基于SDAE与RELM的EEG情感识别方法

EEG Emotion Recognition Method Based on SDAE and RELM

针对情感识别中堆叠式自动编码器存在反向传播方法收敛速度慢和容易陷入局部最优的问题,提出一种基于堆叠式降噪自动编码器(SDAE)和正则化极限学习机(RELM)的情感状态识别方法。从脑电信号的时域、频域和时频域中提取表征情感状态的初始特征,使用SDAE进行无监督特征学习,提取初始特征的高层抽象表示。在网络的回归层,使用RELM进行情感分类。在DEAP数据集上的实验结果表明,与SDAE以及DT、KNN等传统基于机器学习的方法相比,该方法在实时性、准确性和泛化性能等方面均有明显提升。

The Stacked Auto-Encoders(SAE)used by the existing emotion recognition methods are limited by the low convergence speed at the back propagation stage,and tend to fall into local optimality.To address the problem,an emotion recognition method is proposed based on Stacked Denoising Auto-Encoder(SDAE)and Regularized Extreme Learning Machine(RELM).The method first requires the extraction of the initial features that characterize the emotional state from the time domain,frequency domain,and time-frequency domain of the Electroencephalogram(EEG)signals.Then SDAE is used for unsupervised feature learning to extract high-level abstract representations of the initial features.In the regression layer of the network,RELM is used for emotion classification.The experimental results on the DEAP data set show that the proposed method displays significant improvements in real-time performance,accuracy and generalization performance compared with SDAE,DT,KNN and other machine learning-based methods.