Dynamic learning framework for epileptic seizure prediction using sparsity based EEG Reconstruction with Optimized CNN classifier
作者：
Highlights：
• A model is developed to forecast the oncoming seizures of the epileptic patients.
• Sparsity-based EEG reconstruction is developed for artifact removal from EEG data.
• A lightweight 3D optimized CNN is modelled to extract features and classify them.
• Optimized CNN based on Fletcher Reeves accelerate proposed model convergence rate.
• OCNN classifies preictal and interictal states, predicts seizures before 1.2 h.
摘要
•A model is developed to forecast the oncoming seizures of the epileptic patients.•Sparsity-based EEG reconstruction is developed for artifact removal from EEG data.•A lightweight 3D optimized CNN is modelled to extract features and classify them.•Optimized CNN based on Fletcher Reeves accelerate proposed model convergence rate.•OCNN classifies preictal and interictal states, predicts seizures before 1.2 h.
论文关键词：Fletcher Reeves,K-SVD,Kullback-Leibler divergence,Optimal Seizure Prediction Horizon,Optimized Convolutional Neural Network,Principle Component Analysis
论文评审过程：Received 17 April 2020, Revised 7 December 2020, Accepted 19 December 2020, Available online 24 December 2020, Version of Record 9 January 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.114533
