Mondal Ashok, Banerjee Poulami, Somkuwar Ajay
Department of Electronics and Communication Engineering, National Institute of Technology, Bhopal, India.
Department of Electronics and Communication Engineering, National Institute of Technology, Bhopal, India.
Comput Methods Programs Biomed. 2017 Feb;139:119-136. doi: 10.1016/j.cmpb.2016.10.025. Epub 2016 Nov 4.
There is always heart sound (HS) signal interfering during the recording of lung sound (LS) signals. This obscures the features of LS signals and creates confusion on pathological states, if any, of the lungs. In this work, a new method is proposed for reduction of heart sound interference which is based on empirical mode decomposition (EMD) technique and prediction algorithm.
In this approach, first the mixed signal is split into several components in terms of intrinsic mode functions (IMFs). Thereafter, HS-included segments are localized and removed from them. The missing values of the gap thus produced, is predicted by a new Fast Fourier Transform (FFT) based prediction algorithm and the time domain LS signal is reconstructed by taking an inverse FFT of the estimated missing values.
The experiments have been conducted on simulated and recorded HS corrupted LS signals at three different flow rates and various SNR levels. The performance of the proposed method is evaluated by qualitative and quantitative analysis of the results.
It is found that the proposed method is superior to the baseline method in terms of quantitative and qualitative measurement. The developed method gives better results compared to baseline method for different SNR levels. Our method gives cross correlation index (CCI) of 0.9488, signal to deviation ratio (SDR) of 9.8262, and normalized maximum amplitude error (NMAE) of 26.94 for 0 dB SNR value.
在肺音（LS）信号记录过程中，总是存在心音（HS）信号干扰。这会掩盖LS信号的特征，并在肺部存在任何病理状态时造成混淆。在这项工作中，提出了一种基于经验模态分解（EMD）技术和预测算法的心音干扰消除新方法。
在这种方法中，首先将混合信号根据固有模态函数（IMF）分解为几个分量。此后，定位并去除包含HS的片段。由此产生的间隙的缺失值，通过一种基于快速傅里叶变换（FFT）的新预测算法进行预测，并且通过对估计的缺失值进行快速傅里叶逆变换来重建时域LS信号。
在三种不同流速和各种信噪比水平下，对模拟和记录的受HS干扰的LS信号进行了实验。通过对结果的定性和定量分析来评估所提出方法的性能。
发现所提出的方法在定量和定性测量方面优于基线方法。对于不同的信噪比水平，所开发的方法与基线方法相比给出了更好的结果。对于0 dB信噪比的值，我们的方法给出的互相关指数（CCI）为0.9488，信号偏差比（SDR）为9.8262，归一化最大幅度误差（NMAE）为26.94。
