Residual-network-based deep learning for Parkinson’s disease classification using vocal datasets
Residual-network-based deep learning for Parkinson’s disease classification using vocal datasets
复制标题
使用声音数据集进行帕金森病分类的基于残差网络的深度学习
DOI：
10.1109/lifetech52111.2021.9391925
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Y.
中科院分区：
文献类型：
--
作者：
Ogawa;M.;Yang;Y.
对于帕金森病的诊断和早期检测，需要一种基于观察到的异常运动体征的非侵入性方法。因此，在本文中，一个10层的一维卷积神经网络（CNN）和新型残差网络类型的一维CNN被引入帕金森病分类使用声乐特征数据集。由此产生的残差网络提供了良好的分类结果，精度为0.888，F-测量为0.928，MCC为0.692。
For the diagnosis and early detection of Parkinson's disease, a noninvasive method based on observed abnormal motor signs is desired. Therefore, in this paper, a 10-layered 1-d convolutional neural network (CNN) and novel-residual-network-type 1-d CNN were introduced for Parkinson's disease classification using vocal feature datasets. The resulting residual network provided a good classification result with an accuracy of 0.888, F-measure of 0.928, and MCC of 0.692.