Abstract
Seizure prediction task based on electroencephalography (EEG) is a typical imbalanced classification problem since the preictal samples are much less than the interictal samples. Re-sampling is a common method to solve class-imbalance problems in the area of seizure prediction. However, up-sampling has the deficiency of overfitting minority class, and down-sampling tends to discard important information. In addition, many seizure prediction algorithms depend on artificially designed features, which is a time-consuming and laborious process. To this end, we propose an end-to-end ghost network and class re-balanced loss function (GhostNet-CRBLF). First, the ghostnet with one-dimensional convolution mainly uses linear operations instead of traditional convolution to generate feature maps, which improves model performance and reduces the amount of parameters. In addition, one-dimensional convolution is adopted to better reduce the data dimension. Then, cost-sensitive learning is utilized to solve the problem of data imbalance. Specifically, a simple but effective class re-balanced loss (CRB-loss) function is proposed to increase the misclassification cost of preictal data, which makes classifier to focus more on minority samples and classifies them correctly. Experimental performance indicates the proposed approach can achieve remarkable performance gains in seizure prediction task.

This publication has 12 references indexed in Scilit: