Cheng Xiefeng, Wang Pengfei, She Chenjun
College of Electronic and Optical Engineering & College of Microelectronics, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
National and Local Joint Engineering Laboratory of RF Integration & Micro-Assembly Technology, Nanjing 210003, China.
Entropy (Basel). 2020 Feb 20;22(2):238. doi: 10.3390/e22020238.
In this paper, a new method of biometric characterization of heart sounds based on multimodal multiscale dispersion entropy is proposed. Firstly, the heart sound is periodically segmented, and then each single-cycle heart sound is decomposed into a group of intrinsic mode functions (IMFs) by improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). These IMFs are then segmented to a series of frames, which is used to calculate the refine composite multiscale dispersion entropy (RCMDE) as the characteristic representation of heart sound. In the simulation experiments I, carried out on the open heart sounds database Michigan, Washington and Littman, the feature representation method was combined with the heart sound segmentation method based on logistic regression (LR) and hidden semi-Markov models (HSMM), and feature selection was performed through the Fisher ratio (FR). Finally, the Euclidean distance (ED) and the close principle are used for matching and identification, and the recognition accuracy rate was 96.08%. To improve the practical application value of this method, the proposed method was applied to 80 heart sounds database constructed by 40 volunteer heart sounds to discuss the effect of single-cycle heart sounds with different starting positions on performance in experiment II. The experimental results show that the single-cycle heart sound with the starting position of the start of the first heart sound (S1) has the highest recognition rate of 97.5%. In summary, the proposed method is effective for heart sound biometric recognition.
本文提出了一种基于多模态多尺度分散熵的心音生物特征表征新方法。首先，对心音进行周期性分割，然后通过改进的自适应噪声完全集合经验模态分解（ICEEMDAN）将每个单周期心音分解为一组固有模态函数（IMF）。接着将这些IMF分割成一系列帧，用于计算精细复合多尺度分散熵（RCMDE）作为心音的特征表示。在对密歇根、华盛顿和利特曼开放心音数据库进行的模拟实验I中，将该特征表示方法与基于逻辑回归（LR）和隐半马尔可夫模型（HSMM）的心音分割方法相结合，并通过Fisher比率（FR）进行特征选择。最后，使用欧几里得距离（ED）和近邻原则进行匹配和识别，识别准确率为96.08%。为提高该方法的实际应用价值，在实验II中将所提方法应用于由40名志愿者心音构建的80个心音数据库，以探讨不同起始位置的单周期心音对性能的影响。实验结果表明，以第一心音（S1）起始位置开始的单周期心音识别率最高，为97.5%。综上所述，所提方法在心音生物特征识别中是有效的。
