Semi-supervised extreme learning machine classification method based on graph balance regularization

Abstract

The invention relates to a semi-supervised extreme learning machine classification method based on graph balance regularization. According to the method, an adjacency graph based on label consistencyand an adjacency graph based on information structure consistency are balanced through a non-negative weight value, so that the graph balance is achieved, a Laplace regular term of an optimal graph can be obtained to constrain a model, it is considered that the weight of the label consistency graph is increased when the information consistency graph cannot well describe the structure information of the sample set, and otherwise, the corresponding proportion needs to be reduced. The method comprises the following steps of firstly, constructing an adjacent supervised graph between the training samples through the label consistency of the samples; and combining with a semi-supervised graph based on the sample information consistency to constrain the output of the model, changing the capability of describing data distribution by reasonably adjusting the proportion of the graph, and obtaining an optimal output weight vector after obtaining an optimal adjacent graph. The method has a wide application prospect in the electroencephalogram signal processing systems and the brain-computer interface systems.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and is a method for classifying EEG signals by constructing a Laplacian regular term using a graph based on sample label consistency and information consistency and adding it to a semi-supervised extreme learning machine. Background technique [0002] Brain-computer interface technology (BCI) is an important means to realize human-computer interaction through the analysis method of electroencephalogram signal (EEG), and the classification of EEG signal based on motor imagery is a typical paradigm in BCI technology. Actions are discriminated, and the results are converted into equipment control commands to complete the corresponding imaginary actions, which can provide great help for the rehabilitation of patients with disturbance of consciousness and stroke. Patients can use this technology to realize the control of mechanical equipment and complete the required tasks. Actions. In order to acc...

AI Technical Summary

Problems solved by technology

[0005] When constructing the sample adjacency graph, the machine learning algorithm based on graph regularization can only construct the adjacency graph by using the consistency of the sample label or the similarity of the sample's own structural information, but does not comprehensively consider the synergy between the two. Impact on the trained model

Images