• Journal of Information Technology Services
• /
• v.21 no.3
• /
• pp.63-72
• /
• 2022

The extinction crisis of local cities, caused by a population density increase phenomenon in capital regions, directly causes the increase of vacant houses in local cities. According to population and housing census, Gunsan-si has continuously shown increasing trend of vacant houses during 2015 to 2019. In particular, since Gunsan-si is the city which suffers from doughnut effect and industrial decline, problems regrading to vacant house seems to exacerbate. This study aims to provide a foundation of a system which can predict and deal with the building that has high risk of becoming vacant house through implementing a data driven vacant house prediction machine learning model. Methodologically, this study analyzes three types of machine learning model by differing the data components. First model is trained based on building register, individual declared land value, house price and socioeconomic data and second model is trained with the same data as first model but with additional POI(Point of Interest) data. Finally, third model is trained with same data as the second model but with excluding water usage and electricity usage data. As a result, second model shows the best performance based on F1-score. Random Forest, Gradient Boosting Machine, XGBoost and LightGBM which are tree ensemble series, show the best performance as a whole. Additionally, the complexity of the model can be reduced through eliminating independent variables that have correlation coefficient between the variables and vacant house status lower than the 0.1 based on absolute value. Finally, this study suggests XGBoost and LightGBM based machine learning model, which can handle missing values, as final vacant house prediction model.

• Land and Housing Review
• /
• v.14 no.2
• /
• pp.73-82
• /
• 2023

This study empirically analyzes the policy demand for population inflow in Hongcheon-gun, a region that has experienced population decline over the past decade. The results of this study based on the multinominal logit model provide the policy implications as follows. First, due to the differing factors influencing the demand for population inflow policies among the young and the elderly, local governments should clearly define the policy targets for population inflow. Second, in the context of policy demand for population inflow through corporate attraction, we identify statistically significant and positive effects of the length of residence for both young and old people, and the level of formal education for the elderly. These results emphasize the importance of formulating population inflow policies distinctively targeted for the young and the elderly generations, respectively, thereby increasing population inflow in the population reduction area.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.131-136
• /
• 2023

Local youth outmigration is increasingly growing. Various studies are being conducted to identify the factors contributing to this problem, but there is a lack of research analyzing each region individually. Therefore, this study aims to analyze the factors influencing youth outmigration in Busan and predict the risk levels of youth population outflow using machine learning techniques. By utilizing district-level data collected from the KOSIS, we divided the population into three groups based on age (the early 20s, late 20s, and early 30s) and employed Decision Tree and Random Forest algorithms to classify and predict the risk levels of youth population outmigration. The results indicate that the predictive model for youth outmigration risk levels achieves the highest accuracies of 0.93, 0.75, and 0.63 for each age group, respectively.

• Journal of Information Technology Applications and Management
• /
• v.30 no.1
• /
• pp.33-52
• /
• 2023

This study observes the difference in the actual regional ripple effect of the decrease in admission resources due to the decrease in school age population, which has been weak in empirical studies, and how much the decrease in competition rate by department nationwide provides a significant shock to the decrease in enrollment rate in the population unit. An empirical quantitative analysis was attempted. As a result of applying the panel-tobit regression model, a clear gap was confirmed in the decrease in the registration rate due to the decrease in the competition rate both nationally and in the provinces, and in particular, a highly significant relationship was derived with the decrease in the recruitment rate. In particular, the sensitivity of the risk of unrecruitment due to a decrease in competition rate was the highest in the Jeolla region (0.499), followed by the Gangwon region (0.475) and the Gyeongsang region (0.471), and the metropolitan region (0.158) was confirmed to be the most stable. This suggests that the gap in insufficient funding has gradually widened by region over the past 10 years, and that the shock wave becomes more pronounced in the provinces farther away from the metropolitan area. Based on this study, if we deviate from the standardized application of university development policies for the metropolitan area and regional universities, and present a customized higher education strategy for each region, it will be an opportunity to prevent local extinction due to a decrease in the school-age population and achieve coexistence with higher education institutions and regions at the same time.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.79-84
• /
• 2010

Matching spots between two sets of 2-dimensional electrophoresis can make it possible to find out the generation, extinction and change of proteins. Generally protein spots are separated by 2-dimensional electrophoresis. This process makes the position of the same protein spot a little different according to the status of the tissue or the experimental environment. Matching the spots shows that the relation of spots is non-uniform and non-linear transformation. However we can also find that the local relation preserves the topology. This study proposes a matching method motivated by the preservation of the topology. To compare the similarity of the topology, we compared the distance and the angle between neighbour spots. Experimental result shows that the proposed method is effective.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.6
• /
• pp.1530-1541
• /
• 2013

The coexistence and extinction of species are important concepts for biological systems and can be distinguished by an investigation of stability. When determining local stability of nonlinear systems, Lyapunov indirect method based on the Jacobian linearization has been widely employed due to its simplicity. Despite such popularity, it is not applicable to singular systems whose Jacobian has at least one eigenvalue that is equal to zero. In such singular cases, an appropriate Lyapunov function should be sought to determine the stability of systems, which is rather difficult and quite involved. In this paper, we seek for a simple criterion to determine stability of the equilibrium that is located at the boundary of the positive orthant, when one of eigenvalues of the Jacobian is zero. The goal of the paper is to present a generalized condition for the equilibrium to attract all trajectories that starting from initial condition in the positive orthant and near the equilibrium. Unlike the Lyapunov direct method, the proposed method requires just a simple algebraic computation for checking the stability of the critical point. Our approach is applied to various biological systems to show the effectiveness of the proposed method.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.1
• /
• pp.80.2-80.2
• /
• 2012

We firstly present the unified Far-UV continuum map of the Taurus-Auriga-Perseus (TPA) complex, one of the largest local associations of dark cloud located in (l, b)=([152,180], [-28, 0]), by merging both FIMS and GALEX. The FUV continuum map shows that dust extinction correlate well with the FUV around the complex. It says strong absorption in the dense Taurus cloud and Auriga cloud. Although the column density of Perseus and California cloud is similar to Taurus' and Auriga's, Perseus and California cloud do not show strong absorption in FUV because they are more distant than Taurus and Auriga cloud. We also present the dust scattering simulation based on Monte Carlo Radiative Transfer technique. Through the result of Monte-Carlo dust scattering simulation and comparing the result with FIMS-GALEX unified map we gain deeper understanding related to the spatial dust distribution of TPA region. As a preliminary result of the simulation we present the most probable front face, thickness, albedo, and asymmetry factor in this region, respectively. Through this work we can show a certain inclination of the spatial dust distribution. During this study we have developed the FUV dust scattering simulation code using Monte-Carlo method. We expect that it will be generally used to simulate dust scattering in the Galaxy.

• Journal of The Korean Astronomical Society
• /
• v.22 no.1
• /
• pp.63-79
• /
• 1989

Current estimates, based on the same star-count analysis, of the distance to the globule Bamard 361 range from 300 pc to 650 pc. All the problems associated with the estimates have been fully rectified in this study, and a modification has been made to the classical Wolf diagram to improve the accuracy in the distance determination. A reference field was carefully selected close to the globule but well outside the globule boundary, and star counts for this field were performed on the blue POSS plate in order to set up the reference magnitude sequence appropriate to the general area of B 361. From the reference sequence, the stellar density function has been derived specifically for the direction toward the globule. Correction was made for the general interstellar extinction, and the luminosity function with the Wielen's dip was adopted. The resulting density function clearly reveals the existence of the local Cygnus-Orion arm in the direction of B 361 at about 700 pc away from the Sun. Analysis of the star-count data for the program field locates the globule at distance $600{\pm}50$ pc ; thus, the globule is an object located in the Cygnus-Orion arm, residing somewhat toward its leading edge.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.71.1-71.1
• /
• 2010

We present the FUV continuum map of The Taurus-Auriga-Perseus complex, which is one of the largest local association of dark clouds. The map is well consistent with the dust extinction and the CO emission map of the T-P-A region. The region is divided into 3 sub-regions by diffuse FUV intensities and the spectra of each region imply that the radiation field due to the Per OB2-association can be a main source of the H2 fluorescent emission of the nearby cloud region. We used the PDR H2 model, named CLOUD, developed by van Dishoeck &Black for the sake of comparing our results to the H2 model.

• Journal of Crop Science and Biotechnology
• /
• v.10 no.3
• /
• pp.141-146
• /
• 2007

The roots of Aristolochia elegans Mast.(Aristolochiaceae) are widely used in Mexican traditional medicine as a remedy for scorpion venom. Current experimental evidence supports its purported antidote properties. However, collection from the wilderness has lead to local extinction of natural populations. In order to contribute to species preservation, cultivation, and standardization of morphological and pharmacological properties, a micropropagation method was developed. This includes in-vitro germination of seeds to produce aseptic plantlets, induction of multiple budding, and acclimatization. The treatment with benzylamino purine(10 ${\mu}M$) induced the highest number of buds(3.1 on average) in both types of explants. On the other hand, indolebutyric acid(1.5 ${\mu}M$) caused the highest root index(11.8) per explant. One hundred percent of the micropropagated plantlets developed vigorously after the acclimatization process.