Laptop artificial limb multi-movement-mode identifying method based on support vector data description

Abstract

The invention relates to a laptop artificial limb multi-movement-mode identifying method based on support vector data description. All present myoelectric signal classification algorithms have defects. By the support vector data description method, the invention provides a dynamic model with multi-mode characteristic extracting capability and realizes the self-adaptive adjustment of a multi-mode characteristic space. The method first obtains body lower limb myoelectric signal sample data, then establishes a support vector data description multi-type classifier, and then judges the affiliation of a test sample, and finally carries out the support vector data description incremental learning, including sample addition and sample deletion. The method well satisfies the requirement of multi-movement-mode identification during laptop lower artificial limb control, and overcomes the defects that a support vector data description off-line training method cannot effectively treat the sample data reflecting object characteristic change and the like. The method has wide application prospect in the multi-movement-mode identification of intelligent artificial limb control.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to a method for pattern recognition of electromyographic signals, in particular to an adaptive multi-motion pattern recognition method used in the control of knee upper and lower limb prostheses. Background technique [0002] Wearing prosthetics is an important way for amputees to recover. It can restore their normal state to varying degrees in terms of appearance and mobility, and is conducive to comprehensively improving the quality of life and social participation of disabled people. For the thigh amputee who lacks the knee joint, the coordinated control of the knee and upper limb prostheses is the key to ensure the natural and safe movement of the wearer. In real life, on the one hand, the movement of the lower limbs of the human body can be divided into various movement modes such as walking, running, squatting, and up and down steps. Therefore, it is necessary for the prosthe...

AI Technical Summary

Problems solved by technology

The classic SVM algorithm is a two-class classifier with supervised learning function. When dealing with multi-class problems, it must be transformed, including the following methods: (1) Convert multi-class problems into multiple one-to-one Or one-to-many problems to deal with, but the generalization error is unbounded, and samples are reused in training, so dynamic adjustment cannot be performed; (2) tree classification method needs to solve many quadratic programming problems, and the calculation amount is large; (3)k The SVM-like method needs to process all the data at one time, the constraints increase, the quadratic programming for classification is huge, and the scale of the data is limited; (4) the decision-oriented cyclic graph (Decision Direct Acyclic Graph, DDAG) method does not consider the sample The impact of unbalanced data on classification speed does not consider the impact of classification error transmission on subsequent production

[0013] To sum up, the existing EMG signal classification algorithms have deficiencies, and most of them adopt offline training and learning methods.

Images