混合语音段特征双边式优选算法用于帕金森病分类研究
近年来,已有研究证明基于语音数据可实现帕金森病（PD）的诊断,但是目前相关研究主要集中在特征提取及分类器设计等方面,对于样本优选方面考虑不足。本课题组前期研究结果表明,样本优选可有效改进分类准确性,但是样本和语音的相关关系至今还未能深入研究。因此,本文提出了基于相关特征加权和多核学习算法,同时对语音段和特征进行优选,用于发现语音段和特征的协同效应,从而达到提升PD分类准确性的目的。实验结果表明,本文算法针对受试者的分类准确率达到了82.5%,较已有文献算法提高了30.5%。此外,本文算法还挖掘出了语音段和特征的协同效应,对语音标记物提取有一定参考价值。...
Saved in:
| Published in | Sheng wu yi xue gong cheng xue za zhi Vol. 34; no. 6; pp. 942 - 948 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese English |
| Published |
中国四川
四川大学华西医院
01.12.2017
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Summary: | 近年来,已有研究证明基于语音数据可实现帕金森病（PD）的诊断,但是目前相关研究主要集中在特征提取及分类器设计等方面,对于样本优选方面考虑不足。本课题组前期研究结果表明,样本优选可有效改进分类准确性,但是样本和语音的相关关系至今还未能深入研究。因此,本文提出了基于相关特征加权和多核学习算法,同时对语音段和特征进行优选,用于发现语音段和特征的协同效应,从而达到提升PD分类准确性的目的。实验结果表明,本文算法针对受试者的分类准确率达到了82.5%,较已有文献算法提高了30.5%。此外,本文算法还挖掘出了语音段和特征的协同效应,对语音标记物提取有一定参考价值。 |
|---|---|
| Bibliography: | Parkinson＇s disease; classification; bilateral hybrid speech feature selection; synergy effects; multiplekernel learning 51-1258/R Diagnosis of Parkinson＇s disease （PD） based on speech data has been proved to be an effective way in recent years. However, current researches just care about the feature extraction and classifier design, and do not consider the instance selection. Former research by authors showed that the instance selection can lead to improvement on classification accuracy. However, no attention is paid on the relationship between speech sample and feature until now. Therefore, a new diagnosis algorithm of PD is proposed in this paper by simultaneously selecting speech sample and feature based on relevant feature weighting algorithm and multiple kernel method, so as to find their synergy effects, thereby improving classification accuracy. Experimental results showed that this proposed algorithm obtained apparent improvement on classification accuracy. It can obtain mean classification accuracy of |
| ISSN: | 1001-5515 |
| DOI: | 10.7507/1001-5515.201704061 |