5 Conclusion
In this paper, we have achieved the top accuracy of MIT-BIH-ECG signal classification
using the artificial neural network model by a value of 93.3% of test-accuracy, of
sensitivity and of precision. Accordingly, the ROC shows an excellent curve of rate
classification results. Accordingly, the histogram presents 0.07% error, which overcomes the state of the art without a huge number of feature extraction and without preprocessing stage. Our method is promising and can help clinicians to determine the
class of each ECG patient. Indeed, for going faster, the next step will be dedicated to
our application implementation on GPU and then on an FPGA.
Acknowledgment. The authors would like to thank OMANTEL and Sultan Qaboos University
for their financial support, grant number “EG/SQU-OT/18/01”.
References
1. Visa, S., Ramsay, B., Ralescu, A.L., Van Der Knaap, E.: Confusion matrix-based feature
selection. MAICS 710, 120–127 (2011)
2. Pyakillya, B., Kazachenko, N., Mikhailovsky, N.: Deep learning for ECG classification. In:
Journal of Physics Conference Series, vol. 913, no. 1, p. 012004. IOP Publishing (2017)
3. Celin, S., Vasanth, K.: ECG signal classification using various machine learning techniques.
J. Med. Syst. 42(12), 241 (2018)
4. Rajpurkar, P., Hannun, A.Y., Haghpanahi, M., Bourn, C., Ng, A.Y.: Cardiologist-level
arrhythmia detection with convolutional neural networks (2017). ArXiv e-prints,. arXiv:
1707.01836
5. Acharya, U.R., et al.: A deep convolutional neural network model to classify heartbeats.
Comput. Biol. Med. 89, 389–396 (2017)
6. Wu, Z., et al.: A novel features learning method for ECG arrhythmias using deep belief
networks. In: 2016 6th International Conference on Digital Home (ICDH), pp. 192–196.
IEEE (2016)
7. Andersen, R.S., Peimankar, A., Puthusserypady, S.: A deep learning approach for real-time
detection of atrial fibrillation. Exp. Syst. Appl. 115, 465–473 (2019)
8. Kachuee, M., Fazeli, S., Sarrafzadeh, M.: Ecg heartbeat classification: a deep transferable
representation. In: 2018 IEEE International Conference on Healthcare Informatics (ICHI),
pp. 443–444. IEEE (2018)
9. Alfaras, M., Soriano, M.C., Ortín, S.: A fast machine learning model for ECG-based
heartbeat classification and arrhythmia detection. Front. Phys. 7, 103 (2019)
10. Ji, Y., Zhang, S., Xiao, W.: Electrocardiogram classification based on faster regions with
convolutional neural network. Sensors 19(11), 2558 (2019)
11. Guo, L., Sim, G., Matuszewski, B.: Inter-patient ECG classification with convolutional and
recurrent neural networks. Biocybern. Biomed. Eng. 39(3), 868–879 (2019)
112
L. Khriji et al.
In this paper, we have achieved the top accuracy of MIT-BIH-ECG signal classification
using the artificial neural network model by a value of 93.3% of test-accuracy, of
sensitivity and of precision. Accordingly, the ROC shows an excellent curve of rate
classification results. Accordingly, the histogram presents 0.07% error, which overcomes the state of the art without a huge number of feature extraction and without preprocessing stage. Our method is promising and can help clinicians to determine the
class of each ECG patient. Indeed, for going faster, the next step will be dedicated to
our application implementation on GPU and then on an FPGA.
Acknowledgment. The authors would like to thank OMANTEL and Sultan Qaboos University
for their financial support, grant number “EG/SQU-OT/18/01”.
References
1. Visa, S., Ramsay, B., Ralescu, A.L., Van Der Knaap, E.: Confusion matrix-based feature
selection. MAICS 710, 120–127 (2011)
2. Pyakillya, B., Kazachenko, N., Mikhailovsky, N.: Deep learning for ECG classification. In:
Journal of Physics Conference Series, vol. 913, no. 1, p. 012004. IOP Publishing (2017)
3. Celin, S., Vasanth, K.: ECG signal classification using various machine learning techniques.
J. Med. Syst. 42(12), 241 (2018)
4. Rajpurkar, P., Hannun, A.Y., Haghpanahi, M., Bourn, C., Ng, A.Y.: Cardiologist-level
arrhythmia detection with convolutional neural networks (2017). ArXiv e-prints,. arXiv:
1707.01836
5. Acharya, U.R., et al.: A deep convolutional neural network model to classify heartbeats.
Comput. Biol. Med. 89, 389–396 (2017)
6. Wu, Z., et al.: A novel features learning method for ECG arrhythmias using deep belief
networks. In: 2016 6th International Conference on Digital Home (ICDH), pp. 192–196.
IEEE (2016)
7. Andersen, R.S., Peimankar, A., Puthusserypady, S.: A deep learning approach for real-time
detection of atrial fibrillation. Exp. Syst. Appl. 115, 465–473 (2019)
8. Kachuee, M., Fazeli, S., Sarrafzadeh, M.: Ecg heartbeat classification: a deep transferable
representation. In: 2018 IEEE International Conference on Healthcare Informatics (ICHI),
pp. 443–444. IEEE (2018)
9. Alfaras, M., Soriano, M.C., Ortín, S.: A fast machine learning model for ECG-based
heartbeat classification and arrhythmia detection. Front. Phys. 7, 103 (2019)
10. Ji, Y., Zhang, S., Xiao, W.: Electrocardiogram classification based on faster regions with
convolutional neural network. Sensors 19(11), 2558 (2019)
11. Guo, L., Sim, G., Matuszewski, B.: Inter-patient ECG classification with convolutional and
recurrent neural networks. Biocybern. Biomed. Eng. 39(3), 868–879 (2019)
112
L. Khriji et al.