Adaptive Multiscale Spatiotemporal Mixing Network for Multiview Seizure Detection
- 21 May 2026
- journal article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (11) , 2650041
Abstract
Epileptic seizure detection from Electroencephalography (EEG) signals is challenging due to their complex temporal dynamics and intricate inter-channel dependencies. A key difficulty lies in capturing multiscale temporal features that span different time ranges. Seizure-related EEG patterns include rapidly varying micro-scale features and longer-duration macro-scale features, and modeling them jointly often leads to feature interference, hindering accurate temporal representation. In addition, many existing approaches fail to effectively capture spatial relationships between brain regions, further limiting detection performance. To cope with issues above, we design the Adaptive Multiscale Spatiotemporal Mixing Network (AMSMN). The framework first decomposes EEG signals into macro- and micro-scale sequences, which are processed independently across multiple temporal resolutions to reduce cross-scale interference and better represent temporal dynamics. A spatial attention mechanism then fuses the decomposed features, ensuring that important inter-channel information is preserved. Finally, an Informer-based sparse attention layer captures long-range dependencies, allowing the model to focus on the most relevant global interactions across brain regions. We carry out experiments on two available databases demonstrate that AMSMN consistently achieves superior performance to prior methods in both patient-specific and cross-patient settings. The results confirm that the proposed framework improves seizure detection accuracy, robustness, and generalization by effectively integrating multiscale temporal modeling with global spatial dependency extraction. This work advances EEG-based seizure detection by enabling precise multiscale temporal analysis and efficient global dependency modeling, offering strong performance and generalizability for clinical applications.Keywords
Funding Information
- National Natural Science Foundation of China (62076005)
- the Natural Science Foundation of Anhui Province (2008085MF191)
- the Natural Science Foundation of Anhui Province (2508085MF157)
- the University Synergy Innovation Program of Anhui Province, China (GXXT-2021-002)
- the Major Natural Science Research Projects of the Anhui Provincial Department of Education (2023AH040102)
This publication has 40 references indexed in Scilit:
- MICAL: Mutual Information-Based CNN-Aided Learned Factor Graphs for Seizure Detection From EEG SignalsIEEE Access, 2023
- Seizure detection algorithm based on improved functional brain network structure feature extractionBiomedical Signal Processing and Control, 2022
- A seizure detection method based on hypergraph features and machine learningBiomedical Signal Processing and Control, 2022
- EEG-Based Seizure detection using linear graph convolution network with focal lossComputer Methods and Programs in Biomedicine, 2021
- A robust deep learning approach for automatic classification of seizures against non-seizuresBiomedical Signal Processing and Control, 2021
- Selection of features for patient-independent detection of seizure events using scalp EEG signalsComputers in Biology and Medicine, 2020
- Automatic epileptic EEG detection using convolutional neural network with improvements in time-domainBiomedical Signal Processing and Control, 2019
- Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signalsComputers in Biology and Medicine, 2018
- Analysis of EEG Signals for Detection of Epileptic Seizure Using Hybrid Feature Set2015
- Epileptic seizure detection with linear and nonlinear featuresEpilepsy & Behavior, 2012