• Proceedings of the IEEK Conference
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1293-1296
• /
• 1998

This paper presents a new signature verification technique that not only maximally allows variations in signatures of each person, but also discriminates effectively forgeries from true signatures. The signature verification system is designed to detect unstable portions in signatures of same person, and to give large weight on the portion that is difficult to imitate and plays an important role in signature verification. In registration mode, the system extracts subpatterns from training samples and analizes their consistency and singularity by calculating the variance and complexity of this portion. In verification mode, the system verifies a input signature by comparing corresponding subpatterns with the weights of reference subpatterns.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제10권5호
• /
• pp.449-458
• /
• 2000

In this paper, we propose a feed identification method using neural network to predict feed in crude distillation unit. The proposed FINN(feed identifier by neural network) is functionally composed of two modes-training mode and prediction mode. Also, we implement a neural network-based soft sensor system using Borland C++(3.0) Builder. The effectiveness of the proposed neural network-based feed identification method is shown by simulation results.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 한국전산구조공학회 2003년도 봄 학술발표회 논문집
• /
• pp.382-387
• /
• 2003

In this paper, a neural networks-based damage detection method using the modal properties is presented, which can effectively reduce the effect of the modeling errors in the baseline finite element model from which the training patterns for the networks are to be generated. The differences or the ratios of the mode shape components between before and after damage are used as the input to the neural networks in this method, since they are found to be less sensitive to the modeling errors than the mode shapes themselves. Results of laboratory test on a simply supported bridge model and field test on a bridge with multiple girders confirm the applicability of the present method.

• Journal of Ocean Engineering and Technology
• /
• 제18권2호
• /
• pp.33-38
• /
• 2004

All adaptive neural network controller has been developed for a model of an underwater vehicle. This controller combines a radial basis neural network and sliding mode control techniques. No prior off-line training phase is required, and this scheme exploits the advantages of both neural network control and sliding mode control. An on-line stable adaptive law is derived using Lyapunov theory. The number of neurons and the width of Gaussian function should be chosen carefully. Performance of the controller is demonstrated through computer simulation.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제46권3호
• /
• pp.138-142
• /
• 2009

We propose an effective voice-phishing detection algorithm based on discriminative weight training. The detection of voice phishing is performed based on a Gaussian mixture model (GMM) incorporaiting minimum classification error (MCE) technique. Actually, the MCE technique is based on log-likelihood from the decoding parameter of the SMV(Selectable Mode Vocoder) directly extracted from the decoding process in the mobile phone. According to the experimental result, the proposed approach is found to be effective for the voice phishing detection.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• 제22권7호
• /
• pp.667-675
• /
• 2012

A damage estimation method for support structure of offshore wind turbine using modal parameters is presented for effective structural health monitoring. Natural frequencies and mode shapes for a support structure with monopile of an offshore wind turbine were calculated considering soil condition and added mass. A neural network was learned based on training patterns generated by the changes of natural frequency and mode shape due to various damages. Natural frequencies and mode shapes for 10 prospective damage cases were input to the trained neural network for damage estimation. The identified damage locations and severities agreed reasonably well with the accurate damages. Multi-damage cases could also be successfully estimated. Enhancement of estimation result using another parameters as input to neural network will be carried out by further study. Proposed method could be applied to other type of support structure of offshore wind turbine for structural health monitoring.

• Journal of the Korean Wood Science and Technology
• /
• 제41권5호
• /
• pp.466-473
• /
• 2013

Nondestructive evaluation (NDE) technique method using a resonance frequency mode was carried out for heat-treated wood under different conditions. The effect of heat treatment on the bending strength and NDE technique using the resonance frequency by impact hammer and force transducer mode for Korean paulownia, Pinus densiflora, Lidiodendron tulipifera and Betula costata were measured. The heat treatment temperature has been investigated at $175^{\circ}C$ and $200^{\circ}C$, respectively. There were a close relationship of dynamic modulus of elasticity and static bending modulus of elasticity to MOR. In all conditions, It was found that there were a high correlation at 1% level between dynamic modulus of elasticity and MOR, and static modulus of elasticity and MOR. However, the result indicated that correlation coefficient is higher in dynamic modulus of elasticity to MOR than that in static modulus of elasticity to MOR. Therefore, the dynamic modulus of elasticity using resonance frequency by impact hammer mode is more useful as a nondestructive evaluation method for predicting the MOR of heat-treated wood under different temperature and species conditions.

• Journal of Navigation and Port Research
• /
• 제46권5호
• /
• pp.435-440
• /
• 2022

The development and introduction of a Maritime Autonomous Surface Ship (MASS) are some of the most important changes leading to the fourth industrial era in the maritime area. The term 'MASS' refers to a ship operating independently, without human intervention, to reduce maritime accidents caused by human errors. Recent UK findings MASS also noted that particularly the dynamic positioning system will be considered to apply as newly function to a MASS. The DP system, a ship system developed decades ago and used for specific purposes like offshore operations, provides various functions to facilitate the accurate movements of the vessel, and operators can make decisions within the DP system, in addition to the ordinary ship system. In this paper, it would like to present the connection and application method with the main technical elements of the DP system in connection with the main technology of the DP system to achieve the safe operation of a MASS. In particular, among various position reference systems, the capability plot function of DP system, and the "follow target" mode in the operation mode are attractive functions that can contribute to the safe operation of autonomous ships.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.663-667
• /
• 1999

In this paper, we review the conventional speaker verification algorithm and present the text-dependent speaker verification system for application over telephone lines and its result of experiments. We apply blind-segmentation algorithm which segments speech into sub-word unit without linguistic information to the speaker verification system for training speaker model effectively with limited enrollment data. And the World-mode] that is created from PBW DB for score normalization is used. The experiments are presented in implemented system using database, which were constructed to simulate field test, and are shown 3.3% EER.

• ETRI Journal
• /
• 제34권3호
• /
• pp.450-453
• /
• 2012

IEEE 802.11n standards introduced a mixed-mode format frame structure to achieve higher throughput with multiple antennas while providing backward compatibility with legacy systems. Although multi-input multi-output channel estimation was possible only with high-throughput long training fields (HT-LTFs), the proposed scheme utilizes a legacy LTF as well as HT-LTFs in a decision feedback manner to improve the accuracy of the estimates. It was verified through theoretical analysis and simulations that the proposed scheme effectively enhances the mean square error performance.