基于熵和支持向量机的病态嗓音识别

doi:10.3969/j.issn.0258-8021.2013. 05.06

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (594 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为了更好地分析实际短数据带噪的病态嗓音信号，利用近年来提出的样本熵、多尺度熵、模糊熵和分层熵的方法来提取嗓音的熵特征参数，并借鉴分层分解方法，提出分层多尺度熵和分层模糊熵，分别对测试集39例正常嗓音和36例病态嗓音进行支持向量机（SVM）识别。实验结果表明：三层分层熵、分层多尺度熵、分层模糊熵的识别率和稳定性均较分层前有提高。在耗时较短的情况下，提取2 000点病理嗓音数据的6种熵特征都能达到较好且较稳定的识别率。提取2 000点病理嗓音数据的三层分层模糊熵特征，能得到较好且较稳定的SVM识别率97.33%，较分层前的模糊熵特征识别率提高约4.00%。熵分析方法可推进病态嗓音研究向临床的应用，为临床分析诊断实时、短数据的带噪病理嗓音提供一定的参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	赵冰心胡维平^*

关键词 ：病态嗓音, 模糊熵, 分层熵, 支持向量机

Abstract：To solve the problems of short data and noisy recordings in pathological voice signals, this paper extracted some entropy feature parameters of pathological voice proposed in recent years, including sample entropy, multiscale entropy, fuzzy entropy and hierarchical entropy. Based on hierarchical decomposition method, we developed hierarchical multiscale entropy and hierarchical fuzzy entropy. Support vector machine (SVM) was used to distinguish the test set including 39 cases of normal and 36 cases of pathological voices. Results showed that three level hierarchical entropy，hierarchical multiscale entropy and hierarchical fuzzy entropy all achieved higher recognition rates and better stabilities using the proposed method. Pathological voice’s three level hierarchical fuzzy entropy feature got a better and more stable SVM recognition rate of 97.33% by extracting 2000 points. Compared with fuzzy entropy, the recognition rate was increased about 4.00%. The entropy method provide valuable preference for clinical analysis of short pathological voice time series contaminated by noise, which is benefit for clinical application of pathological voice analysis.

Key words： pathological voice fuzzy entropy hierarchical entropy support vector machine (SVM)

基金资助:广西自然科学基金（2010GXNSFA013128）

引用本文:

赵冰心胡维平^*. 基于熵和支持向量机的病态嗓音识别[J]. 中国生物医学工程学报, 2013, 32(5): 546-552.
ZHAO Bing Xin HU Wei Ping^*. Recognition of Pathological Voice Based on Entropy and Support Vector Machine. journal1, 2013, 32(5): 546-552.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2013. 05.06 或 http://cjbme.csbme.org/CN/Y2013/V32/I5/546

［1］GodinoLlorente JI, GomezVilda P, BlancoVelasco M. Dimensionality reduction of a pathological voice quality assessment system based on gaussian mixture models and shortterm cepstral parameters［J］. IEEE Trans Biomed Eng, 2006,53(10): 1943-1953.
［2］Palumbo A, Amato F, Calabrese B, et al. A novel portable device for pathological voice analysis［C］// International Workshop on Medical Measurements and Applications. Cetraro: IEEE,2009:51-54.
［3］Mitev P, Hadjitodorov S. Fundamental frequency estimation of voice of patients with laryngeal disorders［J］. Information Sciences, 2003,156(1-2):3-19.
［4］Umapathy K, Krishnan S,Parsa V, et al.Discrimination of pathological voices using a timefrequency approach［J］. IEEE Transactions on Biomedical Engineering, 2005,52(3):421-430.
［5］Alonso JB,Díaz F,Travieso CM, et al.Using nonlinear features for voice disorder detection［C］// 3rd Int Conf Nonlinear Speech Process.Barcelona : Speech Communication, 2005:94-106.
［6］Henríquez P,Alonso JB,Ferrer MA, et al. Characterization of healthy and pathological voice through measures based on nonlinear dynamics［J］. IEEE Transactions on Audio, Speech, and Language Processing,2009,17(6):1186-1195.
［7］高俊芬, 胡维平. 基于非线性动力学和高斯混合模型/支持向量机的病态嗓音识别与研究［J］. 生物医学工程学杂志,2012,29(4):750-753.
［8］于燕平，胡维平. 病态嗓音特征的神经网络选择［J］. 中国生物医学工程学报,2009,28(3):327-331.
［9］Pincus SM. Approximate entropy as a measure of system complexity［J］. Proc Natl Acad Sci USA,1991,88(6):2297-2301.
［10］Richman JS, Moorman JR. Physiological timeseries analysis using approximate entropy and sample entropy［J］. Am J Physio:Heart Circ Physiol, 2000,278(6):H2039-H2049.［11］Costa M, Goldberger AL, Peng CK. Multiscale entropy analysis of complex physiologic time series［J］. Phys Rev Lett,2002,89(6):068102.
［12］Chen Weiting, Wang Zhizhong, Xie Hongbo, et al. Characterization of surface EMG signal based on fuzzy entropy［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering,2007,15(2):266-272.
［13］Jiang Ying, Peng CK, Xu Yuesheng. Hierarchical entropy analysis for biological signals［J］. Journal of Computational and Applied Mathematics, 2011, 236(5): 728-742.
［14］Lake DE, Richman JS, Griffin MP, et al. Sample entropy analysis of neonatal heart rate variability［J］. Am J Physio Regul Integr Comp Physio, 2002,283(3):789-797.
［15］Chen Weiting, Zhang Jun, Yu Wangxin, et al. Measuring complexity using FuzzyEn, ApEn, and SampEn ［J］. Medical Engineering & Physics, 2009, 31(1):61-68.
［16］Xie Hongbo, Chen Weiting, He Weixing, et al. Complexity analysis of the biomedical signal using fuzzy entropy measurement ［J］. Applied Soft Computing, 2011, 11(2) 2871-2879.
［17］Saeedi NE, Almasganj F, Torabinejad F. Support vector wavelet adaptation for pathological voice assessment ［J］. Comput Biol Med, 2011, 41 (9): 822-828.