张小恒^{1, 2},
李勇明^2,,,
王品²,
曾孝平²,
颜芳²,
张艳玲^3,,
承欧梅⁴
1.重庆广播电视大学? ?重庆? ?400052
2.重庆大学通信工程学院? ?重庆? ?400030
3.陆军军医大学西南医院神经内科? ?重庆? ?400038
4.重庆医科大学附一院神经内科? ?重庆? ?400016
基金项目:国家自然科学基金(61771080, 61571069)，重庆市基础与前沿研究项目(cstc2018jcyjAX0779, cstc2016jcyjA0043, cstc2016jcyjA0064, cstc2016jcyjA0134)，重庆市教育委员会科学技术研究项目(KJ1603805)，西南医院联合孵化项目(SWH2016LHYS-11)，模式识别国家重点实验室开放课题基金(201800011)

详细信息

作者简介:张小恒：男，1980年生，副教授，工程师，研究方向为人工智能、生物医学信号与信息处理
李勇明：男，1976年生，教授，博士生导师，研究方向为人工智能、生物医学信号信息处理
王品：女，1979年生，副教授，硕士生导师，研究方向为人工智能、生物医学信号信息处理
曾孝平：男，1956年生，教授，博士生导师，研究方向为人工智能、信号与信息处理
颜芳：男，1979年生，副教授，硕士生导师，研究方向为生物医学信号信息处理
张艳玲：女，1974年生，教授，硕士生导师，研究方向为帕金森病诊疗、生物医学信号信息处理
承欧梅：女，1968年生，教授，博士生导师，研究方向为帕金森病诊疗、生物医学信号信息处理

通讯作者:李勇明　yongmingli@cqu.edu.cn

中图分类号:TP391.42; R749

计量

文章访问数:1108
HTML全文浏览量:364
PDF下载量:44
被引次数:0

出版历程

收稿日期:2018-08-09
修回日期:2019-01-28
网络出版日期:2019-02-23
刊出日期:2019-07-01

Classification Algorithm of Parkinson’s Disease Based on Convolutional Sparse Transfer Learning and Sample/Feature Parallel Selection

Xiaoheng ZHANG^{1, 2},
Yongming LI^2,,,
Pin WANG²,
Xiaoping ZENG²,
Fang YAN²,
Yanling ZHANG^3,,
Oumei CHENG⁴
1. Chongqing Radio & TV University, Chongqing 400052, China
2. College of Communication Engineering, Chongqing University, Chongqing 400030, China
3. Department of Neurology of Southwest Hospital, Army Medical University, Chongqing 400038, China
4. Department of Neurology, The First Affiliated Hospital, Chongqing Medical University, Chongqing 400016, China
Funds:The National Natural Science Foundation of China (61771080, 61571069), The Chongqing Research Program of Basic Research and Frontier Technology(cstc2018jcyjAX0779, cstc2016jcyjA0043, cstc2016jcyjA0064, cstc2016jcyjA0134), The Chongqing Education Commission Science and Technology Research Program (KJ1603805), The Southwest Hospital Science and Technology Innovation Program (SWH2016LHYS-11), The Open Project Program of the National Laboratory of Pattern Recognition (201800011)


摘要
摘要:基于语音数据分析的帕金森病(PD)诊断存在样本量小、训练与测试数据分布差异明显的问题。为了解决这些问题，需要从降维和样本扩充两个方面同时进行。因此，该文提出结合加噪加权卷积稀疏迁移学习和样本特征并行优选的PD分类算法。该算法可从源域的公共语音库中学习有利于表达PD语音特征的有效结构信息，同时完成降维和样本间接扩充。样本特征并行优选考虑到了样本和语音特征间的关系，从而有助于获取高质量的特征。首先，对公共语音库进行特征提取构造公共特征库；然后，以公共特征库对PD目标域的训练数据集及测试数据集进行稀疏编码，这里分别采用传统稀疏编码(SC)与卷积稀疏编码(CSC)两种稀疏编码方法；接着，对编码后的语音样本段和特征数据进行同时优选；最后，采用支撑向量机(SVM)进行分类。实验结果表明，该算法针对受试者的分类准确率最高值达到了95.0%，均值达到了86.0%，较相关被比较算法有较大提高。此外，研究还发现，相较于传统稀疏编码方法，卷积稀疏编码更有利于提取PD语音数据的高层特征；同样，迁移学习也有利于提高该算法性能。
关键词:迁移学习/
帕金森病/
稀疏编码/
卷积稀疏编码/
语音样本特征并行优选
Abstract:To solve the problems that there are few labeled data in speech data for diagnosis of Parkinson’s Disease (PD), and the distributed condition of the training and the test data is different, the two aspects of dimension reduction and sample augment are considered. A novel transfer learning algorithm is proposed based on noise weighting sparse coding combined with speech sample / feature parallel selection. The algorithm can learn the structural information from the source domain and express the effective PD features, and achieves dimension reduction and sample augment simultaneously. Considering the relationship between the samples and features, the higher quality features can be extracted. Firstly, the features are extracted from the public data set and the feature data set is constructed as source domain. Then the training data and test data of the target domain are sparsely represented based on source domain. Spares representing includs traditional Sparse Coding(SC) and Convolutional Sparse Coding(CSC); Next, the sparse representing data are screened according to sample feature selection simultaneously, so as to improve the accuracy of the PD classification; Finally, the Support Vector Machine(SVM) classifier is adopted. Experiments show that it achieves the highest classification accuracy of 95.0% and the average classification accuracy of 86.0%, and obtains obvious improvement according to the subjects, compared with the relevant algorithms. Besides, compared with sparse coding, convolutional sparse coding can be beneficial to extracting high level features from PD data set; moreover, it is proved that transfer learning is effective.
Key words:Transfer learning/
Parkinson’s Disease (PD)/
Sparse Coding (SC)/
Convolutional Sparse Coding (CSC)/
Speech sample feature parallel selection



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=788d80dd-1a9d-49eb-8764-330ad0e40258