A Competitive Structure of Convolutional Autoencoder Networks for Electrocardiogram Signals Classification

Alexandre Farias Baia; Adriana Rosa Garcez Castro

doi:10.5753/eniac.2018.4446

Alexandre Farias Baia UFPA
Adriana Rosa Garcez Castro UFPA

DOI: https://doi.org/10.5753/eniac.2018.4446

Resumo

This paper presents the proposal of an electrocardiogram (ECG) signals classification system through a competitive structure of Convolutional Autoencoders (CAE). Two Convolutional Autoencoders were trained to reconstruct ECG signals for the cases of patients with arrhythmia and patients with signals considered normals. After the training, the two networks were arranged in a competitive parallel structure to classify these signals. For the development and testing of the system, the MIT-BIH Arrhythmia Database of ECG signals was used. An accuracy of 88,9% was achieved considering the database used for system testing.

Referências

ECG (2018) “ECG Learning Center”, https://ecg.utah.edu/lesson/1, Junho.

Isin, A., Ozdalili, S. (2017) “Cardiac arrhythmia detection using deep learning”, 9th International Conference on Theory and Application of Soft Computing, Computing with Words and Perception, ICSCCW 2017, Budapeste, Hungria.

Lassoued, H., Ketata, R. (2018) “ECG multi-class classification using neural network as machine learning model”, International Conference on Advanced Systems and Electric Technologies (IC_ASET), Hammamet, Tunísia, Março.

Kelwade, J., Salankar, S. (2015) “Prediction of Cardiac Arrhythmia using Artificial Neural Network”, International Journal of Applications, Vol. 115, nº 20, Abril.

Naik, G., Reddy, K. (2016) “Comparative Analysis of ECG Classification Using Neuro-Fuzzy Algorithm and Multimodal Decision Learning Algorithm”, 3rd International Conference on Soft Computing & Machine Intelligence, Dubai, Emirados Arábes Unidos, Outubro.

Tandale, S., Ghongade, R., Barhatte, A., Dale, M. (2017) “Arrhythmia classification using neuro fuzzy approach”, 3rd International Conference on Advances in Computing,Communication & Automation (ICACCA), Dehradun, Índia, Setembro.

Ye, C., Kumar, B., Coimbra, M. (2012) “Combining general multi-class and specific two-class classifiers for improved customized ECG heartbeat classification”, International Conference on Pattern Recognition (ICPR), p.2428–2431.

Escalona-Moran, M., Soriano, M., Fischer, I., Mirasso, C., (2015) “Electrocardiogram classification using reservoir computing with logistic regression”, IEEE J. Biomed. Health Inform. 19 (3), p.892–898.

PhysioNet, PhysioBank (2018) “MIT-BIH Arrhythmia Database”. https://www.physionet.org/physiobank/database/mitdb/, Junho.

LeCun, Y., Bengio, Y., Hinton, G. (2015) “Deep Learning Review”, Nature: Vol. 521, p. 436-444.

Nardelli, P., Jimenez-Carretero, D., Bermejo-Pelaez, D., Washko, G., Rahaghi, F., Ledesma-Carbayo, M., Estépar, R. (2018) “Pulmonary Artery-Vein Classification in CT Images Using Deep Learning”, DOI 10.1109/TMI.2018.2833385, IEEE Transactions on Medical Imaging.

Penha, D., Castro, A. (2017) “Convolutional Neural Network Applied to the Identification of Residential Equipment in Nonintrusive Load Monitoring Systems”, 3rd International Conference on Artificial Intelligence and Applications, Computer Science & Information Technology, p. 11.

Sakurai, R. (2017) “Implementando a estrutura de uma Rede Neural Convolucional utilizando o MapReduce do Spark”, http://rafaelsakurai.github.io/cnn-mapreduce/, Junho.

Deshpande. A. (2018) “A Beginner's Guide to Understanding Convolutional Neural Networks”, https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/, Junho.

Nair, V., Hinton, G. (2010) “Rectified Linear Units Improve Restricted Boltzmann Machines”, Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel.

MLP, Deep Learning (2018) “Multilayer Perceptron. DeepLearning 0.1 documentation”, http://deeplearning.net/tutorial/mlp.html, Junho.

Sathyanarayana, S. (2014) “A Gentle Introduction to Backpropagation, Numeric Insight. 2014.

Castro, A., Miranda, V., Lima, S. (2012) “Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift”, IEEE Transactions on Power delivery, vol. 27, no. 3, Julho.

Keras (2018) “Keras: The Python Deep Learning Library”, https://keras.io/, Junho.

Python (2018) “Python”, https://www.python.org/, Junho.

Nvidia (2018) “CUDA Zone”, https://developer.nvidia.com/cuda-zone, Junho.

TensorFlow (2018) “TensorFlow”, https://www.tensorflow.org/, Junho.

Ruder, S. (2016) “An overview of gradient descent optimization algorithms”, http://ruder.io/optimizing-gradient-descent/index.html#adamax, Junho.

de Chazal, P., M., O’Dwyer, M., Reilly, R. (2004) “Automatic classification of heartbeats using ECG morphology and heartbeat interval features”, IEEE Trans. Biomed. Eng. 51 (7), p.1196–1206.

Soria, M., Martinez, J. (2009) “Analysis of multidomain features for ECG classification”, Comput. Cardiol., p.561–564.

Llamedo, M., Martínez, J. (2011) “Heartbeat classification using feature selection driven by database generalization criteria”, IEEE Trans. Biomed. Eng. 58 (3), p.616–625.

Mar, T., Zaunseder, S., Martínez, J., Llamedo, M., Poll, R. (2011) “Optimization of ECG classification by means of feature selection”, IEEE Trans. Biomed. Eng. 58 (8), p.2168–2177.

Bazi, Y., Alajlan, N., AlHichri, H., Malek, S. (2013) “Domain adaptation methods for ECG classification”, International Conference on Computer Medical Applications (ICCMA), p.1–4.

de Lannoy, G., François, D., Delbeke, J., Verleysen, M., (2010) “Weighted SVMs and feature relevance assessment in supervised heart beat classification”, Biomedical Engineering Systems and Technologies (BIOSTEC), p.212–223.

Park, K., Cho, B., Lee, D., Song, S., Lee, J., Chee, Y., Kim, I., Kim, S. (2008) “Hierarchical support vector machine based heartbeat classification using higher order statistics and hermite basis function”, Comput. Cardiol., p. 229–232.

Zhang, Z., Dong, J., Luo, X., Choi, K., Wu, X. (2014) “Heartbeat classification using disease- specific feature selection”, Comput. Biol. Med. 46, p.79–89.

Lin, C., Yang, C. (2014) “Heartbeat classification using normalized RR intervals and morphological features”, Math. Problem Eng., p.1–11.

de Lannoy, G., François, D. Delbeke, J., Verleysen, M. (2012) “Weighted conditional random fields for supervised interpatient heartbeat classification”, IEEE Trans. Biomed. Eng.59 (1), p.241–247.

Zhang, Z., Luo, X. (2014) “Heartbeat classification using decision level fusion”, Biomed. Eng. Lett. 4 (4), p.388–395.

Luz, E., Schwartz, W., Cámara-Chávez. G., Menotti, D. (2015) “ECG-based heartbeat classification for arrhythmia detection: A survey”, Elsevier.