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

Smartphone User Authentication Method and System Based on EMG Signal and Siamese Neural Network

An electromyographic signal and neural network technology, applied in the field of smartphone user authentication, to achieve the effects of rotational invariance, good universality, and low false acceptance rate

Active Publication Date: 2021-04-23
BEIHANG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods still have some drawbacks

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
  • Smartphone User Authentication Method and System Based on EMG Signal and Siamese Neural Network
  • Smartphone User Authentication Method and System Based on EMG Signal and Siamese Neural Network
  • Smartphone User Authentication Method and System Based on EMG Signal and Siamese Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] Invite 40 volunteers to build the EMG data set. Volunteers included 28 men and 12 women, with an average age of 24.6 and a range of 18 to 45, which is a typical user group for smartphones. Volunteers wear Myo armbands on their forearms, such as Figure 7 Shown is a schematic diagram of the wearing position of the Myo armband in this embodiment. The Android smartphone runs the data acquisition program and records the EMG signals into a csv file. This embodiment designs a questionnaire to record the location of the smartphone of the volunteer when studying or working, such as Figure 8As shown, the commonly used locations of mobile phones surveyed in this embodiment, the frequency of the survey is marked in the upper right corner. It can be seen that volunteers usually place their smartphones on the left P1, the front P4 and the right P3. Figure 8 In , volunteers sit at a table and place their smartphones on the table. Such as Figure 9 Shown is a schematic diagram...

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 provides a smart phone user authentication method and system based on myoelectric signals and twin neural networks, belonging to the technical field of smart device identity authentication. This system includes: Myo armband, EMG signal segmentation processing module installed on the intelligent processing device, twin neural network training module and armband rotation-independent design module, and an unlocking system installed on the smart phone. The method includes: collecting the myoelectric signal in the process of the user taking the mobile phone through the Myo armband, and extracting it into a myoelectric signal matrix in segments, and using the myoelectric signal matrix to train a convolutional twin neural network. The output of the network is two myoelectric signals. The similarity of the signal; the trained twin neural network is transplanted into the smartphone, and the user is authenticated according to the similarity of the EMG signal. The invention performs identity authentication through the user's action of picking up the mobile phone, is convenient to use, has good universality and real-time performance through verification, and realizes higher identity authentication security.

Description

technical field [0001] The invention belongs to the technical field of smart device identity authentication, and in particular relates to a smart phone user authentication method and system based on electromyographic signals and twin neural networks. Background technique [0002] Screen lock is an important security feature for smartphones to prevent unauthorized access. In recent years, there have been various unlocking techniques to protect the security of smartphones. Among them, biometric-based technologies, including fingerprints and facial recognition, have gradually replaced traditional password-based methods. Compared with password methods, biometric-based methods can achieve safe and convenient authentication. However, these methods still have some drawbacks. For example, special materials can be used to obtain fingerprints to unlock smartphones; 3D printed head models and tape glasses can easily fool Apple's FaceID authentication system. Contents of the invent...

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 Patents(China)
IPC IPC(8): G06F21/32H04L9/32H04M1/72463H04M1/67A61B5/389A61B5/397A61B5/00H04M1/725
CPCH04M1/67H04L9/3231G06F21/32A61B5/72A61B5/7267A61B5/389H04M1/72463
Inventor 牛建伟范博宇张一帆
Owner BEIHANG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com