Publication detail

Classification of Normal and Abnormal Heart Sounds for Automatic Diagnosis

MISHRA, M. SINGH, A. DUTTA, M. BURGET, R. MAŠEK, J.

Original Title

Classification of Normal and Abnormal Heart Sounds for Automatic Diagnosis

Czech Title

Klasifikace normálních a nenormálních zvuků lidského srdce pro automatickou diagnózu

English Title

Classification of Normal and Abnormal Heart Sounds for Automatic Diagnosis

Type

conference paper

Language

en

Original Abstract

Body auscultation is an easy and non-invasive method for detection of diseases in human body. The conventional method is a bit time consuming and requires professionals for diagnosis. Automatic diagnosis of diseases using heart sound can be of great help in the rural areas where professional help is not available. The proposed work presents an automatic and efficient method of diagnosis and classification using heart sound. Mel Frequency Cepstral Coefficient (MFCC) features are extracted from heart sounds for diagnosis. Supervised classification method is used to separate the normal and abnormal heart sound for detection of diseases. The proposed method was tested on a comprehensive database of heart sounds and achieved accuracy of 97.50 % during classification process. The experiment results indicates that the proposed method is efficient for classification of healthy/unhealthy heart sounds and computationally cheap making it suitable for real time applications.

Czech abstract

Vyšetření lidkého těla na základě zvukového poslechu je jednoduchá neinvazivní metoda, kterou musí vykonávat lékař. V hůře rozvinutých státech, kde není dostatečné množství lékařských pracovníků je možné provádět tato vyšetření s pomocí automatických metod. Na základě analýzy srdečních zvuků lze poté klasifikovat možnou srdeční nemoc.

English abstract

Body auscultation is an easy and non-invasive method for detection of diseases in human body. The conventional method is a bit time consuming and requires professionals for diagnosis. Automatic diagnosis of diseases using heart sound can be of great help in the rural areas where professional help is not available. The proposed work presents an automatic and efficient method of diagnosis and classification using heart sound. Mel Frequency Cepstral Coefficient (MFCC) features are extracted from heart sounds for diagnosis. Supervised classification method is used to separate the normal and abnormal heart sound for detection of diseases. The proposed method was tested on a comprehensive database of heart sounds and achieved accuracy of 97.50 % during classification process. The experiment results indicates that the proposed method is efficient for classification of healthy/unhealthy heart sounds and computationally cheap making it suitable for real time applications.

Keywords

Body auscultation;Heart Sounds;Mel Frequency Cepstral Coefficient;Classification;Support Vector Machine

Released

05.07.2017

Location

Barcelona, Španělsko

ISBN

978-1-5090-3981-4

Book

40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)

Pages from

753

Pages to

757

Pages count

5

BibTex


@inproceedings{BUT137841,
  author="Mohan {Mishra} and Anushikha {Singh} and Malay Kishore {Dutta} and Radim {Burget} and Jan {Mašek}",
  title="Classification of Normal and Abnormal Heart Sounds for Automatic Diagnosis",
  annote="Body auscultation is an easy and non-invasive method for detection of diseases in human body. The conventional method is a bit time consuming and requires professionals for diagnosis. Automatic diagnosis of diseases using heart sound can be of great help in the rural areas where professional help is not available. The proposed work presents an automatic and efficient method of diagnosis and classification using heart sound. Mel Frequency Cepstral Coefficient (MFCC) features are extracted from heart sounds for diagnosis. Supervised classification method is used to separate the normal and abnormal heart sound for detection of diseases. The
proposed method was tested on a comprehensive database of heart sounds and achieved accuracy of 97.50 % during classification process. The experiment results indicates that the proposed method is efficient for classification of healthy/unhealthy heart sounds and computationally cheap making it suitable for real time applications.",
  booktitle="40th Anniversary of International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="137841",
  doi="10.1109/TSP.2017.8076089",
  howpublished="electronic, physical medium",
  year="2017",
  month="july",
  pages="753--757",
  type="conference paper"
}