EEG (electroencephalogram) signal feature classification method based on ABC-SVM

Abstract

The invention relates to an EEG (electroencephalogram) signal feature classification method based on an ABC-SVM. The method comprises the steps: firstly carrying out EEG signal feature extraction through employing a CSP algorithm; secondly carrying out the optimization of a penalty factor C and a kernel parameter g of a SVM (support vector machine) through employing an artificial bee colony algorithm; finally carrying out the training of an SVM classifier through the obtained optimal parameter, and carrying out the classification prediction of samples through employing the trained classifier. Compared with an SVM classification recognition method optimized through a conventional algorithm, the method can effectively improve the classification recognition rate of an EEG signal, and is remarkably superior to a conventional classification recognition method.

Description

technical field [0001] The invention relates to a feature extraction and classification method of electroencephalogram signals, in particular to an ABC-SVM-based feature classification method of electroencephalogram signals. Background technique [0002] Brain-computer interface technology (Brain-computer Interface, BCI) is a new technology that integrates artificial intelligence, computer science and information, biomedical engineering and neuroscience. The field of cognitive science has a very broad application prospect. The characteristic of BCI technology is that it does not pass through the normal physiological pathways of peripheral nerves, muscles and bones of the human body, but allows the brain and external devices (computers or related instruments, etc.) to directly transmit information or control commands. [0003] Pattern classification of EEG signals is a particularly important part of the BCI system, and the classification performance is related to the real-ti...

AI Technical Summary

Problems solved by technology

At present, the commonly used model parameter optimization methods mainly include gradient descent method, genetic algorithm and particle swarm algorithm, etc., but these optimization methods have their own limitations.

For example, the gradient descent algorithm has low stability and low efficiency; the genetic algorithm has a slow convergence speed and is easy to fall into a local optimum; compared with the genetic algorithm, the particle swarm optimization algorithm is simple in principle, easy to implement, and fast in convergence speed, but In the later stage, it is easy to fall into local optimum, and the optimal classification effect cannot be achieved.

Images