Sen Ipek, Saraclar Murat, Kahya Yasemin P
Department of Electrical and Electronics Engineering, Bogazici University, Istanbul, Turkey.
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:3670-3. doi: 10.1109/IEMBS.2010.5627651.
The aim of this study is to devise a methodology to estimate and depict the source locations of respiratory adventitious sound components in the lungs, particularly crackles, associated with certain pulmonary diseases. Using the multichannel respiratory sound signals recorded on the chest wall, we have tried to locate the sources of crackling sounds. The source localization is performed using basic independent component analysis (basic ICA) followed by an evaluation of the mixing coefficients in a center of weights approach, where after the ICA, by taking the relevant mixing matrix coefficients and assuming them to be placed on the microphone locations, the estimated sound source location is calculated as the center of those weights. In order to select both the proper data segments prior to the ICA, and the relevant independent component (IC) among the source signal estimates of the ICA subsequently, a Bayesian classifier (under the assumption of Gaussian likelihoods) has been trained, using the data of the same subject yet a different acquisition session from the one intended for source localization. The outcome of the algorithm is a map of estimated source locations of crackles with respect to the microphone locations, which is presented together with the error performances (both validation and test) of the classifier. This approach for the estimation and mapping of the adventitious sound source locations in the lungs using the acoustic data may be a promising imaging alternative, which is practical, non-expensive and harmless.
本研究的目的是设计一种方法，用于估计和描绘肺部呼吸附加音成分（特别是与某些肺部疾病相关的啰音）的源位置。利用记录在胸壁上的多通道呼吸声信号，我们试图定位啰音的来源。源定位是通过基本独立成分分析（basic ICA）进行的，随后采用重心法对混合系数进行评估，即在ICA之后，通过获取相关混合矩阵系数并假设它们位于麦克风位置，将估计的声源位置计算为这些权重的中心。为了在ICA之前选择合适的数据段，并在ICA的源信号估计中随后选择相关的独立成分（IC），我们使用来自同一受试者但与用于源定位的采集会话不同的采集会话的数据，训练了一个贝叶斯分类器（在高斯似然假设下）。该算法的结果是相对于麦克风位置的啰音估计源位置图，并与分类器的误差性能（验证和测试）一起呈现。这种利用声学数据估计和绘制肺部附加声源位置的方法可能是一种很有前景的成像替代方法，它实用、成本低且无害。
