EEG cognitive state evaluation method based on privacy protection

The invention discloses an EEG cognitive state evaluation method based on privacy protection. The method comprises the following steps: firstly, processing obtained data, and then carrying out feature extraction and feature fusion to obtain a required feature vector; secondly, a training set and a t...

Full description

Saved in:
Bibliographic Details
Main Authors LI ZHONGZHENG, ZENG HONG, OUYANG YU, GUO YARU, KONG XINNI, LIU YU, CHENG WENJIE
Format Patent
LanguageChinese
English
Published 09.08.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DIAGNOSIS
ELECTRIC DIGITAL DATA PROCESSING
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
MEDICAL OR VETERINARY SCIENCE
PHYSICS
SURGERY
Online AccessGet full text

Cover

More Information
Summary:The invention discloses an EEG cognitive state evaluation method based on privacy protection. The method comprises the following steps: firstly, processing obtained data, and then carrying out feature extraction and feature fusion to obtain a required feature vector; secondly, a training set and a test set are divided under the inter-subject and cross-subject conditions; a distributed architecture is used for cooperatively training models for a plurality of EEG private data holders, multiple models are used for predicting the cognitive state of a subject, and a cognitive score is calculated; meanwhile, a new model performance evaluation index extreme error rate E2R is added in the verification stage, and the effectiveness of the method is verified through reduction of the E2R. On the premise of protecting EEF privacy, an efficient cognitive state evaluation model is trained, and in combination with the advantage that a plurality of models can be obtained through distributed learning, multi-model collaborative
Bibliography:Application Number: CN20241099431