Deep learning model construction method based on MEMD and application thereof in motor imagery

Abstract

The present invention provides a deep learning model construction method based on MEMD (Multiple Empirical Mode Decomposition). The method comprises the steps of: performing band-pass filtering of multi-channel brain electrical signals measured by a brain control device to obtain p-dimensional brain electrical signals, performing signal segmentation of the p-dimensional brain electrical signals bytaking 2 seconds as a unit to obtain a plurality of signal samples, and performing multi-element empirical mode decomposition of each signal sample; obtaining different intrinsic mode function component numbers n for the signal samples, taking the minimum n as c, and retaining the first c intrinsic mode functions; for each signal sample, adding the c intrinsic mode functions obtained through multi-element empirical mode decomposition with the trend of a data sequence X(t) for stacking to obtain three-dimensional data samples with the sizes of q*p*(c+1), and taking the three-dimensional data samples as input of the deep learning model; and constructing a deep learning model applied in the motor imagery. The deep learning model construction method based on the MEMD and the application thereof in motor imagery are high in computing efficiency in the deep learning model, output an instruction which can control the motion of devices such as a mechanical arm, and are good in timeliness andgood in utilization potentiality.

Description

Technical field [0001] The invention relates to a deep learning model. In particular, it relates to a method for constructing a MEMD-based deep learning model for human brain multi-channel electrical signals and its application in motor imagination. Background technique [0002] EEG signals are a way of reflecting the physiological activities of neurons in the cerebral cortex. A large amount of physiological and pathological information can be extracted from the neuron potentials in various regions. Accurate monitoring and identification of the human brain in different working states can not only provide effective treatments for certain brain diseases in clinical medicine. At the same time, in terms of actual development, the brain-computer interface (BCI) is realized through EEG signals to study human brain functions such as visual induction and motor imagination. Studying the brain state of the human brain when it is in different sensory or cognitive activities is helpful for...

AI Technical Summary

Problems solved by technology

However, how to make the original EEG signal easier to be processed by the deep network, and combine the existing theory to add prior knowledge to promote identification to achieve better results, the research and results in this area are still very limited

Images