Multi-view learning method and system for rhesus monkey eye movement decision decoding

Abstract

The invention discloses a multi-view learning method and system for rhesus monkey eye movement decision decoding, and belongs to the field of multi-view decoding in intrusive brain-computer interfaces. The multi-view learning method comprises the steps that an eye movement decision decoding model comprising a characteristic node extraction network, a reinforced node extraction network and a predicting network is established; eye movement decision direction data obtained after encoding of the local field potential and action potential of a medial frontal cortex auxiliary eye area in a rhesus monkey intrusive brain-computer interface, and one-hot encoding are input into the eye movement decision decoding model for training, and thus the trained eye movement decision decoding model is obtained; and the to-be-decoded local field potential and action potential are input into the trained decoding model, and thus a decoding result of the eye movement direction is obtained. The multi-view learning method and system are less in using limitation, low in computation complexity and suitable for decoding of action potential and local field potential signals in the intrusive brain-computer interface and other various multi-view learning scenes.

Description

technical field [0001] The invention belongs to the field of multi-view decoding in invasive brain-computer interfaces, and more specifically relates to a multi-view learning method and system for rhesus monkey eye movement decision-making decoding. Background technique [0002] A brain-computer interface is a system that provides a direct interaction channel between the brain and external devices. Invasive brain-computer interfaces usually implant electrode arrays directly into the gray matter of the brain to obtain higher-quality signals for decoding. Such as literature [1] X.Chenand V.Stuphorn, "Sequential selection of economic good and action in mediafrontal cortex of macaques during value-based decisions," Elife, vol.4, p.e09418, 2015. Invasive brain-computer interface Applied to rhesus monkeys, it trains two female rhesus monkeys to choose one of the four visual cues in specific directions through eye movement, and according to the selected visual cues, they will recei...

AI Technical Summary

Problems solved by technology

[0004] The feature extraction process in literature [2] requires professional knowledge to adjust parameters for the problem. Its method is more biased towards event detection rather than classification. It performs well in the two-category task of the preferred direction and the non-preferred direction, but in the four-direction classification task. The classification effect in the medium is significantly reduced; the feature selection in the literature [3] requires a large number of channel features to choose from, which is not suitable for the decoding of 1 to 4 channel signals; the modeling and prediction in the literature [4] require a large number of potential changes Real-time synchronized motion state data, not suitable for classification and decoding goals for decision-making directions

Images