EEG-Based Emotion Recognition of Deaf Subjects by Integrated Genetic Firefly Algorithm

Tian, Zekun; Li, Dahua; Song, Yu; Gao, Qiang; Kang, Qiaoju; Yang, Yi

doi:10.1109/tim.2021.3121473

Cited by 20 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high-frequency bands (Beta, Gamma) have higher emotion recognition performance compared to the low-frequency bands (Delta, Theta, Alpha), and the recognition performance of the Gamma band is about 10% higher than the classification results of Delta and Theta bands, indicating that emotions have more obvious changes in the high-frequency bands. This result is generally consistent with previous findings that part of the research indicates emotional information is mainly concentrated in the high-frequency bands (Beta, Gamma) [33].…”

Section: Discussionsupporting

confidence: 93%

Domain-Adaptive Emotion Recognition Based on Horizontal Vertical Flow Representation of EEG Signals

Bai

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the development of cognitive science and brain science, brain-computer interface technology can use Electroencephalogram (EEG) signals to better represent the inner changes of emotions. In this paper, A video-induced emotional stimulation experimental paradigm was designed, and the EEG signals of 15 hearing-impaired subjects under three emotions (positive, neutral, and negative) were collected. Considering the flow diffusion properties of EEG signals, we used the diffusion effect based on horizontal representation and vertical representation forms to obtain the spatial domain features. After EEG preprocessing, the differential entropy feature (DE) in the frequency domain is extracted. The frequency domain features of 62 channels are delivered to two Bi-directional Long Short-Term Memory (BiLSTM) to obtain spatial domain features of horizontal and vertical representations respectively, and then two kinds of domain features are fused by the residual network. The attention mechanism is applied to effectively extract emotional representational information from the fused features. To solve the cross-subject problem of emotion recognition, the domain adaptation method is utilized, and a center alignment loss function is applied to increase the distance of inter-class and reduce the distance of intra-class. According to the experimental results, the average accuracies of 75.89% (subject-dependent) and 69.59% (cross-subject) are obtained. Moreover, the validation was also performed on the public dataset SEED, achieving average accuracies of 93.99% (subject-dependent) and 84.22% (cross-subject), respectively.

show abstract

Section: Discussionsupporting

confidence: 93%

Domain-Adaptive Emotion Recognition Based on Horizontal Vertical Flow Representation of EEG Signals

Bai

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Current methods of emotion induction mainly stimulate subjects through pictures [ 20 ], audio [ 21 ], and video [ 22 ] to obtain corresponding emotional EEG signals. According to the mirror neuron theory [ 23 ], when people observe another person performing a certain activity, their own brain activity is also as if they were performing the process.…”

Section: Methodsmentioning

confidence: 99%

Image-Evoked Emotion Recognition for Hearing-Impaired Subjects with EEG Signals

Zhu

Jin

Bai

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

In recent years, there has been a growing interest in the study of emotion recognition through electroencephalogram (EEG) signals. One particular group of interest are individuals with hearing impairments, who may have a bias towards certain types of information when communicating with those in their environment. To address this, our study collected EEG signals from both hearing-impaired and non-hearing-impaired subjects while they viewed pictures of emotional faces for emotion recognition. Four kinds of feature matrices, symmetry difference, and symmetry quotient based on original signal and differential entropy (DE) were constructed, respectively, to extract the spatial domain information. The multi-axis self-attention classification model was proposed, which consists of local attention and global attention, combining the attention model with convolution through a novel architectural element for feature classification. Three-classification (positive, neutral, negative) and five-classification (happy, neutral, sad, angry, fearful) tasks of emotion recognition were carried out. The experimental results show that the proposed method is superior to the original feature method, and the multi-feature fusion achieved a good effect in both hearing-impaired and non-hearing-impaired subjects. The average classification accuracy for hearing-impaired subjects and non-hearing-impaired subjects was 70.2% (three-classification) and 50.15% (five-classification), and 72.05% (three-classification) and 51.53% (five-classification), respectively. In addition, by exploring the brain topography of different emotions, we found that the discriminative brain regions of the hearing-impaired subjects were also distributed in the parietal lobe, unlike those of the non-hearing-impaired subjects.

show abstract

“…Currently, the commonly used feature selection methods are the Filter, the Wrapper, and the Embedded. The Wrapper method considers the dependencies between features and is widely used in the field of feature selection [35,36]. The Wrapper method uses the error on the learner to evaluate each selected feature subset.…”

Section: B Feature Selectionmentioning

confidence: 99%

Scientific Reports Shore Power Load Forecasting based on a Novel Transformer Method with Feature Selection

Zuo

et al. 2022

Preprint

View full text Add to dashboard Cite

Shipping plays an important role in transporting goods, but it also brings air pollution such as nitrogen and sulfur compounds. Meanwhile, shore power can provide daily work power for ships calling at ports, and it can reduce the pollution of the port. Load forecasting of shore power plays an important role in power decision-making. In this work, we proposed a load forecasting model based on the Transformer and the conditional generation. The Firefly Algorithm (FA) was designed to extract the represented condition features. The proposed shore power transformer (SP-T) method adopts the probability distribution of the target load as the prediction results. The two sub-models, SP-T-1 and SP-T-2, were used to predict the Gaussian distribution parameters μ and σ, respectively. It allowed decision-makers to set the confidence level to obtain the range of predicted values according to the actual situation. To evaluate the proposed model, we used 328 power load data (about 18568.4 hours) of different ships that berth at Zhenjiang Port with shore power. The experimental results showed that SP-T can effectively predict the load data of shore power, with an average P50RMSE was 46.997 and an average P90RMSE was 34.822.

show abstract

EEG-Based Emotion Recognition of Deaf Subjects by Integrated Genetic Firefly Algorithm

Cited by 20 publications

References 36 publications

Domain-Adaptive Emotion Recognition Based on Horizontal Vertical Flow Representation of EEG Signals

Domain-Adaptive Emotion Recognition Based on Horizontal Vertical Flow Representation of EEG Signals

Image-Evoked Emotion Recognition for Hearing-Impaired Subjects with EEG Signals

Scientific Reports Shore Power Load Forecasting based on a Novel Transformer Method with Feature Selection

Contact Info

Product

Resources

About