Authentication device, authentication method, and computer program

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.

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.