EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks and Broad Learning System

Wang, Xuehan; Zhang, Tong; Xu, Xiangmin; Chen, Long; Xing, Xiaofen; Chen, C. L. Philip

doi:10.1109/bibm.2018.8621147

Cited by 80 publications

(34 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy under this dataset is higher than the DEAP dataset. The highest average accuracy could reach 96.77%, which is better than the work in Wang et al ( 2018 ), 90.2%. For the data obtained from time window of 12 s, the best accuracy could reach 94.62%, which shows that PCC-based features exhibit a better performance than others.…”

Section: Datasets and Experimentscontrasting

confidence: 55%

“…In the proposed work, the features are separately extracted in each of the frequency bands (α, β, θ, and γ bands). According to the work in Wang et al ( 2018 ) and other similar researches, data of four frequency bands are used together in order to get the best results. After data are processed, for the data obtained using a time window of 8 s, the shapes of the above three different feature matrixes are 17,920 × 4 × 32 × 32, 17,920 × 4 × 32 × 32, and 17,920 × 4 × 32 × 4, respectively.…”

Section: Datasets and Experimentsmentioning

confidence: 99%

“…The recent study (Tripathi et al, 2017 ) used extracted data for classification, and better accuracy results were obtained by using the CNN, where the classification accuracy of valence and arousal is 81.4 and 73.4%, respectively. The approaches of García et al ( 2016 ) and Wang et al ( 2018 ) used DE-based features and dynamical graph convolutional neural networks, and the accuracy achieved 93.7%. In the approach of Wang et al ( 2019 ), BLSTM and other machine learning classifiers, such as SVM and LR were used for emotion recognition.…”

Section: Datasets and Experimentsmentioning

confidence: 99%

See 2 more Smart Citations

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

Liu

Luo

et al. 2020

Front. Syst. Neurosci.

176

View full text Add to dashboard Cite

Emotion classification based on brain–computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN.

show abstract

Section: Datasets and Experimentscontrasting

confidence: 55%

Section: Datasets and Experimentsmentioning

confidence: 99%

Section: Datasets and Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

Liu

Luo

et al. 2020

Front. Syst. Neurosci.

176

View full text Add to dashboard Cite

show abstract

“…Liu [17] proposed GBLS for image classification. Wang et al [18] applied BLS to the emotional classification. Although the BLS is widely applied in various fields, it is mainly used in supervised classification tasks.…”

Section: Introductionmentioning

confidence: 99%

A Novel Broad Learning Model-Based Semi-Supervised Image Classification Method

2020

View full text Add to dashboard Cite

Broad learning system (BLS) is an effective and efficient incremental learning system without the deep architecture. It has strong feature extraction ability and high computational efficiency. However, it is greatly limited in the applicability of supervised learning. For the collected actual data, more data are unlabeled data and less data are labeled data. To overcome these problems, Fick's law assisted propagation (FLAP) is introduced into the BLS to propose a new semi-supervised classification algorithm, namely FLAP-BLS in this paper. In the FLAP-BLS, the FLAP has the labeled ability from the labeled examples to unlabeled examples, it is used to mark plenty of unlabeled samples by few labeled samples in order to obtain a large number of labeled samples and build the sample data matrix. Then an efficient incremental BLS without deep structure can effectively extract features from large-scale data, it is used to effectively classify the sample matrix. Finally, USPS, MNIST and NORB datasets are selected to validate the effectiveness of the FLAP-BLS. The experiment results show that the FLAP-BLS can effectively classify the few labeled samples and a large of unlabeled samples and obtain classification results with high accuracy, and it has faster classification speed, stronger generalization ability and better stability. The proposed method provides a new method for image classification.

show abstract

“…Furthermore, since the gradientbased approach is used to optimize the cost function, the model is prone to fall into local minima [19]. The weight and structure determination (WASD)-based method obtains the weight matrix through the pseudo-inverse method, which reduces the iterative process and is therefore faster than the gradient-based method [18], [20]. Differing from existing WASD-based methods, in the weight and structure determination neural network aided with double pseudoinversion (WASDNN-DP) proposed in this paper, the weights between the hidden layer and the output layer are first randomly generated, then after the weights between the input layer and the hidden layer are determined by the pseudo-inverse method, the weights between the hidden layer and the output layer are re-determined also by the pseudo-inverse method.…”

Section: Introductionmentioning

confidence: 99%

Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot

Chen

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Deep learning models often have complicated structures with low computational speed and the requirement of a large amount of storage space, which limits their own practical application on some devices with insufficient computing power. This paper proposes the weight and structure determination neural network aided with double pseudoinversion (WASDNN-DP) that can overcome these shortcomings. First, the model structure, theoretical bases, and the algorithms of WASDNN-DP are given. In the process of constructing the network, the weight matrix between the hidden layer and the output layer is first randomly generated. After the weight matrix between the input layer and the hidden layer is analytically determined, the weight matrix between the hidden layer and the output layer is re-determined by the pseudo-inverse method. Furthermore, in WASDNN-DP, the structure of the neural network is determined by a progressive method. Subsequently, based on two datasets collected from children aged 7-15 years by using smart insoles, the comparative experiments between WASDNN-DP and some other machine learning models are carried out, which illustrate the superiority of the proposed WASDNN-DP in the diagnosis of flat foot. INDEX TERMS Classification algorithms, feedforward neural networks, weight and structure determination (WASD), computer aided diagnosis.

show abstract

EEG Emotion Recognition Using Dynamical Graph Convolutional Neural Networks and Broad Learning System

Cited by 80 publications

References 21 publications

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

A Novel Broad Learning Model-Based Semi-Supervised Image Classification Method

Weight and Structure Determination Neural Network Aided With Double Pseudoinversion for Diagnosis of Flat Foot

Contact Info

Product

Resources

About