Enregistré dans:
Détails bibliographiques
Auteurs principaux: Patodiya, Aryan, Cecotti, Hubert
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.13261
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911514492928000
author Patodiya, Aryan
Cecotti, Hubert
author_facet Patodiya, Aryan
Cecotti, Hubert
contents Electroencephalography (EEG) classification plays a key role in brain-computer interface (BCI) systems, yet it remains challenging due to the low signal-to-noise ratio, temporal variability of neural responses, and limited data availability. In this paper, we present a comparative study of deep learning architectures for classifying event-related potentials (ERPs) in EEG signals. The preprocessing pipeline includes bandpass filtering, spatial filtering, and normalization. We design and compare three main pipelines: a 2D convolutional neural network (CNN) using Common Spatial Pattern (CSP), a second 2D CNN trained directly on raw data for a fair comparison, and a 3D CNN that jointly models spatiotemporal representations. To address ERP latency variations, we introduce a temporal shift augmentation strategy during training. At inference time, we employ a confidence-based test-time voting mechanism to improve prediction stability across shifted trials. An experimental evaluation on a stratified five-fold cross-validation protocol demonstrates that while CSP provides a benefit to the 2D architecture, the proposed 3D CNN significantly outperforms both 2D variants in terms of AUC and balanced accuracy. These findings highlight the effectiveness of temporal-aware architectures and augmentation strategies for robust EEG signal classification.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13261
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Convolutional Architectures for EEG Classification: A Comparative Study with Temporal Augmentation and Confidence-Based Voting
Patodiya, Aryan
Cecotti, Hubert
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Electroencephalography (EEG) classification plays a key role in brain-computer interface (BCI) systems, yet it remains challenging due to the low signal-to-noise ratio, temporal variability of neural responses, and limited data availability. In this paper, we present a comparative study of deep learning architectures for classifying event-related potentials (ERPs) in EEG signals. The preprocessing pipeline includes bandpass filtering, spatial filtering, and normalization. We design and compare three main pipelines: a 2D convolutional neural network (CNN) using Common Spatial Pattern (CSP), a second 2D CNN trained directly on raw data for a fair comparison, and a 3D CNN that jointly models spatiotemporal representations. To address ERP latency variations, we introduce a temporal shift augmentation strategy during training. At inference time, we employ a confidence-based test-time voting mechanism to improve prediction stability across shifted trials. An experimental evaluation on a stratified five-fold cross-validation protocol demonstrates that while CSP provides a benefit to the 2D architecture, the proposed 3D CNN significantly outperforms both 2D variants in terms of AUC and balanced accuracy. These findings highlight the effectiveness of temporal-aware architectures and augmentation strategies for robust EEG signal classification.
title Deep Convolutional Architectures for EEG Classification: A Comparative Study with Temporal Augmentation and Confidence-Based Voting
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2603.13261