Page 141 - Control Theory in Biomedical Engineering

Genetic fuzzy logic based system for arrhythmia classification 125

baseline shift from the ECG signals is investigated. Then, the ECG feature
extraction is done. Hence, we obtained several morphological features.
However, we selected only six features to evaluate the FLC. In the second
block, we firstly manually configured the FLC. Then, we applied the GA for
the FLC membership parameters and rules number optimization. Accord-
ingly, a comparison study between the obtained performances before apply-
ing the genetic optimization (ACC ¼ 89.583%) and after its application
(ACC ¼ 97.054%) is treated. This study reveals that the average accuracy
(ACC¼97.054%) is improved by using the optimized membership param-
eters and rules numbers. However, two arrhythmias (P and PVC) are not
efficiently classified. Successively, in order to evaluate the efficiency of
the proposed FLC, a second comparison study with related works is pre-
sented. Therefore, the reached results show the usefulness of the suggested
FLC (ACC¼97.054%), which may provide an effective way for earlier
diagnosis of a number of arrhythmias. Moreover, the accuracy of the clas-
sifier depends not only on the FLC configuration but also on the type
and number of the extracted features. Thus, we recommend using the clus-
tering algorithms that are able to select automatically the type and number of
fuzzy sets. We also recommend adding other features, such as the discrete
wavelet coefficients in order to enrich the input feature vector.

References
Ahmadi, H., Gholamzadeh, M., Shahmoradi, L., Nilashi, M., Rashvand, P., 2018. Diseases
diagnosis using fuzzy logic methods: a systematic and meta-analysis review. Comput.
Methods Programs Biomed. 161, 145–172.
Angra, S., Sachin, A., 2017. Machine learning and its applications: a review. In: Proc of the
Int. Conf. on Big Data Analytics and Computational Intelligence (ICBDAC). India,
23–25 March.
Arabasadi, Z., Alizadehsani, R., Roshanzamir, M., Moosaei, H., Yarifard, A.A., 2017. Com-
puter aided decision making for heart disease detection using hybrid neural network-
Genetic algorithm. Comput. Methods Programs Biomed. 141, 19–26.
Bakator, M., Radosav, D., 2018. Deep learning and medical diagnosis: a review of literature.
Multimodal Technol. Interact. 2 (3), 47.
Chen, W., Thomas, J., Sadatsafavi, M., Fitz Gerald, J.M., 2015. Risk of cardiovascular
comorbidity in patients with chronic obstructive pulmonary disease: a systematic review
and meta-analysis. Lancet Respir. Med. 3 (8), 631–639.
Chen, S., Hua, W., Li, Z., Li, J., Gao, X., 2017. Heartbeat classification using projected and
dynamic features of ECG signal. Biomed. Signal Process. Control 31, 165–173.
De Chazel, P., O’Dwyer, M., Reilly, R.B., 2004. Automatic classification of heartbeats using
ECG morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51 (7),
1196–1206.
Demski, A., Llamedo, S.M., 2016. ECG-kit: a Matlab toolbox for cardiovascular signal pro-
cessing. J. Open Res. Softw. 4(1).