试用软件

What is the reason for such low classification accuracy? How can I overcome this problem?

6 次查看（过去 30 天）

显示更早的评论

Sean Goulding 2022-3-23

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1678529-what-is-the-reason-for-such-low-classification-accuracy-how-can-i-overcome-this-problem

回答： yanqi liu 2022-3-24

For context, I am working with a dataset for diagnosing AD patients using their EEG recordings. Using a train test split on different epochs produced very high accuracy. However, when computing the train test split by subject, my validation accuracy is incredibly low. Do you have any suggestions for how I can overcome this problem?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

yanqi liu 2022-3-24

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1678529-what-is-the-reason-for-such-low-classification-accuracy-how-can-i-overcome-this-problem#answer_925499

yes，sir，may be it is overfitting，so add some batch normal or dropout in layers to retrain the model

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

类别

Sciences Neuroscience Human Brain Mapping EEG/MEG/ECoG

在 Help Center 和 File Exchange 中查找有关 EEG/MEG/ECoG 的更多信息

标签

产品

版本

R2019a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Translated by

试用软件