• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.122-127
• /
• 1998

This paper presents the neuro-fuzzy classifier derived from the generic model of a 3-layer fuzzy perceptron and developed the classification software based on the neuro-fuzzl model. Also, a comparison of the neuro-fuzzy and maximum-likelihood classifiers is presented in this paper. The Airborne Multispectral Scanner(AMS) imagery of Tae-Duk Science Complex Town were used for this comparison. The neuro-fuzzy classifier was more considerably accurate in the mixed composition area like "bare soil" , "dried grass" and "coniferous tree", however, the "cement road" and "asphalt road" classified more correctly with the maximum-likelihood classifier than the neuro-fuzzy classifier. Thus, the neuro-fuzzy model can be used to classify the mixed composition area like the natural environment of korea peninsula. From this research we conclude that the neuro-fuzzy classifier was superior in suppression of mixed pixel classification errors, and more robust to training site heterogeneity and the use of class labels for land use that are mixtures of land cover signatures.

• Journal of Soil and Groundwater Environment
• /
• v.12 no.1
• /
• pp.44-52
• /
• 2007

This study reviewed the overall process of application of contaminant fate and transport model as part of risk assessment. Site characterization and establishment of a conceptual model prior to establishing or selecting a appropriate model were described. Types of models, model selection guidance, and generic site conditions for model application were presented, the process of model calibration, validation, and sensitivity analysis were reviewed. Objectives of modeling should be defined before model selection, and the complexity of selected models should balance the quantity and quality of available input data with the desired model output. If model output is highly sensitive to an assumed or default value of input parameter, or fate and transport models cannot be adequately calibrated or validated, consideration should be given to other options such as using measured data or using another model.

• Korean Journal of Remote Sensing
• /
• v.7 no.1
• /
• pp.1-12
• /
• 1991

토양의 특성은 토지이용에 제한을 가하는 물리적 요소로 활용되고 있으며, 이러한 토양 특성정보는 전통적으로 전문가에 의한 해석에 기초하여 토양도에 서류 형태로 저장, 보관되어 왔 다. 최근에 널리 쓰이기 시작하는 토지정보체계(Geographical Information System, GIS)는 종래의 자료저장, 해석기법을 digital database라는 특성을 이용하여, 새로운 자료분석이 가능한 도구를 제공하게 되었다. 본 연구에서는 위상적으로 체계화된(topologically structured) vector형 토지정 보체계의 관계형 Database Management System(DBMS)과 토양 전문가의 지식을 결합하여 포괄 적인 토양적지 평가모델을 수립한 후, 전문가에 의한 평가, 토양도에 수록된 평가와 각각 비교하 였다. 비교한 결과, 본 연구에서 수립된 토양적지 평가모델은 전문가에 의한 평가와 크게 다르지 않았으며, 이는 토양도의 평가와 비교하여서도 마찬가지였다. 따라서, 본 연구에서 시도된 포괄적 인 토양적지 분석모델은 계속 발전하여 토지정보체계에서의 전문가 기법으로 활용이 가능하다고 판단되어진다.

• The KIPS Transactions:PartD
• /
• v.9D no.5
• /
• pp.939-944
• /
• 2002

In this paper, we propose and apply new classification method to the remotely sensed image acquired from airborne multi-spectral scanner. This is a neuro-fuzzy image classifier derived from the generic model of a 3-layer fuzzy perceptron. We implement a classification software system with the proposed method for land cover image classification. Comparisons with the proposed and maximum-likelihood classifiers are also presented. The results show that the neuro-fuzzy classification method classifies more accurately than the maximum likelihood method. In comparing the maximum-likelihood classification map with the neuro-fuzzy classification map, it is apparent that there is more different as amount as 7.96% in the overall accuracy. Most of the differences are in the "Building" and "Pine tree", for which the neuro-fuzzy classifier was considerably more accurate. However, the "Bare soil" is classified more correctly with the maximum-likelihood classifier rather than the neuro-fuzzy classifier.

• Geomechanics and Engineering
• /
• v.25 no.4
• /
• pp.303-315
• /
• 2021

A rigorous and generic similarity solution is developed for assessment of the undrained expansion responses of a cylindrical cavity expansion in K₀-consolidated anisotropic soils. A K₀-consolidated anisotropic modified Cam-clay (K₀-AMCC) model that can represent the initial stress anisotropy and the effects of stress-induced anisotropy is used to model the soil behaviors during cavity expansion. All the seven basic unknowns, the three stress components, the pore water pressure, the particle velocity, the specific volume and the hardening parameter, are reduced to the functions of a dimensionless radial coordinate and are taken as coupled variables to formulate the problem. The governing equations are formulated by making use of the equilibrium equation, the constitutive equation, the consistency condition, the continuity condition and the undrained condition, which are then solved as an initial value problem. The proposed rigorous similarity solution is compared with some well-documented rigorous solutions to validate the solution and to highlight the special expansion responses in anisotropic soils. The results reveal that the present solution can yield more predictions for cavity expansion problems in soils with initial anisotropic stresses.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.12
• /
• pp.7-23
• /
• 2021

Underground utility tunnels, which contribute to supply of electricity, communication, water and heat, are critical lifelines of an urban area. In case service is discontinued or functional disruption happens, there will be a huge socio-economic impact. For the improved seismic design and evaluation of underground structures, this study proposes a ground displacement measure when the site is subjected to a scenario earthquake based on hazard-consistent source spectra and site amplification/attenuation. This measure provides a rational estimation of ground displacement and can be an alternative to existing response displacement methods.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.13 no.6
• /
• pp.11-25
• /
• 2009

A method of instrumentally estimating the seismic intensity (MMI) based on Fourier Acceleration Spectrum, which is the so-called 'FAS MMI method' of Sokolov and Wald (2002), was considered for its applicability to Korea. In order to implement the FAS MMI method, the empirical models of mean (m) and standard deviation (${\sigma}$) for Korea were derived for MMI ${\leq}$ IV according to individual seismic intensity by using the site-consistent horizontal FAS of 580 records from 65 isoseismal maps prepared based on the reported MMI of Korea Meteorological Administration. The site-consistent FAS at a site were obtained by correcting the observed FAS for the difference of the site amplification function relative to that of the target site of Class D station (Yun and Suh, 2007) which was evaluated to be a representative site for the generic soil profile of Korea. The FAS m model for MMI ${\leq}$ IV follows the overall linear relation in log space according to seismic intensities, featuring the FAS mean model for MMI = IV similar to that of the global model of Sokolov and Wald (2002). The ${\sigma}$-values of the FAS model are found to be greater than those of the global model for MMI ${\geq}$ V, while significantly lower than those of the global model for MMI = IV.

• Journal of the Korean Geographical Society
• /
• v.39 no.4
• /
• pp.495-513
• /
• 2004

The shape of land surface work as a cradle for various environmental processes and human activities. As spatially distributed process modelings become increasing important in current research communities, a classification system that delineates land surface into characteristic geomorphological units is a pre-requisite for sustainable land use planning and management. Existing classification systems are either morphometric or generic, which have limitations to characterize continuous ecological processes over the landscape. A new classification system was developed to delineate the land surface into different geomorphological units from Digital Elevation Models(DEMs). This model assumes that there are pedo-geomorphological units in which distinct sets of hydrological, pedological, and consequent ecological processes occur. The classification system first divides the whole landsurface into eight soil-landscape units. Possible energy and material nows over the land surface were interpreted using a continuity equation of mass flow along the hillslope, and subsequently implemented in terrain analysis procedures. The developed models were tested at a 12$\textrm{km}^2$ area in Yangpyeong-gun, Kyeongi-do, Korea. The method proposed effectively delineates land surface into distinct pedo-geomorphological units, which identify the geomorphological characteristics over a large area at a low cost. The delineated landscape units mal provide a basic information for natural resource survey and environmental modeling practices.