Klasifikasi Sinyal Phonocardiogram Menggunakan Short Time Fourier Transform Dan Convolutional Neural Network

Muhammad, Alwi Adnan Amal (2021) Klasifikasi Sinyal Phonocardiogram Menggunakan Short Time Fourier Transform Dan Convolutional Neural Network. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (500kB)
	Text Abstract.pdf Download (185kB)
	Text Abstrak.pdf Download (184kB)
	Text BAB I.pdf Download (302kB)
	Text BAB II.pdf Download (935kB)
	Text BAB III.pdf Download (636kB)
	Text BAB IV.pdf Restricted to Registered users only Download (838kB) | Request a copy
	Text BAB V.pdf Download (185kB)
	Text Daftar Pustaka.pdf Download (400kB)
	Text Lampiran.pdf Restricted to Registered users only Download (566kB) | Request a copy

Abstract

Based on the report of the American Heart Association, cardiovascular disease is the leading global cause of death, so a diagnostic tool is needed that can reduce the prevalence of this heart disease early. Phonocardiogram (PCG) and electrocardiogram (ECG) are commonly used to detect heart disease. ECG signals are used to visualize the electrical signals of the heart, but ECG measurements require relatively large costs and more time. PCG as an alternative method can overcome these ECG problems. However, the use of PCG electronically requires complex signal analysis to classify heart conditions. This study aims to design a PCG signal classification system as a diagnostic tool for heart conditions based on the extraction method using the Short Time Fourier Transform (STFT) and the classification method using the Convolutional Neural Network (CNN). The system design test used a secondary dataset with 2,575 normal PCG records and 665 abnormal PCG records in wav format. Performance testing uses variations of Hamming, Hann and Blackman-Harris Window in the feature extraction section and variations of 2, 3 and 4 layers of convolution in the classification section. Based on the test results, the use of a hamming window in the feature extraction process and 4 convolution layers in the classification process gave the best results with an accuracy rate of 88.11%, sensitivity 76.64% and specificity 91.19%. This study proves that the use of a hamming window in the feature extraction section and 4 convolution layers in the classification section is the best form of the PCG classification system based on STFT and CNN. Keywords: Phonocardiogram, Short Time Fourier Transform, Hamming Window, Convolutional Neural Network.

Actions (login required)

View Item