Objective:PCG represents the acoustic replay of heart sounds from the cardiac structure.To detect and analyse the different conditions of the heart,heart sound signals are essential.CVD is detected by classifiers who ...Objective:PCG represents the acoustic replay of heart sounds from the cardiac structure.To detect and analyse the different conditions of the heart,heart sound signals are essential.CVD is detected by classifiers who superficially identify the cardiac features.Abnormal sounds in systole or diastole could indicate valve stenosis or regurgitation.The presence of S3 or S4 sounds could indicate heart failure or stiffening of the heart muscle.This paper proposes a CVD detection technique using improved WST and DA classifiers.Method:The PCG was obtained from the Physionet dataset.The raw signals were pre-processed using 2D DCT.The 2D DCT was applied to a matrix containing 3000 sounds with 10000 samples.The DCT matrix was then filtered using a 20Hz–190 Hz Type II Chebyshev filter to remove the high frequency noise above 190 Hz.After filtering,the denoised PCG matrix was obtained from the DCT matrix using inverse 2D DCT.The PCG matrix was feature extracted using WST.WST produces low-frequency components by using the LPFs to filter high-frequency components.These features were then used with the DA classifier to predict the CVD.The DA classifier uses discriminant analysis pattern classification.The DA classifier learns the training PCG pattern,from WST features,and then classifies test samples as normal or abnormal.Results:The proposed method removed noise up to 99%.The 2D DCT filter provided an average noise improvement of 37.34 dB.Further tuning in filter order or attenuation level resulted in distortion of the PCG,and noise improvement declined.The DCT filter removed up to 99%of noise as per the SNR estimation.The improved WST and the DA classifier resulted in an accuracy of 99.63%.Conclusion:Comparative analysis with DNN,advocates the superiority of the proposed method.DNN classifiers provide accurate CVD classification but require a more expensive and complex GPU.The DA classifier requires only a CPU.This work demonstrated that superior CVD classification was obtained using a combination of WST features and the DA classifier with 94%accuracy.展开更多
文摘Objective:PCG represents the acoustic replay of heart sounds from the cardiac structure.To detect and analyse the different conditions of the heart,heart sound signals are essential.CVD is detected by classifiers who superficially identify the cardiac features.Abnormal sounds in systole or diastole could indicate valve stenosis or regurgitation.The presence of S3 or S4 sounds could indicate heart failure or stiffening of the heart muscle.This paper proposes a CVD detection technique using improved WST and DA classifiers.Method:The PCG was obtained from the Physionet dataset.The raw signals were pre-processed using 2D DCT.The 2D DCT was applied to a matrix containing 3000 sounds with 10000 samples.The DCT matrix was then filtered using a 20Hz–190 Hz Type II Chebyshev filter to remove the high frequency noise above 190 Hz.After filtering,the denoised PCG matrix was obtained from the DCT matrix using inverse 2D DCT.The PCG matrix was feature extracted using WST.WST produces low-frequency components by using the LPFs to filter high-frequency components.These features were then used with the DA classifier to predict the CVD.The DA classifier uses discriminant analysis pattern classification.The DA classifier learns the training PCG pattern,from WST features,and then classifies test samples as normal or abnormal.Results:The proposed method removed noise up to 99%.The 2D DCT filter provided an average noise improvement of 37.34 dB.Further tuning in filter order or attenuation level resulted in distortion of the PCG,and noise improvement declined.The DCT filter removed up to 99%of noise as per the SNR estimation.The improved WST and the DA classifier resulted in an accuracy of 99.63%.Conclusion:Comparative analysis with DNN,advocates the superiority of the proposed method.DNN classifiers provide accurate CVD classification but require a more expensive and complex GPU.The DA classifier requires only a CPU.This work demonstrated that superior CVD classification was obtained using a combination of WST features and the DA classifier with 94%accuracy.
