Klasifikasi Sinyal Phonocardiogram Menggunakan Short Time Fourier Transform dan Convolutional Neural Network
DOI:
https://doi.org/10.25126/jtiik.20231015424Abstrak
Berdasarkan laporan American Heart Association, penyakit kardiovaskular menjadi penyebab kematian global tertinggi. Phonocardiogram (PCG) dan electrocardiogram (ECG) biasanya digunakan untuk mendeteksi penyakit jantung. Penggunaan sinyal PCG memberikan hasil prediksi yang lebih baik pada deteksi penyakit jantung bila dibandingkan dengan ECG. Tetapi, penggunaan PCG secara elektronik membutuhkan analisis sinyal yang kompleks untuk mengklasifikasikan kondisi jantung. Penelitian ini bertujuan merancang suatu sistem klasifikasi sinyal PCG berdasarkan metode ekstraksi fitur menggunakan Short Time Fourier Transform (STFT) dan metode klasifikasi menggunakan Convolutional Neural Network (CNN). Pengujian rancangan sistem menggunakan dataset sekunder dengan 2.575 rekaman PCG normal dan 665 rekaman PCG abnormal dalam format wav. Pengujian kinerja menggunakan variasi Hamming, Hann dan Blackman-Harris Window pada bagian ektraksi fitur dan variasi jumlah layer konvolusi pada bagian klasifikasi. Berdasarkan hasil pengujian, penggunaan hamming window pada proses ekstraksi fitur dan 4 layer konvolusi pada proses klasifikasi memberikan hasil terbaik dengan tingkat akurasi 88,11%. Penelitian ini membuktikan bahwa penggunaan hamming window pada bagian ekstraksi fitur dan 4 layer konvolusi pada bagian klasifikasi sebagai bentuk model terbaik sistem klasifikasi PCG berdasarkan STFT dan CNN.
Abstract
According to a report by the American Heart Association, cardiovascular disease is the leading global cause of death. Phonocardiogram (PCG) and electrocardiogram (ECG) are commonly used to detect heart disease. The use of PCG signals provides better predictive results in the detection of heart disease when compared to ECG. However, the use of PCG electronically requires complex signal analysis to classify heart conditions. This study aims to design a PCG signal classification system 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 in the number of convolution layers 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 gives the best results with an accuracy rate of 88.11%. 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.
Downloads
Referensi
BASHAR, M.K., DANDAPAT, S. AND KUMAZAWA, I., 2018. Heart Abnormality Classification Using Phonocardiogram (PCG) Signals. In: 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES). pp.336–340.
CHOWDHURY, T.H., POUDEL, K.N. and HU, Y., 2020. Time-Frequency Analysis, Denoising, Compression, Segmentation, and Classification of PCG Signals. IEEE Access, 8, pp.160882–160890.
CLIFFORD, G.D., LIU, C., MOODY, B., SPRINGER, D., SILVA, I., LI, Q. AND MARK, R.G., 2016. Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016. Computing in Cardiology, 43, pp.609–612.
DEPERLIOĞLU, Ö., 2018. Classification Phonocardiograms with Convolutional Neural Networks. BRAIN. Broad Research in Artificial Intelligence and Neuroscience, 9(1), pp.5–13.
FIERES, J., SCHEMMEL, J. AND MEIER, K., 2006. Training convolutional networks of threshold neurons suited for low-power hardware implementation. In: The 2006 IEEE International Joint Conference on Neural Network Proceedings. pp.21–28.
KRISHNAN, S., 2021. 5 - Advanced analysis of biomedical signals. In: S. Krishnan, ed. Biomedical Signal Analysis for Connected Healthcare. [online] Academic Press.pp.157–222. Available at: <https://www.sciencedirect.com/science/article/pii/B9780128130865000037>.
LI, F., TANG, H., SHANG, S., MATHIAK, K. AND CONG, F., 2020. Classification of heart sounds using convolutional neural network. Applied Sciences (Switzerland), 10(11).
MEINTJES, A., LOWE, A. AND LEGGET, M., 2018. Fundamental Heart Sound Classification using the Continuous Wavelet Transform and Convolutional Neural Networks. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). pp.409–412.
NEBAUER, C., 1998. Evaluation of convolutional neural networks for visual recognition. IEEE Transactions on Neural Networks, 9(4), pp.685–696.
NISBET, R., MINER, G. AND YALE, K., 2018. Chapter 11 - Model Evaluation and Enhancement. In: R. Nisbet, G. Miner and K. Yale, eds. Handbook of Statistical Analysis and Data Mining Applications (Second Edition), Second Edition. [online] Boston: Academic Press.pp.215–233. Available at: <https://www.sciencedirect.com/science/article/pii/B9780124166325000116>.
PUTRA, E. AND SUARTIKA, W., 2016. Klasifikasi Citra Menggunakan Convolutional Neural Network (CNN) pada Caltech 101. Jurnal Teknik ITS, 5(1).
QI, Y., YANG, L., LIU, B., LIU, L., LIU, Y., ZHENG, Q., LIU, D. AND LUO, J., 2021. Accurate diagnosis of lung tissues for 2D Raman spectrogram by deep learning based on short-time Fourier transform. Analytica Chimica Acta, [online] 1179, p.338821. Available at: <https://www.sciencedirect.com/science/article/pii/S0003267021006474>.
RYU, H., PARK, J. AND SHIN, H., 2016. Classification of heart sound recordings using convolution neural network. In: 2016 Computing in Cardiology Conference (CinC). pp.1153–1156.
SUMARNA, S., PURWANTO, A. AND AGUSTIKA, D.K., 2017. Frequency Component Extraction of Heartbeat Cues With Short Time Fourier Transform (Stft). Jurnal Sains Dasar, 5(1), p.1.
VIRANI, S.S., ALONSO, A., BENJAMIN, E.J., BITTENCOURT, M.S., CALLAWAY, C.W., CARSON, A.P., CHAMBERLAIN, A.M., CHANG, A.R., CHENG, S., DELLING, F.N., DJOUSSE, L., ELKIND, M.S.V., FERGUSON, J.F., FORNAGE, M., KHAN, S.S., KISSELA, B.M., KNUTSON, K.L., KWAN, T.W., LACKLAND, D.T., LEWIS, T.T., LICHTMAN, J.H., LONGENECKER, C.T., LOOP, M.S., LUTSEY, P.L., MARTIN, S.S., MATSUSHITA, K., MORAN, A.E., MUSSOLINO, M.E., PERAK, A.M., ROSAMOND, W.D., ROTH, G.A., SAMPSON, U.K.A., SATOU, G.M., SCHROEDER, E.B., SHAH, S.H., SHAY, C.M., SPARTANO, N.L., STOKES, A., TIRSCHWELL, D.L., VANWAGNER, L.B., TSAO, C.W., WONG, S.S. AND HEARD, D.G., 2020. Heart disease and stroke statistics—2020 update: A report from the American Heart Association. Circulation.
ZHONG, Y. HONG, ZHANG, S., HE, R., ZHANG, J., ZHOU, Z., CHENG, X., HUANG, G. AND ZHANG, J., 2019. A convolutional neural network based auto features extraction method for tea classification with electronic tongue. Applied Sciences (Switzerland), 9(12).
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Artikel ini berlisensi Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Penulis yang menerbitkan di jurnal ini menyetujui ketentuan berikut:
- Penulis menyimpan hak cipta dan memberikan jurnal hak penerbitan pertama naskah secara simultan dengan lisensi di bawah Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) yang mengizinkan orang lain untuk berbagi pekerjaan dengan sebuah pernyataan kepenulisan pekerjaan dan penerbitan awal di jurnal ini.
- Penulis bisa memasukkan ke dalam penyusunan kontraktual tambahan terpisah untuk distribusi non ekslusif versi kaya terbitan jurnal (contoh: mempostingnya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan penerbitan awalnya di jurnal ini.
- Penulis diizinkan dan didorong untuk mem-posting karya mereka online (contoh: di repositori institusional atau di website mereka) sebelum dan selama proses penyerahan, karena dapat mengarahkan ke pertukaran produktif, seperti halnya sitiran yang lebih awal dan lebih hebat dari karya yang diterbitkan. (Lihat Efek Akses Terbuka).
