Investigating Critical Frequency Bands and Channels for EEG-Based Emotion Recognition with Deep Neural Networks

By Wei-Long Zheng, Bao-Liang Lu. IEEE Transactions on Autonomous Mental Development, 2015

2,280 citations recorded by the source corpus.

Subfields: Cardiology and Cardiovascular Medicine, Cognitive Neuroscience, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/5139a91a2769fac032f21a71f91946da7df0b582

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

1. Zhen Cui
2. Wenming Zheng
3. Wei-Long Zheng
4. Jinpeng Li
5. Huiguang He
6. Wei Liu
7. Yuan Zong
8. Bao-Liang Lu

In Cognitive Neuroscience

1. Wei-Long Zheng
2. Dongrui Wu
3. Bao-Liang Lu
4. Wei Liu
5. Tzyy-Ping Jung
6. Chunyan Miao
7. Di Wang
8. Peixiang Zhong

In Experimental and Cognitive Psychology

1. Wei-Long Zheng
2. Bao-Liang Lu
3. Wei Liu
4. Dongrui Wu
5. Chunyan Miao
6. Di Wang
7. Peixiang Zhong
8. Zhen Cui

Citations in the corpus

• EEG Based Emotion Recognition by Combining Functional Connectivity Network and Local Activations (2019, background): “The results above further indicated that these two frequency bands are highly correlated with the human emotion valences [49], [50], and they are also consistent with the existing findings that higher frequency brain activities reflect emotional and cognitive processes [51].”
• Targeting EEG/LFP Synchrony with Neural Nets (2017, methodology): “This includes Restricted Boltzmann Machines and Deep Belief Networks [17, 36], CNNs [32, 29], and RNNs [2, 34].”
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks (2019, methodology): “The SEED dataset [7] comprises EEG data of 15 subjects (7 males) recorded in 62 channels using the ESI NeuroScan System.”
• EEG-Based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and Their Applications (2020, methodology): “The experiments conducted on the SJTU emotion EEG dataset (SEED) [120] and the DREAMER dataset [121] achieved recognition accuracy rates of 90.4 and 86.23 percent, respectively.”
• Hierarchical Convolutional Neural Networks for EEG-Based Emotion Recognition (2017, methodology): “Israsena et al. calculated the PSD features of 32- channel EEG signals and applied PCA to extract the most important components of initial input features.”
• EEG Based Emotion Recognition: A Tutorial and Review (2022, methodology): “For example, Zheng and Lu [60] explore the critical EEG electrodes by analyzing the weights of the trained DBNs.”
• Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI (2024, background): “• SEED Series (Zheng & Lu, 2015; Zheng et al., 2018; Liu et al., 2022): (von Weltin et al., 2017): This is another subset of TUEG that contains annotations of slowing events (23 channels, 256 Hz).”
• A Bi-Hemisphere Domain Adversarial Neural Network Model for EEG Emotion Recognition (2021, methodology): “In the subject-dependent experiment, we follow the same experimental protocol as that of [13] by choosing the EEG signals associated with two of the three sessions for each subject to serve as the experimental data, in which each session contains 15 trials of EEG signals.”
• Identifying Stable Patterns over Time for Emotion Recognition from EEG (2016, background): “The findings of these neural patterns are consistent with previous emotion studies [14], [17], [42], [59], [61].”
• A Novel Bi-Hemispheric Discrepancy Model for EEG Emotion Recognition (2019, methodology): “especially on SEED and MPED data sets, which is consistent with the observations of [5] and [12].”
• EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization (2022, methodology): “…EEG datasets, including BCI competition IV dataset 2a, 1 BCI 1 https://www.bbci.de/competition/iv/desc_2a.pdf competition IV dataset 2b, 2 SEED 3 [36] These EEG datasets were collected with different acquisition devices, paradigms, number of subjects, and sample size, thus fairly validating the…”
• Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review (2020, methodology): “A DBN architecture has also been exploited successfully for EEG-based emotion recognition (Zheng and Lu, 2015; Huang et al., 2017).”
• Comparing Recognition Performance and Robustness of Multimodal Deep Learning Models for Multimodal Emotion Recognition (2021, methodology): “Besides, electroencephalography (EEG)-based emotion recognition has been demonstrated to be a reliable method because of its high recognition accuracy, objective evaluation, and stable neural patterns [6]–[10].”
• EEG-Based Emotion Recognition via Channel-Wise Attention and Self Attention (2023, methodology): “DE feature has the balance ability of discriminating EEG pattern between low and high frequency energy, which is typically used as frequency-domain features in EEG emotion recognition [14], [47], [50].”
• Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, background): “examined dominant frequency bands and channels of EEG in an emotion recognition system [165].”
• Spatial–Temporal Recurrent Neural Network for Emotion Recognition (2017, methodology): “However, for the results of DBN in [2], only beta and gamma bands of”