AUTHENTICATION DEVICE, AUTHENTICATION METHOD, AND COMPUTER PROGRAM

• US 20200134152A1
• Filed: 12/23/2019
• Published: 04/30/2020
• Est. Priority Date: 06/27/2017
• Status: Active Grant

• Current Assignee: Simplex Quantum Inc., The University of AIZU Public University Corporation
• Original Assignee: Simplex Quantum Inc., The University of AIZU Public University Corporation
• Inventors: CHEN, Wenxi, CHEN, Ying, HAMADA, Yuji
• Granted Patent: US 11,500,975 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24143 Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2218/16 by matching signal segments
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

An authentication method comprising creating electrocardiogram data of users; calculating a similarity between electrocardiogram data of each user and template data created by averaging electrocardiogram data of each user; creating and training a first NNmodel for every user by using similarities between electrocardiogram data of a user and template data of the same user and similarities between electrocardiogram data of a user and template data of another user, and creating and training second NNmodels for users by using similarities between electrocardiogram data of a user and template data of the user and similarities between electrocardiogram data of the user and template data of another user; and executing a first step in which the similarities calculated using electrocardiogram data for authentication of a user to be authenticated and template data are input to the first NNmodel, and executing a second step in which the similarities are input to the second NNmodels.

Claims

1. An authentication device comprising:

an electrocardiographic waveform data creation unit configured to create a plurality of pieces of electrocardiogram waveform data extracted for each heartbeat from electrocardiogram signals of a plurality of users;

a similarity calculation unit configured to calculate a similarity between each piece of electrocardiogram waveform data of each user and template waveform data created by averaging pieces of electrocardiogram waveform data of the each user;

a neural network model creation unit configured to create and train a first neural network model for every user by using similarities between pieces of electrocardiogram waveform data of a user and the template waveform data of the same user and similarities between pieces of electrocardiogram waveform data of one user and the template waveform data of another user, and create and train a plurality of second neural network models for respective users by using similarities between pieces of electrocardiogram waveform data of a certain user and the template waveform data of the certain user and similarities between pieces of electrocardiogram waveform data of the certain user and the template waveform data of another user different from the certain user; and

an authentication unit configured to, at the time of authentication, execute a first step of authentication process in which the similarities calculated using electrocardiogram waveform data for authentication created from electrocardiogram signals of a user to be authenticated and the template waveform data are input to the first neural network model created and trained in advance, and execute a second step of authentication process in which the similarities are input to the second neural network model created and trained in advance.

2. The authentication device according to claim 1, wherein the pieces of electrocardiogram waveform data and the template waveform data include a QRST wave and a QRS wave for each heartbeat.

3. The authentication device according to claim 2, further comprising the pieces of electrocardiogram waveform data and the template waveform data further include at least one of a difference wave of the QRST wave, a difference wave of the QRS wave, a kurtosis of the QRST wave, a kurtosis of the QRS wave, and a vertical height of an R peak for each heartbeat.

4. The authentication device according to claim 1, wherein the authentication unit is configured to authenticate the user as the authorized user when the first step of authentication process is successful and the second step of authentication process is successful.

5. The authentication device according to claim 1, further comprising an update unit configured to update the template waveform data of the user corresponding to the authorized user using the pieces of electrocardiogram waveform data of the authorized user as authenticated at the authentication by the authentication unit, and further update the second neural network model of the user using the updated template waveform data.

6. The authentication device according to claim 1, wherein

the electrocardiographic waveform data creation unit is configured to create a piece of electrocardiogram waveform data for authentication based on an electrocardiogram signal input at the time of authentication, and

the similarity calculation unit is configured to calculate the similarity based on the piece of electrocardiogram waveform data for authentication.

7. An authentication method comprising:

creating a plurality of pieces of electrocardiogram waveform data extracted for each heartbeat from electrocardiogram signals of a plurality of users;

calculating a similarity between each piece of electrocardiogram waveform data of each user and template waveform data created by averaging pieces of electrocardiogram waveform data of the each user;

creating and training a first neural network model for every user by using similarities between pieces of electrocardiogram waveform data of a user and the template waveform data of the same user and similarities between pieces of electrocardiogram waveform data of one user and the template waveform data of another user, and creating and training a plurality of second neural network models for respective users by using similarities between pieces of electrocardiogram waveform data of a certain user and the template waveform data of the certain user and similarities between pieces of electrocardiogram waveform data of the certain user and the template waveform data of another user different from the certain user; and

at the time of authentication, executing a first step of authentication process in which the similarities calculated using electrocardiogram waveform data for authentication created from electrocardiogram signals of a user to be authenticated and the template waveform data are input to the first neural network model created and trained in advance, and executing a second step of authentication process in which the similarities are input to the second neural network model created and trained in advance.

8. A non-transitory computer-readable storage medium storing therein a program for causing a computer to execute a process comprising:

creating a plurality of pieces of electrocardiogram waveform data extracted for each heartbeat from electrocardiogram signals of a plurality of users;

calculating a similarity between each piece of electrocardiogram waveform data of each user and template waveform data created by averaging pieces of electrocardiogram waveform data of the each user;

creating and training a first neural network model for every user by using similarities between pieces of electrocardiogram waveform data of a user and the template waveform data of the same user and similarities between pieces of electrocardiogram waveform data of one user and the template waveform data of another user, and creating and training a plurality of second neural network models for respective users by using similarities between pieces of electrocardiogram waveform data of a certain user and the template waveform data of the certain user and similarities between pieces of electrocardiogram waveform data of the certain user and the template waveform data of another user different from the certain user; and

at the time of authentication, executing a first step of authentication process in which the similarities calculated using electrocardiogram waveform data for authentication created from electrocardiogram signals of a user to be authenticated and the template waveform data are input to the first neural network model created and trained in advance, and executing a second step of authentication process in which the similarities are input to the second neural network model created and trained in advance.