cs.LG
EEG-FuseFormer: A Transformer-Driven Feature Fusion Framework for Seizure Onset Prediction
Jun 1, 2026
The paper proposes EEG-FuseFormer, a transformer-based framework that fuses features from CNN-LSTM and ResNet-18 to achieve high accuracy in predicting seizure onset from EEG signals.
Epilepsy is one of the most common neurological disorders globally, characterized by recurring seizures and significantly impacting the quality of life. Despite advancements in diagnostic techniques, the mitigation of risks faced by epilepsy patients remains challenging due to the unpredictability of seizure events. An accurate forecast of seizure onset helps to reduce risks in epilepsy patients. In this paper, we propose EEG-FuseFormer, a transformer-based feature fusion framework for seizure-onset prediction that combines intermediate features extracted from Convolutional Neural Networks-Long Short-Term Memory (CNN-LSTM) and ResNet-18 networks. The CNN-LSTM architecture captures both spatial and temporal features directly from the raw signal, whereas the ResNet-18 extracts features from the Short-Time Fourier Transform (STFT) representation of the EEG signals. Fusion is carried out using a transformer encoder, and the final prediction is generated using fully connected dense layers. The CHB-MIT dataset was used to validate the proposed model. The results show that the proposed model achieves a mean recall of 98.85% and outperforms most of the state-of-the-art methods. This study evaluates the ability of the proposed feature fusion model to generalize in cross-patient testing scenarios. Fine-tuning pre-trained models on limited target patient data (target adaptation) within the cross-patient validation framework results in higher recall, precision, and F1-score metrics in comparison to the conventional cross-patient validation approach. Finally, the runtime-based computational complexity of the model is assessed across diverse hardware platforms to highlight the performance-complexity trade-off.
Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models
This paper benchmarks five positional encoding strategies for transformer-based…
A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models
The paper proposes a multi-dimensional evaluation framework to assess EEG founda…
Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG
The paper proposes the Morlet Spectral Transformer (MST), a novel architecture t…
A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity
The paper demonstrates that the valence structure learned by modern LLMs aligns…
CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
CaMBRAIN introduces a novel Mamba-based State Space Model (SSM) for real-time, c…
Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detect…
This study compares multiple post-hoc explainable AI methods (e.g., DeepSHAP, Gr…
GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
The paper proposes GloResNet, a lightweight 3D CNN that effectively predicts bra…
EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks
EvoBrain proposes a dynamic, cross-task continual learning framework to overcome…