Computational NeuroscienceMulti-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning

•Collaborative representation (CR) works as a new feature representation method.•A joint collaboration representation model (JCM) it proposed to fuse multi-channel EEG features.•A two-stage multi-view learning-based sleep staging framework is established.•JCR codes and joint sparse representation (JSR) codes work as two-view features.•The multiple kernel extreme learning machine integrates JCR and JSR features for classification.

BackgroundElectroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation.New methodCollaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search.ResultsThe proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively.Comparison with existing methodsThe two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR.ConclusionsThe proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals.