• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.215-231
• /
• 2017

The US presidential primaries take place sequentially in different places with a time lag. However, they have not attracted as much attention in terms of modelling as the US presidential election has. This study applied several autologistic models to find the relation between the outcome of the primary election for a Democrat candidate with socioeconomic attributes in consideration of spatial and temporal dependence. According to the result applied to the 2016 election data at the county level, Hillary Clinton was supported by people in counties with high population rates of old age, Black, female and Hispanic. In addition, spatial dependence was observed, representing that people were likely to support the same candidate who was supported from neighboring counties. Positive auto-correlation was also observed in the time-series of the election outcome. Among several autologistic models of this study, the model specifying the effect of Super Tuesday had the best fit.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1004-1010
• /
• 2021

Ship-floating object accidents can lead not only to a delay in ship's operations, but also to large scale casualties. Hence, preventive measures are required to avoid them. This study analyzed the spatiotemporal aspects of such collisions based on the data on ship-floating object accidents in sea areas in the last five years, including the collisions in South Korea's territorial seas and exclusive economic zones. We also provide basic data for related research fields. To understand the distribution of the relative density of accidents involving floating objects, the sea area under analysis was visualized as a grid and a two-dimensional histogram was generated. A multinomial logistic regression model was used to analyze the effect of variables such as time of day and season on the collisions. The spatial analysis revealed that the collision density was highest for the areas extending from Geoje Island to Tongyeong, including Jinhae Bay, and that it was high near Jeongok Port in the West Sea and the northern part of Jeju Island. The temporal analysis revealed that the collisions occurred most frequently during the day (71.4%) and in autumn. Furthermore, the likelihood of collision with floating objects was much higher for professional fishing vessels, leisure vessels, and recreational fishing vessels than for cargo vessels during the day and in autumn. The results of this analysis can be used as primary data for the arrangement of Coast Guard vessels, rigid enforcement of regulations, removal of floating objects, and preparation of countermeasures involving preliminary removal of floating objects to prevent accidents by time and season.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.1
• /
• pp.1-12
• /
• 2014

Crown fire, the main propagation type of large forest fire, has caused extreme damage with the fast spread rate and the high flame intensity. In this paper, we developed the probability equation to predict the crown fires using the spatial features of topography, fuel and weather in damaged area by crown fire. Eighteen variables were collected and then classified by burn severity utilizing geographic information system and remote sensing. Crown fire ratio and logistic regression model were used to select related variables and to estimate the weights for the classes of each variables. As a results, elevation, forest type, elevation relief ratio, folded aspect, plan curvature and solar insolation were related to the crown fire propagation. The crown fire propagation probability equation may can be applied to the priority setting of fuel treatment and suppression resources allocation for forest fire.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.99-112
• /
• 2021

This study was performed to predict spatial change of future forestland area in South Korea at regional level for supporting forest-related plans established by local governments. In the study, land use was classified to three types which are forestland, agricultural land, and urban and other lands. A logistic regression model was developed using transitional interaction between each land use type and topographical factors, land use restriction factors, socioeconomic indices, and development infrastructures. In this model, change probability from a target land use type to other land use types was estimated using raster dataset(30m×30m) for each variable. With priority order map based on the probability of land use change, the total annual amount of land use change was allocated to the cells in the order of the highest transition potential for the spatial analysis. In results, it was found that slope degree and slope standard value by the local government were the main factors affecting the probability of change from forestland to urban and other land. Also, forestland was more likely to change to urban and other land in the conditions of a more gentle slope, lower slope criterion allowed to developed, and higher land price and population density. Consequently, it was predicted that forestland area would decrease by 2027 due to the change from forestland to urban and others, especially in metropolitan and major cities, and that forestland area would increase between 2028 and 2050 in the most local provincial cities except Seoul, Gyeonggi-do, and Jeju Island due to locality extinction with decline in population. Thus, local government is required to set an adequate forestland use criterion for balanced development, reasonable use and conservation, and to establish the regional forest strategies and policies considering the future land use change trends.

• Journal of Korean Society of Transportation
• /
• v.35 no.1
• /
• pp.11-24
• /
• 2017

Although many efforts to stop speeding or inappropriate speed, it failed to reduce the number of speeding-related crashes. Therefore, it is important to analyze the characteristics of speeding offenders and the cause of speeding at hot spots. In this study, we investigate the level of severity in speeding by the characteristics of speeding offenders using the Ordered Logistics Regression Models(OLRM). For the analysis, we use the speeding data collected by 39 traffic enforcement cameras in city of Cheongju and other related data including the speeding ticket history of drivers during the most recent 3 years, their demographic characteristics, their own vehicles, and road environment factors. The major results of this study are as follows. Firstly, commercial fleet drivers are more likely to repeat the conviction of high-range speeding with more than 30km/h over speed limits than other drivers. Secondly, mid-range speeding are observed as 21,462 frequency which is 76.7% of total speeding frequency and occurred mostly at suburban and rural area. It concludes that contributory factors affecting the severity of speeding at signalized intersection are drivers' speeding offence history, posted speed limits, time of day, gender of driver, and location of the intersection as show by the OLRM developed in this study(McFadden R-square : 0.296).

• Journal of Korean Society of Transportation
• /
• v.32 no.5
• /
• pp.544-553
• /
• 2014

Activity-based models analyze individuals' various daily activities that are identified as a decision-making unit for transportation planning. In other words, it is the model that determines the types of activities according to the social, economic and situational characteristics of the groups with the same activity patterns and predicts individuals' activity time, distance, spatial movement and transportation mode. The activity-based model is a method of estimating more efficient and realistic demand in transportation forecasting because traffic is regarded as a complex decision-making process that an individual and other people participate in. In this paper, we grasp the factors affecting choice behavior of activity pattern and analyze choice behavior of activity pattern based on multi-dimensional characteristic of each person. First, we classify activity types of reviewing the trip chain and activity purpose. Next, we identified preferable activity types using complicated characteristics of main agent of activity. We concluded that choice behavior of activity pattern is dependent on complex characteristics of each agent, and further multi-dimensional characteristics of each person are affected over the whole decision process of activity schedule.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1089-1098
• /
• 2020

In this study, we propose a method to detect red tide Cochlodinium Polykrikoide using by machine learning and geostationary marine satellite images. To learn the machine learning model, GOCI Level 2 data were used, and the red tide location data of the National Fisheries Research and Development Institute was used. The machine learning model used logistic regression model, decision tree model, and random forest model. As a result of the performance evaluation, compared to the traditional GOCI image-based red tide detection algorithm without machine learning (Son et al., 2012) (75%), it was confirmed that the accuracy was improved by about 13~22%p (88~98%). In addition, as a result of comparing and analyzing the detection performance between machine learning models, the random forest model (98%) showed the highest detection accuracy.It is believed that this machine learning-based red tide detection algorithm can be used to detect red tide early in the future and track and monitor its movement and spread.

• Journal of Korea Water Resources Association
• /
• v.43 no.12
• /
• pp.1083-1091
• /
• 2010

Distributed hydrologic models typically require spatial estimates of precipitation interpolated from sparsely located observational points to the specific grid points. However, widely used estimation schemes fail to describe the realistic variability of daily precipitation field. We compare and contrast the performance of statistical methods for the spatial estimation of precipitation in two hydrologically different basins, and propose a two-step process for effective daily precipitation estimation. The methods assessed are: (1) Inverse Distance Weighted Average (IDW); (2) Multiple Linear Regression (MLR); (3) Climatological MLR; and (4) Locally Weighted Polynomial Regression (LWP). In the suggested simple two-step estimation process, precipitation occurrence is first generated via a logistic regression model before applying IDW scheme (one of the local scheme) to estimate the amount of precipitation separately on wet days. As the results, the suggested method shows the better performance of daily rainfall interpolation which has spatial differences compared with conventional methods. And this technique can be used for streamflow forecasting and downscaling of atmospheric circulation model effectively.

• Journal of Korea Water Resources Association
• /
• v.53 no.2
• /
• pp.121-129
• /
• 2020

The increase of impervious surface and development along the river due to urbanization not only causes an increase in the number of associated flood risk factors but also exacerbates flood damage, leading to difficulties in flood management. Flood control measures should be prioritized based on various geographical information in urban areas. In this study, a probabilistic flood hazard assessment was applied to flood-prone areas near an urban river. Flood hazard maps were alternatively considered and used to describe the expected inundation areas for a given set of predictors such as elevation, slope, runoff curve number, and distance to river. This study proposes a Bayesian logistic regression-based flood risk model that aims to provide a probabilistic risk metric such as population-at-risk (PAR). Finally, the logistic regression model demonstrates the probabilistic flood hazard maps for the entire area.

• The Korean Journal of Applied Statistics
• /
• v.26 no.4
• /
• pp.623-634
• /
• 2013

In this study, we provide empirical evidence of whether a spatial correlation among mode choices at the TAZ(Traffic Analysis Zone) level exists based on transit smart card data observed in Seoul, Korea. The results show that the areas with a higher probability that passengers choose to take a bus are clustered and that those regions have fewer metro stations than bus stations. We also found that the spatial correlation turned out to be statistically meaningful and provided an opportunity for the potential use of the spatial correlation in modeling mode choices. A reliable spatial interaction would constitute valuable information for transportation agencies in terms of their route planning and scheduling based on the transit smart card data.