A Multimodal Attention-Based Fusion Framework with Ensemble Learning for Robust Differentiation of Epileptic and Psychogenic Seizures
IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies · 2026
DOI: 10.68307/qj2jgf82 ↗Kurz gefasst
Fachartikel in der Zeitschrift IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, 2026. Verfasst von Priyanka Singh. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Differentiating epileptic seizures from psychogenic non-epileptic seizures remains a significant clinical challenge, often leading to misdiagnosis and inappropriate treatment. We propose a multimodal attention-based fusion framework that integrates electroencephalography signals, video streams, and peripheral physiological data to address this problem. The system first extracts modality-specific features: time-frequency and nonlinear dynamical descriptors from EEG via wavelet decomposition and adaptive principal component analysis, spatiotemporal behavioral embeddings from video using a 3D ResNet, and autonomic markers from physiological signals encoded by a bidirectional long short-term memory network. A self-attention mechanism then computes context-aware weights for each modality, dynamically suppressing contributions from noisy or uninformative channels before constructing a fused representation. This fused vector is subsequently classified by a heterogeneous ensemble of a support vector machine, a random forest, and a shallow multi-layer perceptron, whose outputs are aggregated through soft voting. The key novelty lies in the attention-based fusion layer, which replaces conventional early or late fusion strategies and enables the model to adaptively prioritize diagnostically relevant modalities on a per-instance basis. Furthermore, the ensemble classifier provides robust decision boundaries even when single-modality cues are ambiguous. We expect this framework to improve diagnostic accuracy in clinical settings where video quality may be compromised or EEG artifacts are prevalent. The proposed method therefore offers a principled approach to integrating heterogeneous seizure-related signals, with potential to reduce misdiagnosis rates and guide appropriate therapeutic interventions.
Zitieren
APA
Singh, P. (2026). A Multimodal Attention-Based Fusion Framework with Ensemble Learning for Robust Differentiation of Epileptic and Psychogenic Seizures. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. https://doi.org/10.68307/qj2jgf82
Vancouver
Singh P. A Multimodal Attention-Based Fusion Framework with Ensemble Learning for Robust Differentiation of Epileptic and Psychogenic Seizures. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. 2026. doi:10.68307/qj2jgf82
BibTeX
@article{Singh2026,
author = {Singh, Priyanka},
title = {A Multimodal Attention-Based Fusion Framework with Ensemble Learning for Robust Differentiation of Epileptic and Psychogenic Seizures},
journal = {IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies},
year = {2026},
doi = {10.68307/qj2jgf82}
}
EUVIMED