• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.31-40
• /
• 2005

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.276-282
• /
• 2017

Password-based authentication is vulnerable because of its low cost and convenience, but it is still widely used. In order to increase the security of the password-based user authentication method, the password is changed frequently, and it is recommended to use a combination of numbers, alphabets and special characters when generating the password. However, it is difficult for users to remember passwords that are difficult to create and it is not easy to change passwords periodically. Therefore, in this paper, we implemented a user authentication system that does not require a password by using the USB memory that is commonly used. Authentication data used for authentication is protected by USB data stored in USB memory using USB device information to improve security. Also, the authentication data is one-time and reusable.Based on this, it is possible to have the same security as the password authentication system and the security level such as certificate or fingerprint recognition.