October 22, 2020Electronics Letters

The proposed approach produced accuracies of 96.1% for low/high valence and 99.6% for low/high arousal classification.

View Full Paper

Ask AI

Bookmark

Why the study?

Human emotion identification using EEG signals is emerging in health monitoring, but efficient automated frameworks for classification are needed.

Does the proposed deep learning framework improve EEG-based emotion recognition accuracy compared to other methods?

Population

DEAP EEG data set

Comparison

Proposed deep learning framework vs other compared methods

Authors

DŞDönüş Şengür SSSiuly Siuly

Discussion

Member takes

Overview

May support EEG-based affective monitoring research; leaves open clinical validation before cardiovascular practice adoption.

Structured PICO

Does the proposed deep learning framework improve EEG-based emotion recognition accuracy compared to other methods?

Population

DEAP EEG data set (publicly available)

Intervention

Deep learning framework (low-pass filtering, delta rhythm extraction, continuous wavelet transform, pre-trained CNN, MobileNetv2 for feature selection, and LSTM for classification)

Comparator

Other compared methods

Outcome

Accuracy of emotion classification ('Valence' and 'Arousal')surrogate

A novel deep learning framework using MobileNetv2 and LSTM achieves high accuracy in classifying human emotions from EEG signals.

Cite This Study

Şengür et al. (2020) studied this question.

synapsesocial.com/papers/6a87c62519ee2aac066c857d https://doi.org/10.1049/el.2020.2685

View Full Paper

Ask AI

Bookmark

October 22, 2020Electronics Letters

The proposed approach produced accuracies of 96.1% for low/high valence and 99.6% for low/high arousal classification.

View Full Paper

Ask AI

Bookmark

Why the study?

Human emotion identification using EEG signals is emerging in health monitoring, but efficient automated frameworks for classification are needed.

Does the proposed deep learning framework improve EEG-based emotion recognition accuracy compared to other methods?

Population

DEAP EEG data set

Comparison

Proposed deep learning framework vs other compared methods

Authors

DŞDönüş Şengür SSSiuly Siuly

Discussion

Member takes

Overview

May support EEG-based affective monitoring research; leaves open clinical validation before cardiovascular practice adoption.

Structured PICO

Does the proposed deep learning framework improve EEG-based emotion recognition accuracy compared to other methods?

Population

DEAP EEG data set (publicly available)

Intervention

Deep learning framework (low-pass filtering, delta rhythm extraction, continuous wavelet transform, pre-trained CNN, MobileNetv2 for feature selection, and LSTM for classification)

Comparator

Other compared methods

Outcome

Accuracy of emotion classification ('Valence' and 'Arousal')surrogate

A novel deep learning framework using MobileNetv2 and LSTM achieves high accuracy in classifying human emotions from EEG signals.

Cite This Study

Şengür et al. (2020) studied this question.

synapsesocial.com/papers/6a87c62519ee2aac066c857d https://doi.org/10.1049/el.2020.2685

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark