Efficient PCG classification system based on Slantlet transform

• Autorzy: Khaleel Asmaa N. , Jasim Abdulhamed M. , Khidhir Abdulsattar M.

Identyfikatory

DOI

10.15199/48.2023.08.25

Warianty tytułu

PL

Wydajny system klasyfikacji PCG oparty na transformacji Slantleta

• Języki publikacji: EN

Abstrakty

EN

Phonocardiogram (PCG) signals represent the recording of sounds and murmurs, which result from heartbeats. PCG signals analysis is critical in the diagnosis of normal and abnormal cases of the heart. A variety of methods have been proposed for PCG signals analysis. In this paper, a classification system for PCG signals is introduced based on SLT filters with detailed statistical functions and ANN algorithm. The proposed system is able to diagnose normal and four abnormal cases. The extracted features from heart sound signal are based on 3-scale slantlet filters and three statistical equations; power, average and standard deviation of the SLT filter coefficients. Based on these important features, ANN were trained and tested to obtain high overall classification accuracy. The results show that the proposed classification system is capable to diagnose the normal PCG case and other four different abnormal cases with an overall diagnosis accuracy of 98.67%. This result of the proposed system overcome other recent works.

PL

Sygnały fonokardiogramu (PCG) reprezentują zapis dźwięków i szmerów, które są wynikiem bicia serca. Analiza sygnałów PCG ma kluczowe znaczenie w diagnostyce prawidłowych i nieprawidłowych przypadków serca. Zaproponowano różne metody analizy sygnałów PCG. W artykule przedstawiono system klasyfikacji sygnałów PCG oparty na filtrach SLT ze szczegółowymi funkcjami statystycznymi i algorytmem ANN. Proponowany system jest w stanie zdiagnozować przypadki normalne i cztery przypadki nieprawidłowe. Cechy wyodrębnione z sygnału tonu serca są oparte na 3-skalowych filtrach skośnych i trzech równaniach statystycznych; moc, średnia i odchylenie standardowe współczynników filtra SLT. W oparciu o te ważne cechy SSN zostały przeszkolone i przetestowane w celu uzyskania wysokiej ogólnej dokładności klasyfikacji. Wyniki pokazują, że proponowany system klasyfikacji jest w stanie zdiagnozować normalny przypadek PCG i inne cztery różne przypadki nieprawidłowe z ogólną dokładnością diagnozy na poziomie 98,67%. Ten wynik proponowanego systemu przewyższa inne ostatnie prace.

Słowa kluczowe

EN

PCG signals; slantlet transform; statistical functions; ANN classifier

PL

fonokardiogram PCG; transdoemacja Slantlet

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2023
• Tom: R. 99, nr 8
• Strony: 141--145
• Opis fizyczny: Bibliogr. 24 poz., rys., tab.

Twórcy

autor

Khaleel Asmaa N.

• College of Electronics Engineering, Ninevah University, Ninewa, Mosul City, Iraq

• https://orcid.org/0000-0001-8352-7884

autor

Jasim Abdulhamed M.

• College of Electronics Engineering, Ninevah University, Ninewa, Mosul City, Iraq

• https://orcid.org/0000-0002-2491-9789

autor

Khidhir Abdulsattar M.

• Mosul Technical Institute, Northern Technical University, Mosul, Iraq

Bibliografia

• [1] Varshney, Shivam, and Satyendra Singh. "Murmur Detection in PCG signals using DWT Entropy and Feature Clustering." In 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), pp. 1-6. IEEE, 2020.
• [2] Gopika, P., V. Sowmya, E. A. Gopalakrishnan, and K. P. Soman. "Performance improvement of deep learning architectures for phonocardiogram signal classification using fast fourier transform." In 2019 9th international conference on advances in computing and communication (ICACC), pp. 290- 294. IEEE, 2019.
• [3] Al Ghawas, Mohamad, and Rand Al Muallem. "Electronic Stethoscope And Heart Rate Monitor." Near East University (2015).
• [4] Bashar, Md Khayrul, Samarendra Dandapat, and Itsuo Kumazawa. "Heart Abnormality Classification Using Phonocardiogram (PCG) Signals." In 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), pp. 336-340. IEEE, 2018.
• [5] Sujadevi, V. G., K. P. Soman, R. Vinayakumar, and AU Prem Sankar. "Deep models for phonocardiography (PCG) classification." In 2017 International Conference on Intelligent Communication and Computational Techniques (ICCT), pp. 211-216. IEEE, 2017.
• [6] Chowdhury, Md, K. Poudel, and Y. Hu. "Detecting Abnormal PCG Signals and Extracting Cardiac Information Employing Deep Learning and the Shannon Energy Envelope." In 2020 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1-4. IEEE, 2020.
• [7] Niedziejko, P., P. Dobrowolski, and I. Krysowaty. "Współczesne metody analizy dźwięku serca." Przegląd Elektrotechniczny 87, no. 9a (2011): 1-7.
• [8] Gradolewski, Dawid, Piotr Tojza, and Grzegorz Redlarski. "Adaptacyjny algorytm filtracji sygnału fonokardiograficznego wykorzystujący sztuczną sieć neuronową." Przegląd Elektrotechniczny (2014): 227-230.
• [9] Mrad, Mohamed Azouz, Kristóf Csorba, Dorián László Galata, Zsombor Kristóf Nagy, and Brigitta Nagy. "Spectroscopy-Based Partial Prediction of In Vitro Dissolution Profile Using Artificial Neural Networks." Periodica Polytechnica Electrical Engineering and Computer Science 66, no. 2 (2022): 122-131.
• [10] Thabit, Rasha. "Multi-biometric watermarking scheme based on interactive segmentation process." Periodica Polytechnica Electrical Engineering and Computer Science 63, no. 4 (2019): 263-273.
• [11] Son, Gui-Young, and Soonil Kwon. "Classification of heart sound signal using multiple features." Applied Sciences 8, no. 12 (2018): 2344.
• [12] Fahad, Imran, Md Ashiqur Rahman Apu, Abesh Ghosh, and Shaikh Anowarul Fattah. "Phonocardiogram heartbeat segmentation and autoregressive modeling for person identification." In TENCON 2019-2019 IEEE Region 10 Conference (TENCON), pp. 1942-1946. IEEE, 2019.
• [13] Chowdhury, Tanzil Hoque, Khem Narayan Poudel, and Yating Hu."Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals." IEEE Access 8 (2020): 160882-160890.
• [11] P. Careena1, M. Mary Synthuja Jain Preetha and P. Arun "Significance of Frequency Domain Features of PCG Records for Murmur Detection - An Investigation",2020
• [14] Careena, P., M. Mary Synthuja Jain Preetha, and P. Arun. "Significance of Frequency Domain Features of PCG Records for Murmur Detection--An Investigation." Biomedical and Pharmacology Journal 13, no. 2 (2020): 555-570.
• [15] Khaled, Sara, Mahmoud Fakhry, and Ahmed S. Mubarak. "Classification of pcg signals using a nonlinear autoregressive network with exogenous inputs (narx)." In 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), pp. 98-102. IEEE, 2020.
• [16] Chowdhury, M., C. Li, and K. Poudel. "Combining Deep Learning with Traditional Machine Learning to Improve Phonocardiography Classification Accuracy." In 2021 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), pp. 1-5. IEEE, 2021.
• [17] Chen, Ding, Weipeng Xuan, Yexing Gu, Fuhai Liu, Jinkai Chen, Shudong Xia, Hao Jin, Shurong Dong, and Jikui Luo. "Automatic Classification of Normal–Abnormal Heart Sounds Using Convolution Neural Network and Long-Short Term Memory." Electronics 11, no. 8 (2022): 1246.
• [18] Zhang, Anqi, Jiaming Wang, Fei Qu, and Zhaoming He. "Classification of Children's Heart Sounds With Noise Reduction Based on Variational Modal Decomposition."Frontiers in Medical Technology 4 (2022).
• [19] Ivan, W. S. "The slantlet transform." IEEE Trans Signal Proces 47 (1999): 1304-1313.
• [20] MOHAMED, BOUSSAA, BENRABH MOHAMED, ATOUF ISSAM, ATIBI MOHAMED, And BENNIS ABDELLATIF. "IMPLEMENTATION OF A PCG SIGNAL CLASSIFICATION SYSTEM IN THE FPGA EMBEDDED PLATFORM." Journal Of Theoretical & Applied Information Technology 96, No. 7 (2018).
• [21] Park, Y-S., and S. Lek. "Artificial neural networks: Multilayer perceptron for ecological modeling." In Developments in environmental modelling, vol. 28, pp. 123-140. Elsevier, 2016.
• [22] Chowdhury, Tanzil Hoque, Khem Narayan Poudel, and Yating Hu. "Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals." IEEE Access 8 (2020): 160882-160890.
• [23] Alafif, Tarik, Mehrez Boulares, Ahmed Barnawi, Talal Alafif, Hassan Althobaiti, and Ali Alferaidi. "Normal and abnormal heart rates recognition using transfer learning." In 2020 12th International Conference on Knowledge and Systems Engineering (KSE), pp. 275-280. IEEE, 2020.
• [24] Tiwari, Shamik, Anurag Jain, Akhilesh Kumar Sharma, and Khaled Mohamad Almustafa. "Phonocardiogram signal based multi-class cardiac diagnostic decision support system." IEEE Access 9 (2021): 110710-110722.