Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Analysis and processing system for mass plantar pressure data

A plantar pressure, analysis and processing technology, applied in the field of analysis and processing systems for massive plantar pressure data, can solve problems such as unsatisfactory plantar pressure data analysis and processing methods, and achieve the effect of standardized and effective processing methods

Inactive Publication Date: 2019-04-05
DALIAN EVERSPRY SCI & TECH
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current analysis and processing methods of plantar pressure data are not ideal.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Analysis and processing system for mass plantar pressure data
  • Analysis and processing system for mass plantar pressure data
  • Analysis and processing system for mass plantar pressure data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides an analysis and processing system for a large amount of plantar pressure data, including:

[0056] 1. Mass footprint data acquisition module:

[0057] This module starts with the collection of user footprint data, which mainly includes dynamic and static footprint data; then obtains the personal information entered by the user, including the user's gender, age, height, weight, etc.; and finally acquires a large amount of data.

[0058] 2. Data attribute unified module;

[0059] 1) The data type is unified:

[0060] (1) Real-time dynamic data needs to be converted into static data through average processing for a certain period of time. During the averaging process, the dynamic data that cannot be obtained is used for feature extraction, and one-dimensional data is directly formed for training or testing;

[0061] (2) For the data that can obtain the characteristic information of the stride in the walking process, it is necessary to use automat...

Embodiment 2

[0090] This embodiment provides the situation that the data processed in Embodiment 1 is used for the adjustment and training of the deep learning neural network:

[0091] The preprocessed data is applied to classification (such as gender, age, height, and weight determination): (Here, the preprocessed overall image and each local area image can be trained separately to obtain models for different plantar regions)

[0092] (1) Training data preparation: the two-dimensional image data of the training set and the verification set after preprocessing are artificially divided into N groups according to the classification requirements;

[0093] (2) Group training based on the CNN network. The improved AlexNet network is used here. The network improvement is as follows:

[0094] A. Initial network:

[0095] Network composition: 4 layers of convolutional layers, 2 layers of pooling layers, and 2 layers of fully connected layers.

[0096] Internet connection:

[0097] conv1+pooling...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a mass sole pressure data analyzing and processing system which comprises a mass footprint data obtaining module, a data processing module and a mass sole pressure data analyzing and processing module, the mass footprint data obtaining module comprises dynamic footprint data obtaining, static footprint data obtaining and personal information input by a user; The data attribute unification module comprises a data type unification module and a data dimension unification module; The label file making module is used for classifying and sorting the acquired mass footprint data and user information; The image preprocessing module is used for preprocessing the barefoot or sock wearing footprint image data; The data set making module is used for dividing the preprocessed barefoot or sock wearing footprint image data into a training set and a verification set; And the deep learning network training and adjusting module is used for designing a deep learning network for massive footprint images and circularly carrying out deep learning network training and adjusting. According to the invention, the processing of mass footprint data is realized, so that the processing mode of mass footprint data is standard and effective.

Description

technical field [0001] The invention relates to a data analysis and processing system, in particular to a massive plantar pressure data analysis and processing system. Background technique [0002] The distribution of plantar pressure can reflect different degrees of posture of people. Plantar pressure can be applied in various fields. Disease diagnosis, detection of walking posture in rehabilitation training to judge the degree of recovery of patients, and providing solutions for the rehabilitation of lower extremity diseases, etc. At the same time, in criminal detection, information such as judging people's height and weight, and ground interactive games are also used. However, the analysis and processing methods of plantar pressure data are not ideal at present. Contents of the invention [0003] This application provides an analysis and processing system for massive plantar pressure data, which is used to organize, analyze and utilize the acquired massive footprint da...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/62G06N3/08
CPCG06N3/084G06V40/10G06V10/267G06F18/214
Inventor 董波郭宝珠张吉昌于昕晔王国建
Owner DALIAN EVERSPRY SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products