Optimized EEG-Based Emotion Recognition with FFT and Hyperparameter-Tuned Machine Learning Classifiers

DOI

10.2991/978-94-6239-828-3_15How to use a DOI?

Keywords

EEG; Emotion Recognition; FFT; Machine Learning; Hyperparameter Optimization; Optuna

Abstract

Emotions play a critical part in everyday life since it affects decision-making, behavior, and human interactions with systems. As a result, emotion recognition has become an important topic in affective computing. Among various physiological signals, electroencephalography (EEG) is widely used for emotion recognition because it directly captures brain activity with high temporal resolution and is less susceptible to conscious manipulation than facial expressions or speech, thereby supporting more objective emotion detection. In this study, EEG-based emotion classification was performed using the Fast Fourier Transform (FFT) to extract frequency-domain features from EEG signals. FFT was selected because it efficiently represents spectral characteristics associated with emotional states across EEG frequency bands. Three machine learning classifiers: K-Nearest Neighbor (KNN), Random Forest (RF), and Sup- port Vector Machine (SVM) were employed to classify emotional states. To enhance classification performance, Optuna was applied in the hyperparameter optimization process. Experimental results show that the Optuna consistently improves the performance of all models compared to the default configuration. Among the evaluated models, SVM achieved the best performance with an accuracy of 0.9174, outperforming both KNN and RF. These findings imply that the combination of FFT as feature extraction and hyperparameter optimization using Optuna effectively enhances the performance of EEG-based emotion classification.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sza Sza Amulya Larasati
AU  - Lazuardy Syahrul Darfiansa
PY  - 2026
DA  - 2026/11/04
TI  - Optimized EEG-Based Emotion Recognition with FFT and Hyperparameter-Tuned Machine Learning Classifiers
BT  - Proceedings of the 2026 11th International Conference on Sustainable Information Engineering and Technology (SIET 2026)
PB  - Atlantis Press
SP  - 167
EP  - 177
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6239-828-3_15
DO  - 10.2991/978-94-6239-828-3_15
ID  - Larasati2026
ER  -