文献类型：期刊文献

英文题名：FLDNet: Frame-Level Distilling Neural Network for EEG Emotion Recognition

作者：Wang, Zhe[1,2];Gu, Tianhao[1,2];Zhu, Yiwen[2];Li, Dongdong[2];Yang, Hai[2];Du, Wenli[2]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2021

卷号：25

期号：7

起止页码：2533

外文期刊名：IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS

收录：;EI(收录号：20210309771480);WOS:【SCI-EXPANDED(收录号:WOS:000678341200018)】；

基金：This work was supported by Shanghai Science and Technology Program "Distributed and generative few-shot algorithm and theory research" under Grant No.20511100600, the Natural Science Foundation of China under Grant No.62076094, Key Lab of Information Network Security of Ministry of Public Security (The Third Research Institute of Ministry of Public Security) under Grant No. C20603, National Key Research and Development Project of Ministry of Science and Technology of China under Grant No. 2018AAA0101302, Natural Science Foundations of China under Grant No. 61806078, National Major Scientific and Technological Special Project for "Significant New Drugs Development" under Grant No. 2019ZX09201004, Zhejiang Lab under Grant No. 2019ND0AB01.

语种：英文

外文关键词：Electroencephalography; Emotion recognition; Feature extraction; Logic gates; Brain modeling; Training; Correlation; Knowledge distillation; self-attention; teacher-student structure; neural network; EEG emotion recognition

摘要：Based on the current research on EEG emotion recognition, there are some limitations, such as hand-engineered features, redundant and meaningless signal frames and the loss of frame-to-frame correlation. In this paper, a novel deep learning framework is proposed, named the frame-level distilling neural network (FLDNet), for learning distilled features from the correlations of different frames. A layer named the frame gate is designed to integrate weighted semantic information on multiple frames to remove redundant and meaningless signal frames. A triple-net structure is introduced to distill the learned features net by net to replace the hand-engineered features with professional knowledge. Specifically, one neural network is normally trained for several epochs. Then, a second network of the same structure will be initialized again to learn the extracted features from the frame gate of the first neural network based on the output of the first net. Similarly, the third net improves the features based on the frame gate of the second network. To utilize the representation ability of the triple neural network, an ensemble layer is conducted to integrate the discriminative ability of the proposed framework for final decisions. Consequently, the proposed FLDNet provides an effective method for capturing the correlation between different frames and automatically learn distilled high-level features for emotion recognition. The experiments are carried out in a subject-independent emotion recognition task on public emotion datasets of DEAP and DREAMER benchmarks, which have demonstrated the effectiveness and robustness of the proposed FLDNet.