当前位置: X-MOL 学术Comput. Biol. Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-channel EEG-based emotion recognition via a multi-level features guided capsule network.
Computers in Biology and Medicine ( IF 7.7 ) Pub Date : 2020-07-22 , DOI: 10.1016/j.compbiomed.2020.103927
Yu Liu 1 , Yufeng Ding 1 , Chang Li 1 , Juan Cheng 1 , Rencheng Song 1 , Feng Wan 2 , Xun Chen 3
Affiliation  

In recent years, deep learning (DL) techniques, and in particular convolutional neural networks (CNNs), have shown great potential in electroencephalograph (EEG)-based emotion recognition. However, existing CNN-based EEG emotion recognition methods usually require a relatively complex stage of feature pre-extraction. More importantly, the CNNs cannot well characterize the intrinsic relationship among the different channels of EEG signals, which is essentially a crucial clue for the recognition of emotion. In this paper, we propose an effective multi-level features guided capsule network (MLF-CapsNet) for multi-channel EEG-based emotion recognition to overcome these issues. The MLF-CapsNet is an end-to-end framework, which can simultaneously extract features from the raw EEG signals and determine the emotional states. Compared with original CapsNet, it incorporates multi-level feature maps learned by different layers in forming the primary capsules so that the capability of feature representation can be enhanced. In addition, it uses a bottleneck layer to reduce the amount of parameters and accelerate the speed of calculation. Our method achieves the average accuracy of 97.97%, 98.31% and 98.32% on valence, arousal and dominance of DEAP dataset, respectively, and 94.59%, 95.26% and 95.13% on valence, arousal and dominance of DREAMER dataset, respectively. These results show that our method exhibits higher accuracy than the state-of-the-art methods.



中文翻译:

通过多级功能引导的胶囊网络,基于多通道EEG的情绪识别。

近年来,深度学习(DL)技术,特别是卷积神经网络(CNN),在基于脑电图(EEG)的情感识别中已显示出巨大潜力。但是,现有的基于CNN的EEG情绪识别方法通常需要特征提取的相对复杂阶段。更重要的是,CNN不能很好地表征脑电信号不同通道之间的内在联系,这本质上是识别情绪的关键线索。在本文中,我们提出了一种有效的多级特征引导胶囊网络(MLF-CapsNet),用于基于多通道EEG的情绪识别,以克服这些问题。MLF-CapsNet是一个端到端框架,可以同时从原始EEG信号中提取特征并确定情绪状态。与原始CapsNet相比,它结合了在形成主胶囊时由不同层学习的多层特征图,从而可以增强特征表示的能力。此外,它使用瓶颈层来减少参数数量并加快计算速度。我们的方法在DEAP数据集的价,唤醒和优势上分别达到97.97%,98.31%和98.32%的平均准确度,在DREAMER数据集的价,唤醒和优势上分别达到94.59%,95.26%和95.13%。这些结果表明,我们的方法比最先进的方法具有更高的准确性。它使用瓶颈层来减少参数数量并加快计算速度。我们的方法在DEAP数据集的价,唤醒和优势方面的平均准确率分别达到97.97%,98.31%和98.32%,在DREAMER数据集的价,唤醒和优势方面分别达到94.59%,95.26%和95.13%。这些结果表明,我们的方法比最先进的方法具有更高的准确性。它使用瓶颈层来减少参数数量并加快计算速度。我们的方法在DEAP数据集的价,唤醒和优势方面的平均准确率分别达到97.97%,98.31%和98.32%,在DREAMER数据集的价,唤醒和优势方面分别达到94.59%,95.26%和95.13%。这些结果表明,我们的方法比最先进的方法具有更高的准确性。

更新日期:2020-07-23
down
wechat
bug