The Community for Technology Leaders
2016 International Conference on Frontiers of Information Technology (FIT) (2016)
Islamabad, Pakistan
Dec. 19, 2016 to Dec. 21, 2016
ISBN: 978-1-5090-5300-1
pp: 142-148
Vincentius Timothy , Departement of Electrical Engineering, Bandung Institute of Technology Ganesha Street 10, Bandung 40132, Indonesia
Ary Setijadi Prihatmanto , Departement of Electrical Engineering, Bandung Institute of Technology Ganesha Street 10, Bandung 40132, Indonesia
Kyung-Hyune Rhee , Department of IT Convergence and Application Engineering, Pukyong National University, Busan, South Korea
ABSTRACT
This paper describes the data preparation step of a proposed method for automated diagnosis of various diseases based on heart rate variability (HRV) analysis and machine learning. HRV analysis — consisting of time-domain analysis, frequency-domain analysis, and nonlinear analysis — is employed because its resulting parameters are unique for each disease and can be used as the statistical symptoms for each disease, while machine learning techniques are employed to automate the diagnosis process. The input data consist of electrocardiogram (ECG) recordings. The proposed method is divided into three main steps, namely dataset preparation step, machine learning step, and disease classification step. The dataset preparation step aims to prepare the training data for machine learning step from raw ECG signals, and to prepare the test data for disease classification step from raw RRI signals. The machine learning step aims to obtain the classifier model and its performance metric from the prepared dataset. The disease classification step aims to perform disease diagnosis from the prepared dataset and the classifier model. The implementation of data preparation step is subsequently described with satisfactory result.
INDEX TERMS
machine learning, Automated diagnosis, ECG signal, RRI signal, HRV analysis
CITATION
Vincentius Timothy, Ary Setijadi Prihatmanto, Kyung-Hyune Rhee, "Data preparation step for automated diagnosis based on HRV analysis and machine learning", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 142-148, 2016, doi:10.1109/FIT.2016.7857554
289 ms
(Ver 3.3 (11022016))