RDPNet: A Multi-Scale Residual Dilated Pyramid Network with Entropy-Based Feature Fusion for Epileptic EEG Classification
Open Access
Abstract
Epilepsy is a prevalent neurological disorder affecting approximately 50 million individuals worldwide. Electroencephalogram (EEG) signals play a vital role in the diagnosis and analysis of epileptic seizures. However, traditional machine learning techniques often rely on handcrafted features, limiting their robustness and generalizability across diverse EEG acquisition settings, seizure types, and patients. To address these limitations, we propose RDPNet, a multi-scale residual dilated pyramid network with entropy-guided feature fusion for automated epileptic EEG classification. RDPNet combines residual convolution modules to extract local features and a dilated convolutional pyramid to capture long-range temporal dependencies. A dual-pathway fusion strategy integrates pooled and entropy-based features from both shallow and deep branches, enabling robust representation of spatial saliency and statistical complexity. We evaluate RDPNet on two benchmark datasets: the University of Bonn and TUSZ. On the Bonn dataset, RDPNet achieves 99.56–100% accuracy in binary classification, 99.29–99.79% in ternary tasks, and 95.10% in five-class classification. On the clinically realistic TUSZ dataset, it reaches a weighted F1-score of 95.72% across seven seizure types. Compared with several baselines, RDPNet consistently outperforms existing approaches, demonstrating superior robustness, generalizability, and clinical potential for epileptic EEG analysis.Keywords
Funding Information
- Natural Science Foundation of Xiamen, China (3502Z202374054, 3502Z202573102, CKZ24016, CYKYPT02)
- Provincial and Ministerial-Level Scientific Research Cultivation Project of Chengyi College, Jimei University (3502Z202374054, 3502Z202573102, CKZ24016, CYKYPT02)
- Big Data Technology Institute of Chengyi College, Jimei University (3502Z202374054, 3502Z202573102, CKZ24016, CYKYPT02)
This publication has 52 references indexed in Scilit:
- TCANet: a temporal convolutional attention network for motor imagery EEG decodingCognitive Neurodynamics, 2025
- Electroencephalogram (EEG) classification using a bio-inspired deep oscillatory neural networkBiomedical Signal Processing and Control, 2024
- Multiband seizure type classification based on 3D convolution with attention mechanismsComputers in Biology and Medicine, 2023
- A CNN-LSTM hybrid network for automatic seizure detection in EEG signalsNeural Computing and Applications, 2023
- A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signalBiomedical Signal Processing and Control, 2023
- A combination of statistical parameters for epileptic seizure detection and classification using VMD and NLTWSVMBiocybernetics and Biomedical Engineering, 2022
- Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a reviewNeural Computing and Applications, 2021
- Evaluation of time domain features on detection of epileptic seizure from EEG signalsHealth and Technology, 2019
- Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signalsComputers in Biology and Medicine, 2018
- A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signalsComputers in Biology and Medicine, 2018