With the increase in the number of the patients of heart diseases, it is important to analyse the heart activity so that we can easily classify and diagnose the disease. Since, the Electrocardiogram (ECG) signals are used for detecting the cardiac diseases so, in this study analyses and classification of ECG signal are done using Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) data mining techniques. A cleaned ECG signal provides vital information about the heart diseases and ischemic changes that may occur. It provides necessary information about the functional characteristics of the heart. In this paper, R-peaks of the ECG signal is analysed and its optimization is done using the Genetic Algorithm (GA) as the optimization algorithm. The optimized features are selected using this algorithm. Classification of heart disease is done using SVM and LDA data mining techniques. The two cardiac disorder named bradycardia and tachycardia is classified using SVM and LDA techniques. The comparison of these two techniques is performed on the basis of precision value. In this study, SVM showed better results.

ECG Signal, Genetic Algorithm, SVM, LDA

[1] V.K. Gujare , P. Malviya, “Big Data Clustering Using Data Mining Technique”, International Journal of Scientific Research in Computer Science and Engineering, Vol. 5, Issue.2. pp.9-13, 2017.
[2] A. Diker, E. Aci, Z. Comert, D. Avci, E. Kacar, I. Serhatlioglu, “Classification of ECG Signal by using Machine Learning Methods”, In the Proceedings of the 2018 26th Signal Processing and Communications Applications Conference (SIU), Izmir, Turkey, pp. 1-4, 2018.
[3] A. Gaikwad1 , M.S. Panse, “Extraction of FECG from Non-Invasive AECG signal for Fetal Heart Rate Calculation”, Int. J. Sc. Res. in Network Security and Communication, , Vol. 5, Issue.3. pp.109-112, 2017.
[4] P. Guo, X. Wang, Y. Han, “The Enhanced Genetic Algorithms for the Optimization Design”, In the Proceedings of the 2010 3rd International Conference on Biomedical Engineering and Informatics, Yantai, China, pp. 2990-2994, 2010.
[5] R. Varatharajan, G. Manogaran, M.K. Priyan, “A big data classification approach using LDA with an enhanced SVM method for ECG signals in cloud computing”, Multimedia Tools and Applications, Vol.77, Issue.8, pp.10195-10215, 2018.
[6] K. Kaur, L.S. Mann.,“Heart Disease Prediction System Using ANOVA, PCA and SVM Classification”, International Journal of Advanced Research, Ideas and Innovations in Technology, Vol. 2, Issue.3, pp.1-6, 2016.
[7] R. Ceylan, “The Effect of Feature Extraction Based on Dictionary Learning on ECG Signal Classification”, International Journal of Intelligent Systems and Applications in Engineering, Vol.6, Issue.1, pp.40-46, 2018.
[8] C. Venkatesan, P. Karthigaikumar, R. Varatharajan, “A novel LMS algorithm for ECG signal preprocessing and KNN classifier based abnormality detection”, Multimedia Tools and Applications, Vol.77, Issue.8, pp.10365-10374, 2018.
[9] S. Raj, K.C. Ray, “ECG signal analysis using DCT-based DOST and PSO optimized SVM”, IEEE Transactions on Instrumentation and Measurement, Vol.66, Issue.3 pp.470-478, 2017.
[10] T. Debnath, M. Hasan, T. Biswas, “Analysis of ECG signal and classification of heart abnormalities using Artificial Neural Network”, In the Proceedings of the International Conference on Electrical and Computer Engineering, Dhaka, Bangladesh, pp.353-356, 2018.
[11] S. Chattopadhyay, S. Das, A. Nag , J.K. Ray, S. Bhattacharjee, B. Neogi, “Design and Simulation Approach Introduced to ECG Peak Detection with Study on Different Cardiovascular Diseases”, International Journal of Scientific and Research Publications, Vol.2, Issue.12, pp.348-353, 2012.