Emotion decoding model construction method and prediction method based on intracranial electroencephalogram signals
By constructing an intracranial EEG signal emotion decoding neural network based on LSTM and feature mapping modules, and combining Maxout activation layers and Adam optimizers, the problem of low decoding accuracy caused by ignoring individual differences in existing technologies is solved, and efficient personalized emotion prediction is achieved.
CN120579600BActive Publication Date: 2026-06-16CAPITAL NORMAL UNIVERSITY
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CAPITAL NORMAL UNIVERSITY
- Filing Date
- 2025-05-23
- Publication Date
- 2026-06-16
Smart Images
Figure CN120579600B_ABST
Abstract
The present application relates to the technical field of emotion recognition, in particular to an emotion decoding model construction method and prediction method based on intracranial electroencephalogram signals. In the present application, intracranial electroencephalogram signals are used for emotion decoding, which is more reliable than emotion decoding based on electroencephalogram signals. By constructing a pre-trained emotion decoding model, only a small amount of target user data is needed to complete personalized fine-tuning, and the sample demand is small. At the same time, by performing transfer learning on the pre-trained emotion decoding model, a personalized emotion decoding model is constructed, which can realize accurate personalized emotion prediction of target users.
Need to check novelty before this filing date? Find Prior Art