Emotion Recognition from Multi-Channel EEG through Parallel Convolutional Recurrent Neural Network

Yang, Yilong; Wu, Qingfeng; Qiu, Ming; Wang, Yingdong; Chen, Xiaowei

doi:10.1109/ijcnn.2018.8489331

Cited by 260 publications

(169 citation statements)

References 12 publications

Supporting

Mentioning

167

Contrasting

Order By: Relevance

“…Yang et al [22] presented a hybrid neural network-based model that combines CNN and RNN to classify human emotions. They consider baseline signals as an effective pre-processing method to improve the recognition accuracy, like in traditional feature-based approaches.…”

Section: Hybrid Modelsmentioning

confidence: 99%

Distinguishing Emotional Responses to Photographs and Artwork Using a Deep Learning-Based Approach

Yang

Han

Min

2019

Sensors

View full text Add to dashboard Cite

Visual stimuli from photographs and artworks raise corresponding emotional responses. It is a long process to prove whether the emotions that arise from photographs and artworks are different or not. We answer this question by employing electroencephalogram (EEG)-based biosignals and a deep convolutional neural network (CNN)-based emotion recognition model. We employ Russell’s emotion model, which matches emotion keywords such as happy, calm or sad to a coordinate system whose axes are valence and arousal, respectively. We collect photographs and artwork images that match the emotion keywords and build eighteen one-minute video clips for nine emotion keywords for photographs and artwork. We hired forty subjects and executed tests about the emotional responses from the video clips. From the t-test on the results, we concluded that the valence shows difference, while the arousal does not.

show abstract

Section: Hybrid Modelsmentioning

confidence: 99%

Distinguishing Emotional Responses to Photographs and Artwork Using a Deep Learning-Based Approach

Yang

Han

Min

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Thus, these waveforms can be classified into five specific frequency power bands: the delta band (δ), the theta band (θ), the alpha band (α), the beta band (β), and the gamma band (γ) [40,41]. Studies on EEG signal processing have been conducted to identify the brain activity patterns involved in cognitive science, neuropsychological research, clinical assessments, and consciousness research [42][43][44][45][46][47]. Recently, EEG has been widely used to assess and evaluate the human emotional states with excellent time resolution [3,15,[28][29][30]48].…”

Section: Introductionmentioning

confidence: 99%

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Al-Qazzaz

Sabir

Ali

et al. 2019

Sensors

View full text Add to dashboard Cite

Identifying emotions has become essential for comprehending varied human behavior during our daily lives. The electroencephalogram (EEG) has been adopted for eliciting information in terms of waveform distribution over the scalp. The rationale behind this work is twofold. First, it aims to propose spectral, entropy and temporal biomarkers for emotion identification. Second, it aims to integrate the spectral, entropy and temporal biomarkers as a means of developing spectro-spatial ( S S ) , entropy-spatial ( E S ) and temporo-spatial ( T S ) emotional profiles over the brain regions. The EEGs of 40 healthy volunteer students from the University of Vienna were recorded while they viewed seven brief emotional video clips. Features using spectral analysis, entropy method and temporal feature were computed. Three stages of two-way analysis of variance (ANOVA) were undertaken so as to identify the emotional biomarkers and Pearson’s correlations were employed to determine the optimal explanatory profiles for emotional detection. The results evidence that the combination of applied spectral, entropy and temporal sets of features may provide and convey reliable biomarkers for identifying S S , E S and T S profiles relating to different emotional states over the brain areas. EEG biomarkers and profiles enable more comprehensive insights into various human behavior effects as an intervention on the brain.

show abstract

“…They tried to recognize short term emotions and perceived emotions for 20 s, achieving 73.06% accuracy for valence and 80.78% for arousal. Yang et al extracted EEG features through the parallel deep learning model of CNN and RNN [23]. Figure 2 shows the overall structure for the proposed emotion recognition procedure.…”

Section: Hand-crafted Features For Emotion Recognitionmentioning

confidence: 99%

“…Alhagry et al proposed a long-short term memory (LSTM) model to learn EEG features and classify emotion depending on arousal and valence values [22]. Yang et al introduced a parallel model of a recurrent neural network (RNN) and a CNN based on EEG signals to obtain meaningful features [23]. With deep learning, emotion recognition within one minute became possible.…”

Section: Introductionmentioning

confidence: 99%

Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network

Lee

Pae

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Physiological signals contain considerable information regarding emotions. This paper investigated the ability of photoplethysmogram (PPG) signals to recognize emotion, adopting a two-dimensional emotion model based on valence and arousal to represent human feelings. The main purpose was to recognize short term emotion using a single PPG signal pulse. We used a one-dimensional convolutional neural network (1D CNN) to extract PPG signal features to classify the valence and arousal. We split the PPG signal into a single 1.1 s pulse and normalized it for input to the neural network based on the personal maximum and minimum values. We chose the dataset for emotion analysis using physiological (DEAP) signals for the experiment and tested the 1D CNN as a binary classification (high or low valence and arousal), achieving the short-term emotion recognition of 1.1 s with 75.3% and 76.2% valence and arousal accuracies, respectively, on the DEAP data.

show abstract

Emotion Recognition from Multi-Channel EEG through Parallel Convolutional Recurrent Neural Network

Cited by 260 publications

References 12 publications

Distinguishing Emotional Responses to Photographs and Artwork Using a Deep Learning-Based Approach

Distinguishing Emotional Responses to Photographs and Artwork Using a Deep Learning-Based Approach

Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers

Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network

Contact Info

Product

Resources

About