http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatic heart activity diagnosis based on Gram polynomials and probabilistic neural networks
Francesco Beritelli,Giacomo Capizzi,Grazia Lo Sciuto,Christian Napoli,Francesco Scaglione 대한의용생체공학회 2018 Biomedical Engineering Letters (BMEL) Vol.8 No.1
The paper proposes a new approach to heartactivity diagnosis based on Gram polynomials and probabilisticneural networks (PNN). Heart disease recognition isbased on the analysis of phonocardiogram (PCG) digitalsequences. The PNN provides a powerful tool for properclassification of the input data set. The novelty of theproposed approach lies in a powerful feature extractionbased on Gram polynomials and the Fourier transform. Theproposed system presents good performance obtainingoverall sensitivity of 93%, specificity of 91% and accuracyof 94%, using a public database of over 3000 heart beatsound recordings, classified as normal and abnormal heartsounds. Thus, it can be concluded that Gram polynomialsand PNN prove to be a very efficient technique using thePCG signal for characterizing heart diseases.