| Issue |
E3S Web Conf.
Volume 185, 2020
2020 International Conference on Energy, Environment and Bioengineering (ICEEB 2020)
|
|
|---|---|---|
| Article Number | 02007 | |
| Number of page(s) | 4 | |
| Section | Energy Saving and Environmental Protection Technology | |
| DOI | https://doi.org/10.1051/e3sconf/202018502007 | |
| Published online | 01 September 2020 | |
The study of EEG Recognition of Depression on Bi-LSTM based on ERP P300
1 State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300132, China
2 Physical Examination Center of the 983th Hospital of the People's Liberation Army Joint Service Support Force, Tianjin 300142, China
* Corresponding author: fu254@126.com
Depression is a kind of relatively common psychological disease of among people. The extract of EEG feature is to utilize the course of development of better aided diagnosis with depression patients, so as to put forward the accurate treatment options. The traditional machine study is to directly input EEG into Neural Networks and not to consider the influence of time series for data accuracy and Bi-LSTM is not only to inherit the treatment of LSTM to timely constraint, but also combine the influence of two-way factors on neutral network, which has good computing advantage. This essay adopts a kind of the study of EEG recognition of depression on Bi-LSTM based on ERP. Compared with other model, the accuracy rate identification and classification under 16 reaches 80.6% with good credit after the improvement of the Bi- LSTM.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.