Personalization is essential in enhancing the performance of machine learning models in brain-computer interfaces (BCIs) for emotion recognition, specifically in valence and arousal classification. In this work, we address the challenge of personalizing BCI models utilizing a wireless consumer non-invasive electroencephalogram (EEG) device with dry electrodes. Our research investigates the effectiveness of three machine learning algorithms in classifying valence and arousal: k-Nearest Neighbors (k-NNs), Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs). To achieve personalization, we adopt an incremental learning approach by progressively incorporating high-quality subject data during model training that are taken from the ground-truth. We compare the performance of the models before and after personalization. The results demonstrate significant improvements in valence and arousal classification accuracy through personalization, with the personalized models outperforming the non-personalized models by up to 27.82% and 28.80%, respectively.

Amrani, H., Micucci, D., Nalin, M., Napoletano, P. (2024). Emotion Personalization with Machine Learning using EEG Signals and Dry Electrodes. In 2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 - Proceedings (pp.132-137). Institute of Electrical and Electronics Engineers Inc. [10.1109/metroxraine58569.2023.10405681].

Emotion Personalization with Machine Learning using EEG Signals and Dry Electrodes

Amrani, H;Micucci, D;Napoletano, P
2024

Abstract

Personalization is essential in enhancing the performance of machine learning models in brain-computer interfaces (BCIs) for emotion recognition, specifically in valence and arousal classification. In this work, we address the challenge of personalizing BCI models utilizing a wireless consumer non-invasive electroencephalogram (EEG) device with dry electrodes. Our research investigates the effectiveness of three machine learning algorithms in classifying valence and arousal: k-Nearest Neighbors (k-NNs), Support Vector Machines (SVMs), and Artificial Neural Networks (ANNs). To achieve personalization, we adopt an incremental learning approach by progressively incorporating high-quality subject data during model training that are taken from the ground-truth. We compare the performance of the models before and after personalization. The results demonstrate significant improvements in valence and arousal classification accuracy through personalization, with the personalized models outperforming the non-personalized models by up to 27.82% and 28.80%, respectively.
paper
Brain-computer Interface; Dry electrodes; Electroencephalography; Emotion; Incremental Learning; Machine Learning; Personalization;
English
2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023
2023
2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 - Proceedings
9798350300802
1-feb-2024
2024
132
137
reserved
Amrani, H., Micucci, D., Nalin, M., Napoletano, P. (2024). Emotion Personalization with Machine Learning using EEG Signals and Dry Electrodes. In 2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 - Proceedings (pp.132-137). Institute of Electrical and Electronics Engineers Inc. [10.1109/metroxraine58569.2023.10405681].
File in questo prodotto:
File Dimensione Formato  
Amrani-2023-MetroXRAINE-VoR.pdf

Solo gestori archivio

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Tutti i diritti riservati
Dimensione 1.69 MB
Formato Adobe PDF
1.69 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/462798
Citazioni
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
Social impact