dandapat, S.: Compressed sensing for multi-lead electrocardiogram signals. In: 2012 World Congress on Information and Communication Technologies, pp. 812–816. IEEE (2012)
Mondéjar-Guerra, V., Novo, J., Rouco, J., Penedo, M.G., Ortega, M.: Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomed. Signal Process. Control 47, 41–48 (2019)
Sellami, A., Hwang, H.: A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Exp. Syst. Appl. 122, 75–84 (2019)
Chen, M., Wang, G., Ding, Z., Li, J., Yang, H.: Unsupervised domain adaptation for ecg arrhythmia classification. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 304–307 (2020)
Niu, L., Chen, C., Liu, H.: A deep-learning approach to ecg classification based on adversarial domain adaptation. Healthcare 8(4), 437 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, J., Xia, X., Peng, X., Hui, J., Han, C. (2022). Research on ECG Signal Classification Based on Data Enhancement of Generative Adversarial Network. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2022. Lecture Notes in Computer Science, vol 13338. Springer, Cham. https://doi.org/10.1007/978-3-031-06794-5_33
Download citation
DOI: https://doi.org/10.1007/978-3-031-06794-5_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06793-8
Online ISBN: 978-3-031-06794-5
eBook Packages: Computer ScienceComputer Science (R0)