Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Detecting Abnormalities in Heart Sounds

Kalp Seslerindeki Anormalliklerin Belirlenmesi

How to cite: Telçeken M, Kutlu Y. Detecting abnormalities in heart sounds. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2021; 4(2): 137-143.

Full Text: PDF, in Turkish.

Total number of downloads: 683

Title: Detecting Abnormalities in Heart Sounds

Abstract: Heart sounds are important data that reflect the state of the heart. It is possible to prevent larger problems that may occur with early diagnosis of abnormalities in heart sounds. Therefore, in this study, the detection of abnormalities in heart sounds has been studied. In order to detect abnormalities in heart sounds, the heartbeat-sounds data set obtained free of charge from the kaggle.com website was examined. Mel frequency cepstral coefficients (MFCCs) were used in the selection of the characteristics of the sounds. Parameters such as the number of filters to be applied for MFCCs, the number of attributes to be extracted are examined separately with different values. The classification performance of heart sounds with feature matrices extracted in different parameters of MFCCs with K-nearest neighbor algorithm was investigated. The classification performance of different feature extractions was compared and the best case was tried to be determined. Two different records that make up the data set were examined separately as normal and abnormal. Then, the new data set obtained by combining the two records was examined as normal and abnormal.

Keywords: MFCC; k-nearest negihbors; heart sound; classification


Başlık: Kalp Seslerindeki Anormalliklerin Belirlenmesi

Özet: Kalp sesleri kalbin durumunu yansıtan önemli verilerdir. Kalp seslerindeki anormalliklerin erken teşhisi ile oluşabilecek daha büyük sorunları önlemek mümkün olabilmektedir. Bu nedenle bu çalışmada kalp seslerindeki anormalliklerin tespiti üzerine çalışılmıştır. Kalp seslerindeki anormallikleri tespit etmek için kaggle.com internet sitesi üzerinden ücretsiz olarak elde edilmiş kalp hızı - sesleri veri seti incelenmiştir. Seslerin özelliklerinin seçiminde Mel frekansı sepstral katsayıları (MFCCs) kullanılmıştır. MFCCs için uygulanacak filtre sayısı, çıkarılacak öznitelik sayısı gibi parametreler farklı değerlerde ayrı ayrı incelenmiştir. Kalp seslerinin MFCCs’nin farklı parametrelerinden çıkartılan öznitelik matrisleri K-en yakın komşu algoritması ile sınıflandırma başarımları incelenmiştir. Farklı öznitelik çıkarımlarının sınıflandırma başarımları karşılaştırılmış ve en iyi durum tespit edilmeye çalışılmıştır. Veri setini oluşturan iki farklı kayıt ayrı ayrı normal ve anormal olarak incelenmiştir. Sonrada iki kayıt birleştirilerek elde edilen yeni veri seti normal ve anormal olarak incelenmiştir.

Anahtar kelimeler: MFCCs; k-yakın komşu; kalp sesi; sınıflandırma


Bibliography:
  • Roy JK, Roy TS. A simple technique for heart sound detection and real time analysis. In 2017 Eleventh International Conference on Sensing Technology (ICST), 2017, pp. 1-7.
  • Garcia G, Moreira G, Menotti D, Luz E. Inter-patient ECG heartbeat classifcation with temporal VCG optimized by PSO. Scientific Reports 2017; 7(1): 10543.
  • Andrisevic N, Ejaz K, Gutierrez FR, Flores RA. Detection of heart murmurs using wavelet analysis and artificial neural networks. Journal of Biomechanical Engineering 2005; 127(6): 899-904.
  • Gupta CN, Palaniappan R, Swaminathan S, Krishnan SM. Neural network classification of homomorphic segmented heart sounds. Applied Soft Computing 2007; 7(1): 286-297.
  • Uguz H, Arslan A, Turkoglu I. A biomedical system based on hidden Markov model for diagnosis of the heart valve diseases. Pattern Recognition Letters 2007; 28: 395-404.
  • Dokur Z, Olmez T. Heart sound classification using wavelet transform and incremental self-organizing map. Digital Signal Processing 2008; 18(6): 951-959.
  • Sofwan A, Santoso I, Pradipta H, Arfan M, Zahra MAA. (2019). Normal and murmur heart sound classification using linear predictive coding and k-Nearest neighbor methods. In 2019 3rd International Conference on Informatics and Computational Sciences (ICICoS), 2019.
  • Kaggle dataset, https://www.kaggle.com/kinguistics/heartbeat-sounds
  • Banerjee M, Majhi S. (2020). Multi-class heart sounds classification using 2D-convolutional neural network. In 2020 5th International Conference on Computing, Communication and Security (ICCCS), 2020.
  • Fu W, Yang X, Wang Y. Heart sound diagnosis based on DTW and MFCC. In 3rd International Congress on Image and Signal Processing (CISP2010), 2010, 6(2): 2920-2923.
  • Cayci CY. Müzikal enstrümanların doğrusal ayırtaç analizi yöntemiyle ayırt edilmesi. Yüksek Lisans Tezi, Hacettepe Üniversitesi, Fen Bilimleri Enstitüsü, Ankara, 2007.
  • Cheng O, Abdulla W, Salcic Z. Performance evaluation of front-end algorithms for robust speech recognition. In Proc. ISSPA, 2005.
  • Sillverman BW, Jones MC. An important contribution to nonparametric discriminant analysis and density estimation. International Statistical Review 1951; 57(3): 233-247.
  • Boulares M, Alafif T, Barnawi A. Transfer learning benchmark for cardiovascular disease recognition. IEEE Access 2020; 8: 109475-109491.
  • Narvaez P, Gutierrez S, Percybrooks WS. Automatic segmentation and classification of heart sounds using modified empirical wavelet transform and power features. Applied Sciences 2020; 10: 4791.