Motor imagery EEG recognition with KNN-based smooth auto-encoder

作者：

Highlights：

• We devised a novel model, KNN-based smooth auto-encoder, to achieve accurate recognition of motor imaging EEG signals.

• K-SAE construct a new input and learns the robust features representation by reconstructing this new input instead of the original input, which is different from the traditional automatic encoder (AE).

• The Gaussian filter is selected as the convolution kernel function in k-SAE to smooth the noise in the feature.

• The experiments in this paper select two sets of data for verifying the validity of the proposed method. One is obtained by EEG signal acquisition experiment and the other is public data set.

摘要

•We devised a novel model, KNN-based smooth auto-encoder, to achieve accurate recognition of motor imaging EEG signals.•K-SAE construct a new input and learns the robust features representation by reconstructing this new input instead of the original input, which is different from the traditional automatic encoder (AE).•The Gaussian filter is selected as the convolution kernel function in k-SAE to smooth the noise in the feature.•The experiments in this paper select two sets of data for verifying the validity of the proposed method. One is obtained by EEG signal acquisition experiment and the other is public data set.

论文关键词：KNN-based smooth auto-encoder,BCI,Motor imagery,Feature extraction,EEG recognition

论文评审过程：Received 27 February 2019, Revised 6 October 2019, Accepted 27 October 2019, Available online 11 November 2019, Version of Record 19 November 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.101747