Journal of Convergence for Information Technology (융합정보논문지)

Convergence Society for SMB (중소기업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Classificatin of Normal and Abnormal Heart Sounds Using Neural Network

뉴럴네트워크를 이용한 심음의 정상 비정상 분류

  • Yoon, Hee-jin (Internet Information and Communication Division, IT Collage, Jangan University)
  • 윤희진 (장안대학교 IT학부 인터넷정보통신과)
  • Received : 2018.09.18
  • Accepted : 2018.10.20
  • Published : 2018.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

The heart disease taking the second place of the cause of the death of modern people is a terrible disease that makes sudden death without noticing. To judge the aortic valve disease of heart diseases a name of disease was diagnosed using psychological data provided from physioNet. Aortic valve is a valve of the area that blood is spilled from left ventricle to aorta. Aortic stenosis of heart troubles is a disease when the valve does not open appropriately in contracting the left ventricle to aorta due to narrowed aortic valve. In this paper, 3126 samples of cardiac sound data were used as an experiment data composed of 180 characteristics including normal people and aortic valve stenosis patients. To diagnose normal and aortic valve stenosis patients, NEWFM was utilized. By using an average method of weight as an feature selection method of NEWFM, the result shows 91.0871% accuracy.

현대인의 사망원인 2위를 차지하고 있는 심장병은 자각 증세 없이 갑자기 돌연사를 당할 수 있는 무서운 질병으로 예방이 중요하다. 심장병 중 대동맥판막 협착증을 판단하기 위해서 physioNet에서 제공하는 심음 데이터 중 S1과 S2 사이의 수축 심음 데이터를 이용하여 병명을 진단하였다. 대동맥 판막은 좌심실에서 대동맥으로 피가 유출되는 부위의 판막이다. 심장병 중 대동맥판막 협착증은 대동맥판막이 좁아져 좌심실의 수축 시 판막이 열리지 않는 질환이다. 위 논문에서는 정상인과 대동맥판막 협착증 환자를 합쳐 특징이 180개로 이루어진 3126개의 샘플 심음 데이터를 실험데이터로 사용하였다. 정상과 대동맥판막 협착증 환자를 구분하기 위해 가중퍼지신경망(NEWFM, Neural Network with Weighted Fuzzy Membership Function)이용하였다. 가중퍼지신경망의 특징선택 방법으로 가중치의 평균 방법을 이용하였으며, 분류 결과는 91.0871%의 정확도를 나타내었다.

Keywords

References

  1. S. H. Eum. (2015). A study of Classification of Heart Murmurs using Shannon Entropy and Neural Network. The Journal of Korea Insitiute of signal Processing and System, 16(4), 134-138.
  2. J. S. Choi. (1989). Heart Sounds and Murmurs, Hyunmon, Seoul.
  3. Y. J. Lee & G. H. Lee. (2016). Heart Murmur Detection Algorithm based on Spectral Flatness. Journal of Korea Multimedia society, 19(3), 557-566. https://doi.org/10.9717/kmms.2016.19.3.557
  4. W. Hang S. H. Kim & K. S. Bae. (2010). Hidden Markov model with heart sound signals for identification of heart diseases. Proceedings of 20th international Congress on Acoustics, ICA 2010, 23-27.
  5. T. Nilanon, J. Yao & J. Hao. (2016). Normal/abnormal heart sound recordings classification using convolutional neural network. In Computing in Cardiology Conference (CinC), (pp. 585-588). IEEE.
  6. S. Kofman, A. Bickel & A. Eitan. (2012) Discovery of multiple level heart-sound morphological variability resulting from changes in physiological states. Biomedical Signal Processing and Control, 7(4), 315-324. https://doi.org/10.1016/j.bspc.2011.08.001
  7. L. Jia, D. Song, L. Tao, & Y. Lu. (2012). Heart Sounds Classification with a Fuzzy Neural Network Method with Structure Learning, Advances in Neural Networks. Lecture Notes in Computer Science, 7368, 130-140.
  8. G. D. Clifford, C. Liu, B. Moody, D. Springer, I. Silva, Q. Li & R. G. Mark. (2016). Classification of Normal/Abnormal Heart Sound Recordings : the PhysioNet/Computing in Cardiology Challenge 2016. Computing in Cardiology 2016, 43, ISSN:2325-887X. DOI : 10.22489/CinC.2016.179-154
  9. CLASSIFICATION OF NORMAL/ABNORMAL HEART SOUND RECORDINGS:THE PHYSIONET/ COMPUTING IN CARDIOLOGY CHALLENGE 2016. http://physionet.org/challenge/2016
  10. G. Amit, K. Shukha, N. Gavriely & N. Intrator.(2009). Respiratory modulation of heart sound morphology. Am. J. Physiol. Heart Circ. Physiol, 296(3), H796-H805. https://doi.org/10.1152/ajpheart.00806.2008
  11. H. Y. Liang, L. Sakari & H. Iiro. (1997). A heart sound segmentation algorithm using wavelet decomposition and reconstruction. Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, ; IEEE: Chicago, IL, pp 1630-1633.
  12. S. B. Shinde & A. Priyadarshi. (2013). Diagnosis of Heart Disease Using Data Mining Tehnique. International Journal of Science and Research(USR),ISSN(Online), 2319-7064.
  13. G. E. Guraksin & H. Uguz. (2011). Classification of heart sounds based on the least squares support vector machine. International Journal of Innovative Computing, Information and Control, 7(12), 7131-7144.