Analisis Sinyal ECG (Electrocardiogram) pada Aktivitas Duduk dan Berdiri dengan Metode HRV (Heart Rate Variability) pada Domain Waktu
Keywords:
ECG, HRV, Arduino UNO, AD8232, MATLAB, SVM ClassifierAbstract
SVM is one of machine leaning is used for pattern recognition classification. In this research, linear SVM methods will be applied to analyze multivariable classification. As an input signal the PQRST signal is used from the measurement results of the ECG cardiac activity device. ECG signals in this study were processed using HRV methods in the time domain. Classification is used to compare ECG signals from measurement result in sitting and standing activities. As a tool designed a heart rate monitoring tool (ECG) with a processor using the Arduino UNO module and the AD8232 ECG amplifier module . The results of ECG signal extraction by the HRV method obtained 11 ECG features (variables). In the traning data contain 10 data and one other file containing 4 ECG data for testing data. In the data transfer process there are 110 features of traning data and 44 features in testing data. The results of the traning data have 100 % accuracy, so that it will procedure a hyperplane that is able to separate the two classes sitting and standing. From the results of testing with the hyperplane the system can classify properly.
References
[2] Carr.J Joseprh dan Brown .John. Introduction Biomedical Equipment Technology.4th edition. Prentice Hall. New Jersey
[3] Cristianini N. dan Taylor J.S. 2000. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge Press University.
[4] Halomoan, Junartho. 2013. Analisa Sinyal EKG dengan Metoda HRV (Heart Rate Variability) pada Domain Waktu Aktivitas Berdiri dan Terlentang. Skripsi. Yogyakarta. Seminar Nasional Aplikasi Teknologi Informasi (SNATI).
[5] Istiqomah, Tyas. 2012. Rancang Bangun Elektrocardiograf (EKG). Skripsi. Surabaya: Fakultas Sains dan Teknologi Universitas Airlangga.
[6] M. Brennan, M. Palaniswami, dan P. Kamen. 2001. Do Existing Measures of Poincare Plot Geometry Reflect Nonlinear Features of Heart Rate Variability?. IEEE Trans. Biomed. Eng., 48(11):1342-1346.
[7] Min, Tian Kai. 2017. Comparison of Atrial Fibrillation and Congestive Heart Failure Recognition Based on Traditional Method and Convolutional Neural Network. Thesis. Chiayi County: Chung Cheng University.
[8] Nussey, J. 2013. Arduino for Dummies. West Sussex: John Wiley & Sons.
[9] R. W. Picard, E. Vyzas, dan J. Healey. 2001. Toward Machine Emotional Intelligence: Analysis of Affective Physiological State. IEEE Trans. Pattern Analysis and Machine Intelligence, 23(10).
[10] Suprayitno, E. et al. 2012. Analisa Sinyal Electrocardiography dan Phonocardiography Secara Simultan Menggunakan Continuous Wavelet Transform. Skripsi. Malang: Univeritas Brawijaya.
[11] Tribun Medan. 10 Desember, 2017. Data WHO 17,5 Juta Orang di Dunia Meninggal karena Jantung, Ini 7 Kiat Menjaga Kesehatan Jantung, (Online), (http://medan.tribunnews.com, diakses 9 Januari 2019).
