May 8, 2015IEEE Transactions on Autonomous Mental Development

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

View Full Paper

Ask AI

Bookmark

Population

15 subjects performing EEG experiments twice at an interval of a few days

Comparison

Deep belief networks trained with differential… vs Shallow models

Design

Other

Authors

WZWei‐Long ZhengShanghai Jiao Tong University BLBao‐Liang LuUniversity of Science and Technology of China

Discussion

Member takes

Implication

Supports efficient EEG emotion classifiers in research; leaves open clinical translation pending larger validation.

Structured PICO

Population

15 subjects performing EEG experiments twice at an interval of a few days

Intervention

Deep belief networks (DBNs) trained with differential entropy features extracted from multichannel EEG data

Comparator

Shallow models (Support Vector Machine [SVM], Logistic Regression [LR], and K-Nearest Neighbors [KNN])

Outcome

Emotion recognition accuracy for three emotions (positive, neutral, negative)

Deep belief networks outperform shallow models in EEG-based emotion recognition, achieving high accuracy even with a reduced number of critical channels.

Cite This Study

Zheng et al. (2015) studied this question.

synapsesocial.com/papers/69d995040d540cafc58363bf https://doi.org/10.1109/tamd.2015.2431497

View Full Paper

Ask AI

Bookmark

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

Discussion

Member takes

Implication

Structured PICO

Cite This Study

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

Discussion

Member takes

Implication

Structured PICO

Cite This Study

Also Consider

Also Consider