Movement-intention continuous electroencephalogram-and-electromyogram multilayer dynamic fusion and recognition system and method

Abstract

The invention discloses a movement-intention continuous electroencephalogram-and-electromyogram multilayer dynamic fusion and recognition system and method. The movement-intention continuous electroencephalogram-and-electromyogram multilayer dynamic fusion and recognition system includes an electroencephalogram collection module, an electromyogram collection module, a signal preprocessing module,a feature extraction module, a fatigue state judgement module, an intention recognition module and a decision judgement module. According to the movement-intention continuous electroencephalogram-and-electromyogram multilayer dynamic fusion and recognition system and method, by collecting electroencephalograms and electromyograms, muscular and mental fatigue states of a human body are judged in real time; according to different fatigue states and fatigue degrees, different movement intention recognition means are adopted, advantages of different bioelectric signals are fully exerted, and the defect is overcome that due to different fatigue states and degrees, the accuracy rate of intention recognition decreases; and finally, recognition with high robustness and accuracy is achieved.

Description

【Technical field】 [0001] The invention belongs to the technical field of human-computer interaction, and relates to a system and method for recognizing motion intention continuous EEG multi-level dynamic fusion. 【Background technique】 [0002] At present, lower extremity exoskeleton technology has been widely used in neurorehabilitation, military and other fields. Among them, the accurate and rapid identification of human motion intention in the lower extremity exoskeleton is the core research content. [0003] Existing recognition methods for exoskeleton human movement intention mainly include intention recognition based on mechanical information and intention recognition based on bioelectric information. The motion intention recognition method of the signal mainly adopts the recognition of a single myoelectricity. Mechanical information is more convenient to collect than bioelectrical signals, and the signal is stable. However, due to the characteristics of the informati...

AI Technical Summary

Problems solved by technology

The patent (CN108681396A) proposes a recognition method based on brain-muscle information fusion, which does not fully consider the influence of the user's mental and muscle state on the brain-myography information after long-term use

At this time, due to muscle and mental fatigue, muscle excitability and contractility decrease; nerve excitability decreases, concentration is difficult, and the accuracy of sports prediction results will also decrease.

The shortcomings of the above intention recognition methods have greatly reduced the human-machine coordination of the lower limb exoskeleton robot, hindered its development, and are not conducive to the promotion of exoskeleton technology

Images