Semi-supervised learning quantization algorithm with deep features for motor imagery EEG Recognition in smart healthcare application

This paper depicts a novel semi-supervised classification model with convolutional neural networks (CNN) for EEG Recognition. The performance of popular machine learning algorithm usually rely on the number of labeled training samples, such as the deep learning approaches,sparse classification approaches and supervised learning approaches. However, the labeled samples are very difficulty to get for electroencephalography(EEG) data. In addition, most deep learning algorithms are usually time-consuming in the process of training. Considering these problems, in this article, a novel semi-supervised quantization algorithm based on the cartesian K-means algorithm is proposed, which named it as the semi-supervised cartesian K-means (SSCK), we use the CNN models pre-trained on motor imagery samples to create deep features, and then we applied it for motor imagery (MI) data classification. Unlike the traditional semi-supervised learning models that labeled information can be directly casted into the model training, label information can only be implicitly used in the semi-supervised learning strategy, in the semi-supervised learning algorithm, supervised information is integrated into the quantization algorithm by resorting a supervised constructed laplacian regularizer. Experimental results over four popular EEG datasets substantiate the efficiency and effectiveness of our proposed semi-supervised cartesian K-means.