EEG-ERnet:基于节奏EEG卷积神经网络模型的情绪识别
Shuang Zhang1,2, Chen Ling3, Jingru Wu3
1Key Laboratory of Numerical Simulation of Sichuan Provincial Universities, School of Mathematics and Information Sciences, Neijiang Normal University, 641000 Neijiang, Sichuan, China.
Journal of integrative neuroscience
|September 8, 2025
概括
这项研究介绍了EEG-ERnet,这是一个新的深度学习模型,用于从脑电图 (EEG) 信号中独立于主体的情绪识别. 该模型通过分析EEG数据中的节奏模式,有效地解码情绪,实现高分类准确度.
科学领域:
- 神经科学是一个神经科学.
- 人工智能的人工智能
- 信号处理 信号处理
背景情况:
- 使用脑电图 (EEG) 识别情绪对于推进脑计算机接口 (BCI) 至关重要.
- 像CNN这样的深度学习模型显示出希望,但在区分大脑节律特征和时间动态方面扎.
- 独立于主体的情绪识别是必要的,因为情绪反应的个体变化.
研究的目的:
- 开发一种新的网络模型,用于从EEG信号中准确且独立于主体的情绪识别.
- 为了解决标准CNN在捕捉独特的大脑节奏和时间变化的局限性.
- 通过考虑个体差异来提高情绪识别系统的性能.
主要方法:
- 提出了一种使用深度平行卷积神经网络 (CNN) 的新型网络模型.
- 从各种大脑节律中提取功率光谱密度 (PSD),并将其投射为2D图像.
- 开发了EEG-ERnet (情感识别网络) 来处理这些节奏图像表示以进行情感分类.
主要成果:
- 证明在5秒间隔内的特定情绪节奏有效支持情绪分类.
- 在DEAP数据集上实现了高平均分类准确率:93.27%的价值,92.16%的兴奋,90.56%的统治,和86.68%的喜欢.
- 通过10倍交叉验证验证模型的有效性.
结论:
- 提供了关于情绪EEG信号节奏特征的宝贵见解.
- EEG-ERnet模型显示了开发高效,独立于主体的情感感知系统的巨大潜力.
- 拟议的模型为便携式和现实世界的情感识别应用铺平了道路.
相关概念视频
01:24ECG Interpretation of Rhythms
12.8K
An electrocardiogram (ECG)graphically represents the heart's electrical activity on ECG paper or a monitor.
Components of the Electrocardiogram
The primary components of a normal ECG waveform in Normal sinus rhythm(NSR) include the P wave, PR interval, QRS complex, ST segment, T wave, and occasionally a U wave.
ECG waveforms are divided by vertical and horizontal lines at standard intervals.
The horizontal axis measures time and rate, and the vertical axis measures amplitude or voltage....
Components of the Electrocardiogram
The primary components of a normal ECG waveform in Normal sinus rhythm(NSR) include the P wave, PR interval, QRS complex, ST segment, T wave, and occasionally a U wave.
ECG waveforms are divided by vertical and horizontal lines at standard intervals.
The horizontal axis measures time and rate, and the vertical axis measures amplitude or voltage....
12.8K
01:25Correlation between ECG and Cardiac Cycle
11.8K
The electrical signals recorded on an electrocardiogram (ECG) occur before the mechanical processes of contraction and relaxation during the cardiac cycle.
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...
11.8K