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

Implicit identity authentication method based on gait features

An identity authentication and gait feature technology, applied in digital data authentication, neural learning methods, character and pattern recognition, etc. The effect of authentication accuracy and rich data sources

Pending Publication Date: 2022-08-02
ZHEJIANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide an authentication method based on the fact that the actual usage scenarios are complicated and changeable, the carrying methods are different, the accuracy of the existing authentication methods is not high, and the actual usability is not strong. The implicit identity authentication method based on gait features, which integrates multiple sensor data and multi-type signals as input, constructs a two-stage identity authentication framework that first classifies activity scenes and then classifies users, further improving the accuracy of user authentication

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
  • Implicit identity authentication method based on gait features
  • Implicit identity authentication method based on gait features
  • Implicit identity authentication method based on gait features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be further described in detail below with reference to the accompanying drawings and examples.

[0071] This embodiment takes the acquired gait data of 35 users in the scenarios of walking, going upstairs, and going downstairs as an example to describe the implicit identity authentication method based on gait features proposed by the present invention. The overall framework is as follows: figure 1 shown.

[0072] Step (1) Collect motion sensor data of N users, and construct a labeled gait sequence set S for training the model, as follows:

[0073] Considering the built-in accelerometer, gyroscope, magnetometer and direction meter of the mobile phone as the input data source, the accelerometer signal of the i-th user is expressed as N (N=35 in this embodiment) represents the number of users, where is the dimension of 1×L i vector of , acc i is the dimension L i ×3 matrix, L i Collection duration d by the user i (The sampling duration i...

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 an implicit identity authentication method based on gait features. Gait features extracted by an existing identity authentication method are limited, and the authentication accuracy is low. According to the method, data preprocessing is performed on an acquired gait sequence by fusing data of various motion sensors, and a gait data set is expanded by combining signals of different frequency components. According to the method, the two stages of firstly recognizing the activity scene and then authenticating the user identity are adopted, original gait data are input into the constructed classification model, and the optimal classification model is obtained through training. The obtained gait sequence is input into the trained activity scene classification model after being preprocessed, and the user classification model in the corresponding scene is called according to the judgment of the activity scene, so that whether the current user is a legal user or not can be judged. According to the method, multi-motion sensor data are fused, different types of gait data are combined, the change of an actual use scene can be coped, the authentication accuracy is further improved, and the actual usability of the method is enhanced.

Description

Technical field [0001] The invention belongs to the technical fields of biometric authentication and information security, especially the field of implicit identity authentication, and specifically relates to an implicit identity authentication method based on gait characteristics. Background technique [0002] With the development and popularity of smartphones, it has become an indispensable part of people's work, life and entertainment. Smartphones store a large amount of users' private data, including private information such as address books, photos, chat records, and bank account passwords. Once leaked, it will pose a threat to the user's personal and property security, so identity authentication technology was proposed. [0003] Explicit identity authentication is an important branch of identity authentication technology, including password-based and physiological characteristics-based identity authentication methods. The password-based authentication method means tha...

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): G06F21/32G06K9/62G06N3/04G06N3/08G01D21/02
CPCG06F21/32G06N3/08G01D21/02G06N3/045G06F18/214
Inventor 王匡兰贞谢磊陈惠芳
Owner ZHEJIANG UNIV
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