• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.10 no.3
• /
• pp.103-109
• /
• 2011

With the growing popularity of digital video applications, those areas of the efficient transmit, storage management, and search technology for video data are emerging as an important core technology. To be an effective video indexing system, users need to be able to find the video segments that they want. Unfortunately, video data is difficult to manage because of its unstructured data type and large volume with linear forms. This paper proposes a shot verification using visual rhythm and video retrieval system. The shot verification is designed to detect a segment from video easily and quickly, known as shot boundaries, just by changing the visual rhythm without playing the image. Therefore, this can decrease the false detected shots and generate the unidentified shots and key frames. The retrieval system is constructed in terms of visual descriptor from the list of MPEG-7. The effectiveness of the proposed shot verification process and video retrieval system is demonstrated.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.385-388
• /
• 2002

In this paper, a new signature verification method is proposed. In the proposed method, on-line signature features are decomposed into multi-level signals by using the discrete wavelet transform, and then they are verified using the adaptive algorithm in time-frequency domain. Through computer simulations, the effectiveness of the proposed method is examined.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2001.04a
• /
• pp.394-402
• /
• 2001

In order to lessen cable vibration, new cable damper system with high damping rubber was developed using the basis of the LRB design scheme. The analysis model of cable damper system incorporate voigt-kelvin damper model into the nonlinear cable analysis model. To achieve maximum damping capacity both reducing damper stiffness and developing high damping rubber were performed. As a result of verification test, the high damping rubber damper show its effectiveness in improving cable damping capacity.

• Management & Information Systems Review
• /
• v.17
• /
• pp.161-189
• /
• 2005

As the importance of intellectual assets has been brought into relief, this study aims at positively verifying where the intellectual workers' overall level of their knowledge conversion preference and their job character has reached, and how much the knowledge conversion preference, the job character and the fitness of both factors affects the job effectiveness respectively. For this purpose 3 types of research hypotheses were set up and the result of the verification of the hypotheses is summarized as follows: First, the verification of the relation between the knowledge conversion preference and the job effectiveness revealed that the workers who have the higher synthetic ability in knowledge conversion preference show the higher job satisfaction and job product. Secondly, the verification of the relation between the MPS representing the job character by measured index and the job satisfaction revealed that the absolute value of relative coefficient between the 4 factors excluding the public welfare factor and the MPS is 4, interpreted as medium correlation. Thirdly, the analysis on the degree of relation between the job product measured by the quality of job result and the input effort and the MPS showed that the absolute value of person relative coefficient is 5, interpreted not only as medium correlation but also very meaningful. Accordingly, the main purpose of this study was to give a guideline which can be utilized as an indicator for educating, training and placing the workers. As results, the main effect that the variable of knowledge conversion preference and job character chosen as the independent variable influences on the dependent variable of job satisfaction and job product is very meaningful except the public welfare factor.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.247-257
• /
• 2016

It is required to have Personal Information Agreement when a financial company uses personal information by the Law of Privacy. So, financial companies have to demand customers the submission of Personal Information Agreement. Thus, financial companies have made Personal Information Agreement in various formats for customers. However, financial companies are lack of a verification process, the cases of collecting invalid Agreement often occurred. This study focuses on the verification process of Personal Information Agreement and the contents of Personal Information Agreement. In conclusion, this study proposes an improved model that added to the process of verification for the concept of Agreement. Based on this study, I hope financial companies to reform their agreement process and to improve the effectiveness on the implementation of Personal Information Utilization Agreement.

• Journal of the Korea Society for Simulation
• /
• v.28 no.1
• /
• pp.41-47
• /
• 2019

Defense simulation is actively used to test various weapon systems and evaluate their effectiveness. The AddSIM environment is a simulation framework designed to support the weapon systems dealt with in defense simulation from an integrated point of view and is designed for reuse and scalability. Models used in AddSIM require base model structure fidelity and verification of user code area. Therefore, this paper describes the dynamic verification method used for completeness of models used in AddSIM. For the dynamic verification of user code, the specification method and the verification algorithm are described. Also, we introduce the prototype of the dynamic verifier implemented based on verification specification method and algorithm. The case study analyzes the verification results based on the simulation example implemented in AddSIM environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1099-1104
• /
• 2013

This paper presents a learning-based visual inspection method that addresses the need for an improved adaptability of a visual inspection system for parts verification in panorama sunroof assembly lines. It is essential to ensure that the many parts required (bolts and nuts, etc.) are properly installed in the PLC sunroof manufacturing process. Instead of human inspectors, a visual inspection system can automatically perform parts verification tasks to assure that parts are properly installed while rejecting any that are improperly assembled. The proposed visual inspection method is able to adapt to changing inspection tasks and environmental conditions through an efficient learning process. The proposed system consists of two major modules: learning mode and test mode. The SVM (Support Vector Machine) learning algorithm is employed to implement part learning and verification. The proposed method is very robust for changing environmental conditions, and various experimental results show the effectiveness of the proposed method.

• The Journal of the Korea Contents Association
• /
• v.2 no.1
• /
• pp.39-45
• /
• 2002

Author verification system of ancient literatures or art works are important in the aspects of cultural properties control and owner's properties estimation. For this, experts of cultural properties administration have been done in inspecting the author verification. But inspection fee of experts is expensive. Therefore, social demands are increasing the automatic author verification system. For this, this paper proposes the automatic author verification system by the edge structure analysis of art works. The method of edge structure analysis is adopted because of these feature factors are significant in the several feature factors. In the near future, 1 will develope the entire system to teat the various art works by comining several feature vectors. Finally, the effectiveness of this paper is demonstrated by the several experiments.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.39-49
• /
• 2014

Cyber threats on the Internet are tremendously increasing and their techniques are also evolving constantly. Intrusion Detection System (IDS) is one of the powerful solutions for detecting and analyzing the cyber attacks in realtime. Most organizations deploy it into their networks and operate it for security monitoring and response service. However, IDS has a fatal problem in that it raises a large number of alerts and most of them are false positives. In order to cope with this problem, many approaches have been proposed for the purpose of automatically identifying whether the IDS alerts are caused by real attacks or not. In this paper, we present an alert verification method based on correlation analysis between vulnerability inspection results for real systems that should be protected and the IDS alerts. In addition, we carry out practical experiments to demonstrate the effectiveness of the proposed verification method using two types of real data, i.e., the IDS alerts and the vulnerability inspection results.