Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network

Inspired by the neuroscience research results that the human brain can produce dynamic responses to different emotions, a new electroencephalogram (EEG)-based human emotion classification model was proposed, named R2G-ST-BiLSTM, which uses a hierarchical neural network model to learn more discrimina...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pengwei Zhang, Chongdan Min, Kangjia Zhang, Wen Xue, Jingxia Chen
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	EEG emotion recognition spatiotemporal features attention antagonism neural network BiLSTM Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/987fc71566b745dba95a44b8c054b909
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:987fc71566b745dba95a44b8c054b909
record_format	dspace
spelling	oai:doaj.org-article:987fc71566b745dba95a44b8c054b9092021-12-02T11:50:59ZHierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network1662-453X10.3389/fnins.2021.738167https://doaj.org/article/987fc71566b745dba95a44b8c054b9092021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.738167/fullhttps://doaj.org/toc/1662-453XInspired by the neuroscience research results that the human brain can produce dynamic responses to different emotions, a new electroencephalogram (EEG)-based human emotion classification model was proposed, named R2G-ST-BiLSTM, which uses a hierarchical neural network model to learn more discriminative spatiotemporal EEG features from local to global brain regions. First, the bidirectional long- and short-term memory (BiLSTM) network is used to obtain the internal spatial relationship of EEG signals on different channels within and between regions of the brain. Considering the different effects of various cerebral regions on emotions, the regional attention mechanism is introduced in the R2G-ST-BiLSTM model to determine the weight of different brain regions, which could enhance or weaken the contribution of each brain area to emotion recognition. Then a hierarchical BiLSTM network is again used to learn the spatiotemporal EEG features from regional to global brain areas, which are then input into an emotion classifier. Especially, we introduce a domain discriminator to work together with the classifier to reduce the domain offset between the training and testing data. Finally, we make experiments on the EEG data of the DEAP and SEED datasets to test and compare the performance of the models. It is proven that our method achieves higher accuracy than those of the state-of-the-art methods. Our method provides a good way to develop affective brain–computer interface applications.Pengwei ZhangChongdan MinKangjia ZhangWen XueJingxia ChenFrontiers Media S.A.articleEEGemotion recognitionspatiotemporal featuresattentionantagonism neural networkBiLSTMNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	EEG emotion recognition spatiotemporal features attention antagonism neural network BiLSTM Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	EEG emotion recognition spatiotemporal features attention antagonism neural network BiLSTM Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Pengwei Zhang Chongdan Min Kangjia Zhang Wen Xue Jingxia Chen Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
description	Inspired by the neuroscience research results that the human brain can produce dynamic responses to different emotions, a new electroencephalogram (EEG)-based human emotion classification model was proposed, named R2G-ST-BiLSTM, which uses a hierarchical neural network model to learn more discriminative spatiotemporal EEG features from local to global brain regions. First, the bidirectional long- and short-term memory (BiLSTM) network is used to obtain the internal spatial relationship of EEG signals on different channels within and between regions of the brain. Considering the different effects of various cerebral regions on emotions, the regional attention mechanism is introduced in the R2G-ST-BiLSTM model to determine the weight of different brain regions, which could enhance or weaken the contribution of each brain area to emotion recognition. Then a hierarchical BiLSTM network is again used to learn the spatiotemporal EEG features from regional to global brain areas, which are then input into an emotion classifier. Especially, we introduce a domain discriminator to work together with the classifier to reduce the domain offset between the training and testing data. Finally, we make experiments on the EEG data of the DEAP and SEED datasets to test and compare the performance of the models. It is proven that our method achieves higher accuracy than those of the state-of-the-art methods. Our method provides a good way to develop affective brain–computer interface applications.
format	article
author	Pengwei Zhang Chongdan Min Kangjia Zhang Wen Xue Jingxia Chen
author_facet	Pengwei Zhang Chongdan Min Kangjia Zhang Wen Xue Jingxia Chen
author_sort	Pengwei Zhang
title	Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
title_short	Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
title_full	Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
title_fullStr	Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
title_full_unstemmed	Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network
title_sort	hierarchical spatiotemporal electroencephalogram feature learning and emotion recognition with attention-based antagonism neural network
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/987fc71566b745dba95a44b8c054b909
work_keys_str_mv	AT pengweizhang hierarchicalspatiotemporalelectroencephalogramfeaturelearningandemotionrecognitionwithattentionbasedantagonismneuralnetwork AT chongdanmin hierarchicalspatiotemporalelectroencephalogramfeaturelearningandemotionrecognitionwithattentionbasedantagonismneuralnetwork AT kangjiazhang hierarchicalspatiotemporalelectroencephalogramfeaturelearningandemotionrecognitionwithattentionbasedantagonismneuralnetwork AT wenxue hierarchicalspatiotemporalelectroencephalogramfeaturelearningandemotionrecognitionwithattentionbasedantagonismneuralnetwork AT jingxiachen hierarchicalspatiotemporalelectroencephalogramfeaturelearningandemotionrecognitionwithattentionbasedantagonismneuralnetwork
_version_	1718395179515248640

Hierarchical Spatiotemporal Electroencephalogram Feature Learning and Emotion Recognition With Attention-Based Antagonism Neural Network

Ejemplares similares