• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.3
• /
• pp.67-72
• /
• 2010

This paper presents biometrical driver verification system in car experiment through analysis of speech, and face information. We have used Mel-scale Frequency Cesptral Coefficients (MFCCs) for speaker verification using speech information. For face verification, face region is detected by AdaBoost algorithm and dimension-reduced feature vector is extracted by using principal component analysis only from face region. In this paper, we apply the extracted speech- and face feature vectors to an SVM kernel with Gaussian Mixture Models(GMM) supervector. The experimental results of the proposed approach show a clear improvement compared to a simple GMM or SVM approach.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1416-1432
• /
• 2022

The access control system is a system that allows users to selectively enter the building by granting an access key to the user for security. Access keys with weak security are easily exposed to attackers and cannot properly perform the role that authenticates users. Access code keys should be protected from forgery or spoofing. For this reason, access key verification service models is important in security. However, most models manage all access keys on one central server. This method not only interrupts all services due to server errors, but also risks forgery and spoofing in the process of transmitting access keys. Therefore, blockchain algorithms are used to reduce this risk. This paper proposes a blockchain-based access key verification service model that used distributed stored blockchain gateways on storing access keys and authenticates the user's identity based on them. To evaluate the performance of this model, an experiment was conducted to confirm the performance of the access key forgery recovery rate and the blockchain network performance. As a result, the proposed method is 100% forgery recovery rate, and the registration and verification process is evaluated at 387.58 TPS and 136.66 TPS.

• Structural Engineering and Mechanics
• /
• v.57 no.5
• /
• pp.877-895
• /
• 2016

This paper is concerned with the analytical derivation of natural sloshing frequencies of liquid in annular cylindrical tank and its verification by experiment. The whole liquid domain is divided into three simple sub-regions, and the region-wise linearized velocity potentials are derived by the separation of variables. Two sets of matrix equations for solving the natural sloshing frequencies are derived by enforcing the boundary conditions and the continuity conditions at the interfaces between sub-regions. In addition, the natural sloshing frequencies are measured by experiment and the numerical accuracy of the proposed analytical method is verified through the comparison between the analytical and experimental results. It is confirmed that the present analytical method provides the fundamental sloshing frequencies which are in an excellent agreement with the experiment. As well, the effects of the tank radial gap, the bottom flow gap and the liquid fill height on the fundamental sloshing frequency are parametrically investigated.

• MALSORI
• /
• no.47
• /
• pp.131-140
• /
• 2003

We propose a new method of generating client models for HMM based text-dependent speaker verification system with only a small amount of training data. To make a client model, statistical methods such as segmental K-means algorithm are widely used, but they do not guarantee the quality or reliability of a model when only limited data are avaliable. In this paper, we propose a blind speech segmentation based on level building DTW algorithm as an alternative method to make a client model with limited data. In addition, considering the fact that voiced sounds have much more speaker-specific information than unvoiced sounds and energy of the former is higher than that of the latter, we also propose a new score evaluation method using the observation probability raised to the power of weighting factor estimated from the normalized log energy. Our experiment shows that the proposed methods are superior to conventional HMM based speaker verification system.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.53-60
• /
• 2011

Since the importance of software reliability for game service increases continuously, the reliability evaluation becomes very important. This research performed an experiment which was intended to analyze the effect of software verification and validation, a representative activity of the software development process, on the software reliability. The results from the experiments provided the reliability evaluation based on the development process (e.g., Bayesian Belief Network based reliability estimation) with very useful bases.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.145-149
• /
• 2019

Various supplementary authentication methods are used to supplement user authentication and authorization provided by existing password verification online1. In recent years, authentication and authorization methods using user attribute information have been studied and utilized in various services. User attribute information can be divided into static information and dynamic information. The existing methods focus on research to identify users using dynamic information or to generate challenge questions for user reauthentication. Static information such as a user's home address, school, company, etc. is associated with dynamic information such as location information. We propose a method to verify user attribute information by using the association between two attribute information. For this purpose, the static information of the user is verified by using the user's location record which is dynamic information. The experiment of this paper collects the dynamic information of the actual user and extracts the static information to verify the user attributes. And we implemented the user attribute information authentication system using the proposal verification method and evaluated the utility based on applicability, convenience, and security.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.884-885
• /
• 2015

This paper presents the characteristic analysis and experiment of pitching moment in permanent magnet linear synchronous motor (PMLSM) for precision machine tools. In this paper, we define force characteristics of the moment and the moment analysis by the finite element method. Manufacture experiment and we will compare the results of finite element analysis and experimental results.

• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.277-279
• /
• 2003

Theory calculation way because verification is lacking, we compare and analyzed with calculation theory value and experiment value that is noted through a water tank model experiment based on connection theory way that is announced in existing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.797-800
• /
• 2008

Online signature verification system is widely used in banking account, credit card and so on, because system for online signature verification is easy to implementation and inexpensive. Therefore there are a lot of study on online signature verification. However there is little research about online signature is safe or not. This paper shows a way of online signature estimation using various information of signature. This paper make a experiment about relation sorority grade of online signature and 2-D information of online signature like the number of strokes and cross points, density of points, standard deviation of direction, velocity and acceleration, lengths of signature and convex hull etc. Finally, this paper presents several features of safe online signature.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.6
• /
• pp.585-591
• /
• 2002

While the multilayer perceptron(MLP) provides several advantages against the existing pattern recognition methods, it requires relatively long time in learning. This results in prolonging speaker enrollment time with a speaker verification system that uses the MLP as a classifier. This paper proposes a method that shortens the enrollment time through adopting the cohort speakers method used in the existing parametric systems and reducing the number of background speakers required to learn the MLP, and confirms the effect of the method by showing the result of an experiment that applies the method to a continuant and MLP-based speaker verification system.