• Journal of the Korean GEO-environmental Society
• /
• v.19 no.9
• /
• pp.29-36
• /
• 2018

Several studies have been conducted on monitoring system and automatic measuring instruments to prevent slope failure in advance in Korea and overseas. However, these studies have quite complex structure. Since most of the measurement systems are installed on the slope surface, the researches are carried on the measurement system that detects sign of slope collapse in advance and alerts are still unsatisfactory. In this study, slope collapse experiments were carried out to understand the slope failure mechanism according to rainfall conditions. The water content and displacement behavior at the early stage of the slope failure were analyzed through the measurement of the ground displacement and water content. The results of this study can be used by local government as a basic data for the design of slope failure alarm system to evacuate residents in case of slope failure or landslide due to heavy rainfall.

• Journal of the Korean association of regional geographers
• /
• v.20 no.2
• /
• pp.217-229
• /
• 2014

This study was performed to identify neighborhood deprivation indicators associated with health and to test the contextual effects of those indicators on individual health. This study calculated SMR based on Dong district and see the differences of prediction across deprivation index and indicators. Then, a multi-level analysis using HGLM was conducted to test the contextual effect of neighborhood depreivation indicators on health after controlling for demographic and socioeconomic status of individuals. The results showed that regional SMR had strong correlations with land price, education, welfare recipients, female household proportion in Dong district but failed to show the correlation with individual health and neighborhood deprivation. Individual health was only associated with individual level of demographic and socioeconomic status. That is, spatial dispersion of illness is understood as the distribution of social classes in terms of socioeconomic status of individuals, not the contextual aspects of community.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.11-19
• /
• 2018

Although many researches related to monitoring and automatic measuring devices for early warning system during slope failure have been carried out in Korea and aboard, most of the researches have installed measuring devices on the slope surface, and there are only few researches about warning systems that can detect and warn before slope failure and disaster occurs. In this study, slope failure simulation experiment was performed by attaching sensors to rock bolts, and initial slope behavior characteristics during slope failure were analyzed. Also, the experiment results were compared and reviewed with varied slope conditions, i.e. shotcrete slope and natural slope, and varied material conditions, i.e. GFRP and steel rock bolt. This study can be used as a basic data in development of warning and alarm system for early evacuation through early detection and warning before slope failure occurs in steep slopes and slope failure vulnerable areas.

• The Journal of Information Systems
• /
• v.30 no.2
• /
• pp.147-163
• /
• 2021

Purpose The study aims to predict real estate prices by utilizing regional characteristics. Since real estate has the characteristic of immobility, the characteristics of a region have a great influence on the price of real estate. In addition, real estate prices are closely related to economic development and are a major concern for policy makers and investors. Accurate house price forecasting is necessary to prepare for the impact of house price fluctuations. To improve the performance of our predictive models, we applied LSTM, a widely used deep learning technique for predicting time series data. Design/methodology/approach This study used time series data on real estate prices provided by the Ministry of Land, Infrastructure and Transport. For time series data preprocessing, HP filters were applied to decompose trends and SOM was used to cluster regions with similar price directions. To build a real estate price prediction model, SVR and LSTM were applied, and the prices of regions classified into similar clusters by SOM were used as input variables. Findings The clustering results showed that the region of the same cluster was geographically close, and it was possible to confirm the characteristics of being classified as the same cluster even if there was a price level and a similar industry group. As a result of predicting real estate prices in 1, 2, and 3 months, LSTM showed better predictive performance than SVR, and LSTM showed better predictive performance in long-term forecasting 3 months later than in 1-month short-term forecasting.

• Structural Engineering and Mechanics
• /
• v.78 no.3
• /
• pp.351-368
• /
• 2021

This paper, by applying a reliability-based framework, develops seismic vulnerability macrozonation maps for Tehran, the capital and one of the most earthquake-vulnerable city of Iran. Seismic performance assessment of 3-, 4- and 5-story steel moment resisting frames (SMRFs), designed according to ASCE/SEI 41-17 and Iranian Code of Practice for Seismic Resistant Design of Buildings (2800 Standard), is investigated in terms of overall maximum inter-story drift ratio (MIDR) and unit repair cost ratio which is hereafter known as "damage ratio". To this end, Tehran city is first meshed into a network of 66 points to numerically locate low- to mid-rise SMRFs. Active faults around Tehran are next modeled explicitly. Two different combination of faults, based on available seismological data, are then developed to explore the impact of choosing a proper seismic scenario. In addition, soil effect is exclusively addressed. After building analytical models, reliability methods in combination with structure-specific probabilistic models are applied to predict demand and damage ratio of structures in a cost-effective paradigm. Due to capability of proposed methodology incorporating both aleatory and epistemic uncertainties explicitly, this framework which is centered on the regional demand and damage ratio estimation via structure-specific characteristics can efficiently pave the way for decision makers to find the most vulnerable area in a regional scale. This technical basis can also be adapted to any other structures which the demand and/or damage ratio prediction models are developed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.2
• /
• pp.69-78
• /
• 1999

In this paper, a neural network approach to forecast Korean regional precipitation is presented. We first analyze the characteristics of the conventional models for time series prediction, and then propose a new model and its learning method for the precipitation forecast. The proposed model is a layered network in which the outputs of a layer are buffered within a given period time and then fed fully connected to the upper layer. This study adopted the dual connections between two layers for the model. The network behavior and learning algorithm for the model are also described. The dual connection structure plays the role of the bias of the ordinary Multi-Layer Perceptron(MLP), and reflects the relationships among the features effectively. From these advantageous features, the model provides the learning efficiency in comparison with the FIR network, which is the most popular model for time series prediction. We have applied the model to the monthly and seasonal forecast of precipitation. The precipitation data and SST(Sea Surface Temperature) data for several decades are used as the learning pattern for the neural network predictor. The experimental results have shown the validity of the proposed model.

• Journal of Korean Society of Forest Science
• /
• v.102 no.4
• /
• pp.467-476
• /
• 2013

Site index information given from forest site map only exist in the sampled locations. In this study, site index for unsampled locations were estimated using kriging interpolation method which can interpolate values between point samples to generate a continuous surface. Site index of Pinus densiplora in Danyang area were calculated using Chapman-Richards model by plot unit. Then site index for unsampled locations were interpolated by theoretical variogram models and ordinary kriging. Also in order to assess parameter selection, cross-validation was performed by calculating mean error (ME), average standard error (ASE) and root mean square error (RMSE). In result, gaussian model was excluded because of the biggest relative nugget (37.40%). Then spherical model (16.80%) and exponential model (8.77%) were selected. Site index estimates of Pinus densiplora throughout the entire area in Danyang showed 4.39~19.53 based on exponential model, and 4.54~19.23 based on spherical model. By cross-validation, RMSE had almost no difference. But ME and ASE from spherical model were slightly lower than exponential model. Therefore site index prediction map from spherical model were finally selected. Average site index from site prediction map was 10.78. It can be expected that regional variance can be considered by site index prediction map in order to estimate forest biomass which has big spatial variance and eventually it is helpful to improve an accuracy of forest carbon estimation.

• Journal of the Korean association of regional geographers
• /
• v.19 no.2
• /
• pp.352-361
• /
• 2013

This paper aims to analyze the root mean square errors of MODIS LST data and inland water temperature measurement data in order to use MODIS LST data as an input of numerical weather prediction model. MODIS LST data from July 2011 to June 2012 were compared to water temperature measurement data in the automated water quality measurement network. MODIS data have two composites: day-time and night-time. Monthly errors of day-time and night-time LST range $2{\sim}8^{\circ}C$ and $3{\sim}12^{\circ}C$, respectively. Temporally, monthly errors of day-time LST are less in fall and those of night-time LST are less in summer. Spatially, on the four major rivers including the Han, Nakdong, Geum, and Yeongsan rivers, the errors of Yeongsan river were the smallest, which location is the south-most among them. In this study, the errors of MODIS LST as an input of numerical weather prediction model were analyzed and the results can be used as an error level of MODIS LST data for inaccessible areas such as North Korea.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.170-177
• /
• 2017

The price of land in Jeju is reaching a new high every day and this phenomenon not only causes real difficulties for the purchase of real estate by local residents, but also results in psychological deprivation. Therefore, this study analyzes the factors causing the increase of the land price in Jeju, in order to examine the measures required to stabilize the land price which is continuously rising. As a result of this study, we developed a land price prediction model including seven variables, including the 'inflation rate', 'interest rate', and 'population'. According to the model, land prices in Jeju are expected to rise steadily, and it is predicted that in 2020 the price will increase to 170% of that in 2015 and will triple by 2025. Based on the results of this study, this study suggested policy alternatives, such as 'Establishing a tourism policy for managing the number of tourists' and 'increasing the approval standards for development activities'. The two policies proposed in this study can be implemented as a regional initiative, which may be less effective than the changes in the national system, but it is meaningful that the efforts to stabilize the land price will continue at the regional level.

• Journal of Korea Water Resources Association
• /
• v.45 no.7
• /
• pp.631-641
• /
• 2012

In this study, satellite data (MTSAT-1R), a numerical weather prediction model, RDAPS (Regional Data Assimilation and Prediction System) output, ground weather station data, and artificial neural networks were used to improve the accuracy of summer rainfall forecasts. The developed model was applied to the Seoul station to forecast the rainfall at 3, 6, 9, and 12-hour lead times. Also to reflect the different weather conditions during the summer season which is related to the frontal precipitation and the cyclonic precipitation such as Jangma and Typhoon, the neural network models were formed for two different periods of June-July and August-September respectively. The rainfall forecast model was trained during the summer season of 2006 and 2008 and was verified for that of 2009 based on the data availability. The results demonstrated that the model allows us to get the improved rainfall forecasts until lead time of 6 hour, but there is still a large room to improve the rainfall forecast skill.