• Journal of the Korean Data and Information Science Society
• /
• v.28 no.1
• /
• pp.173-183
• /
• 2017

We investigate the factors affecting the price of apartments using the spatial and temporal data of private real estate prices. The factors affecting the price of apartment were analyzed using geographical and temporal weighted regression (GTWR) model which incorporates the temporal and spatial variation. In contrast to the OLS, a general approach used in previous studies, and GWR method which is most widely used for analyzing spatial data, GTWR considers both temporal and spatial characteristics of the house price, and leads to better description of the house price determination. Year of construction and floor area are selected as the significant factors from the analysis, and the house price are affected by them temporally and geographically.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.173-185
• /
• 2009

This paper proposes two new image contrast enhancement methods, RSWHE (Recursively Separated and Weighted Histogram Equalization) and RSWHS (Recursively Separated and Weighted Histogram Specification). RSWHE is a histogram equalization method based on histogram decomposition and weighting, whereas RSWHS is a histogram specification method based on histogram decomposition and weighting. The two proposed methods work as follows: 1) decompose an input histogram based on the image's mean brightness, 2) compute the probability for the area corresponding to each sub-histogram, 3) modify the sub-histogram by weighting it with the computed probability value, 4) lastly, perform histogram equalization (in the case of RSWHE) or histogram specification (in the case of RSWHS) on the modified sub-histograms independently. Experimental results show that RSWHE and RSWHS outperform other methods in terms of contrast enhancement and mean brightness preservation as well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.206-211
• /
• 2009

This paper presents a methodology to 1-day-forecast stock index using the automatic feature extraction method based on the neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by automatically removing the worst input features one by one. CPP$_{n,m}$(Current Price Position of the day n: a percentage of the difference between the price of the day n and the moving average from the day n-1 to the day n-m) and the 2 wavelet transformed coefficients from the recent 32 days of CPP$_{n,m}$ are selected as minimized features using bounded sum of weighted fuzzy membership functions (BSWFMs). For the data sets, from 1989 to 1998, the proposed method shows that the forecast rate is 60.93%.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.721-724
• /
• 2005

In this study the spatial distribution characters of forest in forest damaged area were first considered by analyzing spatial data and monitoring forest landscape. Then suitable tree species on each site were selected through the weighted score analysis of GIS analysis methods. Finally, the best forest stand arrangement method could be presented on the 3D based simulation system for the advanced reforestation technology in Korea. For this purpose, the virtual reforestation system was implemented by using the concept of virtual GIS and CBD (Component Based Development) method. By use of this system the change offorest landscape of burnt forest area some years after reforestation practice could be detected and monitored by applying the site index and 3D modeling method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.378-382
• /
• 2006

This paper presents an approach to detect premature ventricular contractions(PVC) using the neural network with weighted fuzzy membership functions(NEWFM). NEWFM classifies normal and PVC beats by the trained weighted fuzzy membership functions using wavelet transformed coefficients extracted from the MIT-BIH PVC database. The two most important coefficients are selected by the non-overlap area distribution measurement method to minimize the classification rules that show PVC classification rate of 99.90%. By Presenting locations of the extracted two coefficients based on the R wave location, it is shown that PVC can be detected using only information of the two portions.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.29 no.3
• /
• pp.211-216
• /
• 2007

Temporomandibular joint disorders (TMD) often show muscular disorder, internal derangement and degenerative change of articular surface of the condyle. It is important to choose adequate diagnostic method for obtaining data for the diagnosis and treatment. Magnetic Resonance Imaging (MRI) has some advantages, because it shows good resolution image for the soft tissue and it is not invasive to the human body. We have performed serial research about the retrodiscal tissue of the TMJ according to the progress of the disease, using T2 weighted image, since 2002. In this study, we applicated resized observation area to compare signal intensity between the retrodiscal tissue of the TMJ and cerebral gray matter, using T2 weighted image.

• Journal of Korean Society of Rural Planning
• /
• v.14 no.2
• /
• pp.55-64
• /
• 2008

This study aims to analyze the sensitivity of WSM(weighted scenario method)-AHP method according to variation of nonlinear exponent for accessibility criteria, which are used to make urbanization potential maps with the optimal weighting value for multiple criteria in grid-based GIS technique. Besides this study tried to develop WSM-AHP2 which is simplified by using rank of the potential value for each scenario. The two methods were applied to the test area, Suwon city located south area of Seoul, with time series land-use maps of 1986 and 1996. The evaluation system of urbanization potential have 7 criteria including 6 accessibility criteria. The results of WSM-AHP2, the optimal weighting values and their corresponding potential maps, have almost similar with those of WSM-AHP. In the application of CA(cellular automata) model for expansion of urbanized area using the three potential maps by WSM-AHP, WSM-AHP2, and specialists's AHP evaluation, it also showed that the accuracy of simulation for actual urban area is the highest in the potential map of WSM-AHP, followed by WSM-AHP2 and specialists's AHP evaluation. From the results of this study, WSM-AHP and simplified WSM-AHP2 will be used to generate the optimal potential maps for land-use planning in urban fringe area.

• Environmental and Resource Economics Review
• /
• v.12 no.4
• /
• pp.545-557
• /
• 2003

A new semiparametric estimator of a dichotomous choice contingent valuation model is proposed by adapting the well-known density weighted average derivative of the regression function. A small sample behavior of the estimator is demonstrated very briefly by a simulation and the estimator is applied to estimate the WTP for preserving the Dong River area in Korea.

• Proceedings of the KSMRM Conference
• /
• 2002.11a
• /
• pp.114-114
• /
• 2002

Purpose： To know the fate of Gadophrin-2-enhanced areas in hearts with acute reperfused myocardial infarction. Method： The left anterior descending branches of coronary arteries were occluded for 90 min and reperfused for 60 min in 15 rabbits. Then, Gadophrin-2 (0.05 mmol/kg) was injected via ear veins. Short-axial T1-weighted spin echo images and fast cine images were obtained 24 hours after injection of Gadophrin-2. After four weeks, short-axial cine MRI was performed and T1-weighted spin echo Images were obtained 5 min and 15 min after injection of Gd-DTPA (0.2 mmol/kg). The animals were sacrificed and short-axial slices of the specimen were stained with 1.5% triphenyltetrazolium chloride (TTC) solution.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.1-7
• /
• 2011

The methodology of KOSPI forecast has been considered as one of the most difficult problem to develop accurately since short-term KOSPI is correlated with various factors including politics and economics. In this paper, we presents a methodology for forecasting short-term trends of stock price for five days using the feature selection method based on a neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by removing the worst input features one by one. A technical indicator are selected for preprocessing KOSPI data in the first step. In the second step, thirty-nine numbers of input features are produced by wavelet transforms. Twelve numbers of input features are selected as the minimized numbers of input features from thirty-nine numbers of input features using the non-overlap area distribution measurement method. The proposed method shows that sensitivity, specificity, and accuracy rates are 72.79%, 74.76%, and 73.84%, respectively.