Gait recognition method for lower limb prosthesis

Abstract

The invention discloses a gait recognition method for an artificial lower limb. The gait recognition method comprises the following steps: 1, acquiring gait data; 2, preprocessing the gait data; 3, extracting gait features based on a support vector machine algorithm; and 4, classifying the gaits. According to the method, the gait features are extracted based on the support vector machine algorithm, the data are normalized, the network convergence speed is increased, and the gait recognition accuracy of the artificial lower limb is effectively improved through training of a large number of test sets.

Description

Technical Field

[0001] The present invention relates to the field of integrated biomedical engineering technology, and more particularly to a gait recognition method for lower limb prostheses. Background Art

[0002] The lower limbs are the most important supporting structures of the human body, capable of bearing the weight of the body and supporting various activities of the body. Limb disabilities greatly limit the patient's mobility and seriously affect their self-care ability. In addition, the lack of lower limb support and movement will also bring physical problems to limb-disabled patients, such as muscle atrophy, osteoporosis, pressure sores, etc. Therefore, for limb-disabled patients, finding appropriate treatment methods and assistive devices is very important, which can help them restore their motor function as much as possible and improve their quality of life. At present, there are various implementation methods for gait recognition technology, such as relative motion feature recognition methods, vision-based gait recognition methods, gait recognition methods based on contour feature fusion, etc., but the existing methods have the problem of low accuracy. Summary of the Invention

[0003] In view of the above situation, in order to make up for the shortcomings of the low accuracy of traditional lower limb prosthesis gait recognition methods, the present invention proposes a gait recognition method for lower limb prostheses, effectively improving the accuracy of gait recognition.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] A gait recognition method for lower limb prostheses, comprising the following steps:

[0006] (1) Collect gait data;

[0007] (2) Preprocess the gait data;

[0008] (3) Extract gait features based on the support vector machine algorithm;

[0009] (4) Classify the gait.

[0010] Compared with the prior art, the beneficial effects of the present invention are:

[0011] The present invention extracts gait features based on the support vector machine algorithm, normalizes the data, improves the network convergence speed, and effectively improves the gait recognition accuracy of lower limb prostheses through the training of a large number of test sets. Brief Description of the Drawings

[0012] Figure 1 It is a flowchart of the present invention. Detailed Embodiment

[0013] The present invention will be described below with reference to the accompanying drawings and specific embodiments.

[0014] A gait recognition method for a lower limb prosthesis, specifically including the following steps.

[0015] Step 1: Collect gait data.

[0016] Start the lower limb prosthesis, and the system begins to collect gait data.

[0017] Step 2: Preprocess the gait data.

[0018] Use the moving average filtering method to filter the gait data, reducing the time error with the original data while ensuring the original smoothing effect.

[0019] The moving average filtering function is:

[0020]

[0021] Where L is the width of the sliding window, i is the serial number of the data, and is the amplitude value of the original data point i.

[0022] After filtering the gait data, perform data normalization so that the data values of each feature fall within the same scale range, eliminating the influence of dimensions and making the comparison and processing of features more reasonable and unified.

[0023] Step 3: Extract gait features based on the support vector machine algorithm.

[0024] Combine 4 gait phases (heel strike phase, heel and sole contact phase, sole contact phase, and toe contact phase) to extract 4 features: the maximum value, minimum value, average value, and standard deviation of the data. Divide the feature data into a training set and a test set for training to improve the recognition accuracy. This system includes 6 binary classifiers, which respectively distinguish the early support phase and the initial support phase, the early support phase and the mid-support phase, the early support phase and the late support phase, the initial support phase and the mid-support phase, the initial support phase and the late support phase, and the mid-support phase and the late support phase.

[0025] Step 4: Classify the gait.

[0026] Through the "voting" of 6 binary classifiers, the gait phase with the most votes is the phase category where the gait sample is located.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A gait recognition method for a lower limb prosthesis, characterized in that: It includes the following steps: (1) Collect gait data; (2) Preprocess the gait data; (3) Extract gait features based on the support vector machine algorithm; (4) Classify the gait.

Images