July 8, 2025ElectronicsOpen Access

A Comparative Study on Machine Learning Methods for EEG-Based Human Emotion Recognition

View Full Paper

Ask AI

Bookmark

Why the study?

The study was conducted to compare deep and shallow neural networks for human emotion recognition from raw EEG data, aiming to enable real-time processing in embedded and edge-deployable systems.

Population

Raw EEG data from the DEAP dataset

Comparison

Deep learning models (CNNs, RNNs) vs traditional approaches (MLP, SVM, kNN)

Design

Comparative benchmarking study

Authors

SDShokoufeh DavarzaniWestern Michigan University SMS. MasihiWestern Michigan University MPMasoud Shariat PanahiWestern Michigan University

Discussion

Member takes

Implication

Deep learning may advance EEG emotion recognition in wearables; leaves open clinical validation before healthcare use.

Structured PICO

Population

DEAP dataset (EEG data for human emotion recognition)

Intervention

Deep learning models (convolutional neural networks [CNNs] and recurrent neural networks [RNNs])

Comparator

Traditional shallow algorithms (multi-layer perceptron [MLP], support vector machine [SVM], and k-nearest neighbors [kNN])

Outcome

Classification accuracy of emotions into four categories based on the valence-arousal plane (HAPV, LAPV, HANV, LANV)

Deep learning models (CNN and RNN) significantly outperform traditional shallow algorithms in EEG-based human emotion recognition.

Cite This Study

Davarzani et al. (2025) studied this question.

synapsesocial.com/papers/6a7d40a1e9ddcd9870aa167e https://doi.org/10.3390/electronics14142744

View Full Paper

Ask AI

Bookmark

A Comparative Study on Machine Learning Methods for EEG-Based Human Emotion Recognition

Discussion

Member takes

Implication

Structured PICO

Cite This Study

A Comparative Study on Machine Learning Methods for EEG-Based Human Emotion Recognition

Discussion

Member takes

Implication

Structured PICO

Cite This Study

Also Consider

Also Consider