@article{2025-BSPC-EyeMovementsClassification,
   author = {Zeng, Zheng and Tao, Linkai and Hu, Jun and Su, Ruizhi and Meng, Long and Chen, Chen and Chen, Wei},
   title = {Multi-scale Inception-based Deep Fusion Network for electrooculogram-based eye movements classification},
   journal = {Biomedical Signal Processing and Control},
   volume = {103},
   pages = {107377},
   abstract = {Classifying eye movements accurately is essential for various practical applications. However, eye movement classification (EMC) based on electrooculogram (EOG) is still challenging, and the existing solutions are still suboptimal in terms of accuracy. Traditional machine learning (ML)-based methods mainly focus on hand-crafted features, relying heavily on prior knowledge of EOG analysis. Besides, most existing deep learning (DL)-based methods simply concentrate on extracting sing-scale or multi-scale features without considering the contribution of features across different levels, constraining the model capacity in learning discriminative representations. To address the aforementioned problems, a novel Multi-scale Inception-based Deep Fusion Network (MIDF-NET), composed of paralleled CNN streams and a multi-scale feature fusion (MSFF) module, is proposed to extract informative features from raw EOG signals. The paralleled CNN streams can extract multi-scale representations of EOGs effectively and the MSFF module fuses these features, taking advantage of low and high-level multi-scale features. Comprehensive experiments were conducted on 5 public EOG datasets (50 subjects and 59 recordings), containing 5 types of eye movements (Blink, Up, Down, Right, and Left). State-of-the-art EOG-based eye movement approaches including classical machine learning models and deep networks were also implemented for comparison. Experimental results demonstrate that our MIDF-NET achieved the highest accuracy among the 5 public datasets (87.7%, 86.0%, 95.0%, 94.2%, and 95.4%), outperforming state-of-the-art methods with a significant accuracy improvement. In conclusion, the proposed MIDF-NET can comprehensively consider the multi-level features according to the feature fusion sub-networks and effectively classify the eye movement patterns via the enhanced representation of EOGs.},
   keywords = {Electrooculogram (EOG)
Eye movement classification (EMC)
Deep learning},
   DOI = {10.1016/j.bspc.2024.107377},
   year = {2025}
}