脑电图
计算机科学
情绪识别
唤醒
语音识别
比例(比率)
价(化学)
人工智能
模式识别(心理学)
情绪分类
卷积(计算机科学)
认知心理学
信号(编程语言)
情感配价
大脑活动与冥想
认知
序列(生物学)
心理学
动力学(音乐)
同步脑电与功能磁共振
特征提取
作者
Zhe Tao,Guanghao Huang,Leilei Ma,Zhuochao Chen,Yinhua Liu,Keum‐Shik Hong
出处
期刊:Brain Informatics
[Springer Science+Business Media]
日期:2026-06-03
卷期号:13 (1): 22-
被引量:2
标识
DOI:10.1186/s40708-026-00309-x
摘要
Electroencephalography (EEG) provides a non-invasive, portable, and cost-effective solution for emotion classification, but existing methods often struggle to capture spatial-spectral dependencies and multi-temporal scale dynamics inherent in EEG signals. This paper proposes a spectral-spatial attention multi-temporal scale network (SSA-MTSNet) to address these challenges. The SSA-MTSNet integrates 3 components: a spectral-spatial attention module, a multi-temporal scale spatio-temporal convolution module, and a long short-term memory (LSTM) module. First, the SSA-MTSNet preserves electrode topology and simultaneously enhances EEG signal frequencies and interactions among brain regions through attention mechanisms. Then, short- and long-term emotional cues are captured using multi-temporal scale convolution, followed by sequence modeling with LSTM. Evaluated on the SEED and SEED-IV datasets, the SSA-MTSNet achieves average accuracies of 98.34% and 91.79% respectively, and 95.13% and 95.30% on the valence and arousal classification tasks of DEAP, respectively. These results suggest that the proposed model achieves competitive performance across different experimental paradigms and emotion labeling strategies by jointly modeling complementary spectral, spatial, and temporal EEG information for emotion recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI