• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.395-398
• /
• 1998

In this paper, a method for the improvement of learning speed and convergence rate was proposed applied it to physiological neural structure with the advantages of artificial neural networks and fuzzy theory to physiological neuron structure, To compare the proposed method with conventional the single layer perception algorithm, we applied these algorithms bit parity problem and pattern recognition containing noise. The simulation result indicated that our learning algorithm reduces the possibility of local minima more than the conventional single layer perception does. Furthermore we show that our learning algorithm guarantees the convergence.

• Textile Coloration and Finishing
• /
• v.13 no.3
• /
• pp.180-187
• /
• 2001

Generally, polyester microfiber has much greater dye uptake than that of regular ones. In spite of high dye up-take visual shade depth of dyed fabric decreases with smaller denier, which results in poor washing fastness of dyed fabric. In this study, in order to investigate the washing fastness, polyester microfiber fabric was dyed by using two type of disperse dyes and treated with 3 different reduction clearing methods. The reduction clearing methods in this study are normal alkaline reduction clearing, $N_2$ gas replacement method, and ultrasonic treatment during reduction clearing. The results were as followings ; The most important factors affecting the washing fastness of polyester artificial suede fabric were found to be the reduction clearing method, the chemical structure of used disperse dyes and the structure and denier of fibers. It was also obtained that the heat treatment of dyed fabric decreased the washing fastness due to the dye migration from inner phase to surface.

• Knowledge Management Research
• /
• v.21 no.1
• /
• pp.41-59
• /
• 2020

This explorative study examines the difference in firm performance according to the adoption of the core technology of the Fourth industrial revolution, including artificial intelligence(AI), internet of things (IoT), cloud computing, and big data technology. Additionally, we investigate the importance of internal organizational structure exclusively responsible for information security. We analyze unique microdata offered by the Korea Information Society Development Institute to examine the impact of the adoption of the new technologies and the existence of organizational structure for information protection on firm performance, i.e., firm sales. By considering the core information technology as powerful knowledge assets, we argue that the adoption of such technology leads firms to have comparative advantage comparing to the competitors. Also, we emphasize the need to consider the organizational structure suitable for information security, which can become a structural asset of a firm.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.76-78
• /
• 2005

When the data from the artificial satellite is analyzed, recent years it is perceived to vegetation index using BRF(Bidirectional Reflectance Factor) of the observation target. To make the BRF models, it is important to measure the 3D structure of the observation target actually. In this study, it is proposed to the observation technique by using laser scanning data. Also, our team has been operating the radio controlled helicopter which can fly over the tall forest canopy and it can be equipped the measurement system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.436-439
• /
• 2007

Noise reduction in the image is very important to improve the quality of the image. This paper discusses a new noise reduction technique which uses the On/Off spatio-temporal structure of the receptive fields. Also this paper proposes a structurally improved artificial vision system which incorporates the sphere type retina structure, an improved On/Off spatio-temporal receptive fields structure, and chiasm for hemianopia testing.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.170-173
• /
• 2004

When the data from the artificial satellite is analyzed, recent years it is perceived to vegetation index using BRF(Bi-directional Reflectance Factor) of the observation target. To make the BRF models, it is important to measure the 3D structure of the observation target actually. In this study, it is proposed to the observation technique by using multi-angle stereo pair image, and shown the observation result in grassland area. Also, our team has been operating the radio controlled helicopter which can fly over the tall forest canopy and it can be equipped the measurement system.

• Journal of the Korean Chemical Society
• /
• v.58 no.6
• /
• pp.543-552
• /
• 2014

A quantitative structure activity relationship (QSAR) study is performed for modeling and prediction of oral bioavailabilities of 216 diverse set of drugs. After calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regression (MLR), artificial neural network (ANN), support vector machine (SVM) and random forest (RF) techniques. Comparison between statistical parameters of these models indicates the suitability of SVM over other models. The root mean square errors of SVM model were 5.933 and 4.934 for training and test sets, respectively. Robustness and reliability of the developed SVM model was evaluated by performing of leave many out cross validation test, which produces the statistic of $Q^2_{SVM}=0.603$ and SPRESS = 7.902. Moreover, the chemical applicability domains of model were determined via leverage approach. The results of this study revealed the applicability of QSAR approach by using SVM in prediction of oral bioavailability of drugs.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.127-132
• /
• 2006

Recently, several displacement measuring instruments such a GPS are substantially developed by development of an artificial satellite. Considering this trend, in future displacement measurement will be a very efficiency method, therefore we need to develop structure maintenance & management by using displacement measuring instruments. In this study, I suggest to maintenance & management method about simple beams and cantilever beams which are very important structurein civil engineering by using displacements. I suggest a system which trace behavior of beams by combining some measurement points and a specific displacement function and research that tl1e proper number of measurement and optimum measurement points to efficiently use the system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.12
• /
• pp.1183-1187
• /
• 2011

In this paper, an optimal FIR (Finite-Impulse-Response) filter is proposed for discrete time-varying state-space models. The proposed filter estimates the current state using measured output samples on the recent time horizon so that the variance of the estimation error is minimized. It is designed to be linear, unbiased, with an FIR structure, and is independent of any state information. Due to its FIR structure, the proposed filter is believed to be robust for modeling uncertainty or numerical errors than other IIR filters, such as the Kalman filter. For a general system with system and measurement noise, the proposed filter is derived without any artificial assumptions such as the nonsingular assumption of the system matrix A and any infinite covariance of the initial state. A numerical example show that the proposed FIR filter has better performance than the Kalman filter based on the IIR (Infinite- Impulse-Response) structure when modeling uncertainties exist.

• 한국전산유체공학회:학술대회논문집
• /
• 2008.03b
• /
• pp.180-183
• /
• 2008

This paper is about the ocean current power generation using sea water incoming into the lake surrounded by barrages and sea water discharged from a dam made of artificial structures. In operation of a tidal power plant, the sea water discharged from a turbine structure and a gate structure of a tidal power plant is faster than the tidal current caused by tides in nature and has better characteristics than that to run ocean current turbines. It is shown that the sea water discharged after generating electricity through a turbine generator of a tidal power plant and the sea water discharged from a gate structure of a tidal dam still have kinetic energy high enough to run an ocean current turbine and produce valuable electricity.