Optimal configuration of multilayer perceptron neural network classifier for recognition of intracranial epileptic seizures
作者：
Highlights：
• An automated classification of intracranial seizures was proposed.
• Entropy based multi-features with multilayer neural network model was used.
• Neural network was optimally configured to ensure better classification.
• Performances were evaluated using mutual range of coefficient and z-score.
• Classification accuracy of 97.68% was achieved for pre-ictal vs. epileptic.
摘要
•An automated classification of intracranial seizures was proposed.•Entropy based multi-features with multilayer neural network model was used.•Neural network was optimally configured to ensure better classification.•Performances were evaluated using mutual range of coefficient and z-score.•Classification accuracy of 97.68% was achieved for pre-ictal vs. epileptic.
论文关键词：Entropy,Epileptic seizures,MLP,Mutual range of coefficient,Training function,Transfer function
论文评审过程：Received 29 April 2017, Revised 15 July 2017, Accepted 19 July 2017, Available online 27 July 2017, Version of Record 29 July 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.07.029
