Puspasari, Ira (2015) Analisis Non-Stasioner pada Deteksi Non-Invasive Sinyal Suara Jantung Koroner. Jurnal Nasional Teknik Elektro dan Teknologi Informasi (JNTETI) Universitas Gadjah Mada, 4 (2). pp. 99-103. ISSN 2301-4156
Text
Ira_Puspasari_Analisis_Non-Stasioner_pada_Deteksi_Non-Invasive_Sinyal_Jantung_Koroner.pdf - Published Version Download (253kB) |
Search this title on : |
Abstract
Feature extraction part has become a very important thing which can be use to develop a system of electronic heart sound diagnosis. Therefore, it is necessary to hold a research about an effective feature extraction method to know the dynamics of the data contained in heart sound. This researched has learned more about feature extraction method, using non-stationary signal processing, Short Time Fourier Transform. The result of the signal of CHD (coronary heart disease) showed that the first signal has an average frequency at 505.56±8.82 Hz, and this signal is detected on an average window at 21.44±2.92, an average time at 0.05±0.02 s. The results of the second signal feature extraction, was detected an average frequency at 376.11±2.20 Hz, with an average window at 141.67±2.5, and an average time at 0.35±0.02 s. The results of feature extraction on the third signal, showed an average frequency at 217.14±12.78 Hz, an average window at 74.29±4.16, and an average time at 0.17±0.02 s. The results of this study indicate that the entire frequency has an average value of more than 200 Hz.
Export Record
Item Type: | Article |
---|---|
Uncontrolled Keywords: | ekstraksi ciri, pengolahan sinyal, suara jantung, koroner, Time-frequency analysis |
Dewey Decimal Classification: | 600 – Technology > 620 Engineering & Applied operations |
Divisions: | Perpustakaan > Journals |
Depositing User: | Agung P. W. |
Date Deposited: | 17 Sep 2015 13:44 |
Last Modified: | 17 Sep 2015 13:44 |
URI: | http://repository.dinamika.ac.id/id/eprint/1325 |
Download Statistics
Downloads over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
Actions (login required)
View Item |