A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals
作者：
Highlights：
• A comparison of fifty features of different types for seizure detection is presented.
• Features are from time and frequency domain with non-linear ones.
• Computational complexity of each feature is also presented.
• Additionally, those features are compared to learned features by proposed CNN-AE.
• Finally, employing a hybrid method from all features best results are obtained.
摘要
•A comparison of fifty features of different types for seizure detection is presented.•Features are from time and frequency domain with non-linear ones.•Computational complexity of each feature is also presented.•Additionally, those features are compared to learned features by proposed CNN-AE.•Finally, employing a hybrid method from all features best results are obtained.
论文关键词：Epileptic seizures,Electroencephalography (EEG),Convolutional autoencoder,Feature extraction,Computational complexity
论文评审过程：Received 9 December 2019, Revised 19 July 2020, Accepted 21 July 2020, Available online 30 July 2020, Version of Record 5 August 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113788
