• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.1
• /
• pp.76-86
• /
• 2012

The purpose of this study is to investigate the environmental equity of the accessibility to public transportation services in the city of Daegu. The 2005 census data as well as bus stop and subway station datasets were integrated for building the GIS database. Public transportation service areas were then identified by a coverage method. Mann Whitney U test was used for statistically comparing the socioeconomic characteristics over different levels of access to the public transportation services. Both Dong-gu, Suseong-gu, Dalseo-gu, and Buk-gu located outside of the city had worse accessibility than others while Jung-gu, Seo-gu, and Nam-gu had better accessibility than others. There appeared no environmental inequity pattern in terms of the percentages of men, women, and teenagers over the city of Daegu whereas there existed some environmental inequity pattern in terms of the percentages of people above the age of 65 and people below poverty line. This environmental inequity pattern would be caused by some factors. Firstly, the lower income class has tended to reside in the declined or blighted areas far away from public transportation facilities since this class can not afford to pay expensive rents and land prices around the main roads with higher accessibility. Many old people belonging to the lower income class also reside in the declined or blighted areas. Secondly, there has been no law to locate bus stops and subway stations considering residents' socioeconomic characteristics and the spatial distribution of public transportation facilities has been not managed systematically by the city government. This research would shed insight on building the public transportation policy to locate bus stops and subway stations and to select the routes of buses and subways considering the spatial distribution of residents' socioeconomic characteristics.

• Journal of Advanced Navigation Technology
• /
• v.22 no.2
• /
• pp.76-83
• /
• 2018

In order to prevent overusing the fishing gear and to reduce discarded fishing gear, there is a need for a technique that can efficiently transmit the information including the type and location of the fishing gear and the user's real name to the fishing boat and the control center using IoT-based communication. In order to do this, it is necessary to be able to confirm the position information of a plurality of buoys that can be identified by the base stations on the land. In this paper, in order to service the maritime IoT communication system, we calculate the link budget between the land base station and the targets on the sea to derive the service coverage. To design a marine IoT radio network for building a fishing gear monitoring system, we calculate link budget for wireless service optimization at sea for NB-IoT using 1.8 GHz frequency band and LoRa service using 900 MHz frequency band. In addition, the link budget between the land base station and buoy, the link budget between the land base station and fishing boat are calculated and the results are analyzed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.4
• /
• pp.89-101
• /
• 2017

Crime occurs differently based on not only place locations and building uses but also the characteristics of the people who use the place and the spatial structures of the buildings and locations. Therefore, if spatial big data, which contain spatial and regional properties, can be utilized, proper crime prevention measures can be enacted. Recently, with the advent of big data and the revolutionary intelligent information era, predictive policing has emerged as a new paradigm for police activities. Based on 7420 actual crime incidents occurring over three years in a typical provincial city, "J city," this study identified the areas in which crimes occurred and predicted risky areas. Spatial regression analysis was performed using spatial big data about only physical and environmental variables. Based on the results, using the street width, average number of building floors, building coverage ratio, the type of use of the first floor (Type II neighborhood living facility, commercial facility, pleasure use, or residential use), this study established a Crime Incident Prediction Model (CIPM) based on Bayesian probability theory. As a result, it was found that the model was suitable for crime prediction because the overlap analysis with the actual crime areas and the receiver operating characteristic curve (Roc curve), which evaluated the accuracy of the model, showed an area under the curve (AUC) value of 0.8. It was also found that a block where the commercial and entertainment facilities were concentrated, a block where the number of building floors is high, and a block where the commercial, entertainment, residential facilities are mixed are high-risk areas. This study provides a meaningful step forward to the development of a crime prediction model, unlike previous studies that explored the spatial distribution of crime and the factors influencing crime occurrence.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.2
• /
• pp.109-118
• /
• 2010

This study aims to propose practical strategies for the new urban ideal of regeneration. A book review highlights the emergence of new trends of urbanization in knowledge-information industrial society beyond the new town Ideal of the industrial society. The meaning of ‘landscape’ in landscape urbanism represents not the visual and decorative pictures, but the dynamic process in the context of changes and evolutions. Also, knowledge-information industrial society and landscape have a meaning in the same context of flow and process with changes of velocity. Finally, these key words convey a meaning with the new urban trends of urbanization in knowledge-information industrial society in the context of value-oriented characteristics of dynamics and process. Urban regeneration is emerging as the new urban ideal in the knowledge-information industrial society, beyond the new town ideal of industrial society. It is in the same context as landscape urbanism with respect to green infrastructure buildings and designs for the transformation of urban surfaces covered with concrete and asphalt into the ecological surface, and of the ecological surfaces into the cultural surface that could be communicated with human beings. This research revealed the six strategies for urban regeneration as follows. The First, the strategies for the transformation of urban surfaces into ecological surfaces, the second, the strategies for the transformation of ecological surfaces into cultural surfaces, the third, the introduction of mixed and convergence land use, the forth, the transformation of former sites(e.g. military and factory) into urban parks, the fifth, the introduction of waterfront park zones that have the function of ecological and park-oriented mixed land use and, the sixth, the building and design of green infrastructure in the residential and commercial complex in CBD. These strategies call for the reforms of development laws and regulations to restrict building coverage ratio, building heights, and the introduction of park-oriented mixed zoning regulations. Another method for implementating the above listed strategies was the introduction of a strategic planning system instead of the traditional master plan system. This system uses a value planning approach and brand making by imagery. It is able to construct the meaning of an image and its creativeness directly.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Korean Journal of Environment and Ecology
• /
• v.29 no.6
• /
• pp.850-857
• /
• 2015

This study was aimed to identify the characteristics of nest and breeding site conditions of Chinese Egret (Egretta europhotes) that breed in the uninhabited islets of the western coast of South Korea. It is expected that the information collected through this study can contribute to providing basic information required when building and managing artificial nests in their natural breeding habitats. Chinese Egrets make their nests in the shrub layers of Long Leaf Elaeagnus (Elaeagnus macrophylla), Arrow Bamboo (Pseudosasa japonica), and Baby Brier (Rosa multiflora). A total of 50 breeding nests of Chinese Egret were investigated in June and July 2013, with area-wise distribution as follows: Seomando (11 nests), Hwangseodo (14 nests), Mokdo (10 nests), and Napdaekiseom (15 nests). Vegetation coverage (cover, %), height from the ground to the top (height, cm), thickness from top to bottom of the nest (thickness, cm), reuse period, major axis (cm), minor axis (cm), and depth (cm) of each nest were measured. According to the results of the study on the nest characteristics of 4 breeding groups, the nests in Hwangseodo had the highest coverage, the nests in Mokdo were built in the highest places, the nests in Napdaekiseom showed the longest reuse period, and the nests in Mokdo had the greatest depth. The differences in height and reuse period were significant between Mokdo and Napdaekiseom. Moreover, there were significant differences in reuse period and depth between Seomando and Hwangseodo. There were significant differences in cover, minor axis, and depth between breeding groups that built nests on Arrow Bamboo (Mokdo and Napdaekiseom) and Baby Brier (Seomando and Hwangseodo). Nest characteristics of Chinese Egret were generally similar, while some variables showed different values for different breeding groups.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.1
• /
• pp.16-28
• /
• 2015

This study is suggested to enlarge the green area and to connect and improve the present green areas by deriving the lines of community greenway using living areas and community spaces close to the life of residence in Nam-gu. The purpose of this paper is to suggest the method of establishing greenway for the formation of community in which the residence can grow the community spirit and love their living space much more. Land-use status, green coverage ratio, and impermeability paving ratio are investigated. The community facilities are classified. The highest is educational facility, which is 7.7%, the green facility is 1.9% and the total area of community facilities which is 21.4%. The total area of Nam-gu is divided into 31 zones in total according to the administrative districts, the mail roads and reserved land of railroad and urban development. The total 20 lines of community greenway lines are chosen and the total length of lines is 18.2km. Finally, the characteristics of community greenway lines are analysed, the characteristics of community greenway lines are overall estimated according to the land-use, the street environment and the community facility. The classification system of community greenway is established on the basis on the function and purpose of greenway, the present status of land-use and the type of community facility. Based on the field investigation, the 6 greenway types are suggested considering the interconnection. The method of establishment of community greenway is suggested according to the principle of function and purpose, the principle of land-use and the principle of use of the facilities. Furthermore, the planting methods suitable to each greenway type are suggested in the building planting case of wall planting, roof planting, veranda planting, etc., and in the complex planting of parks, schools, roads, parking lots and other small areas.

• Korean Journal of Cognitive Science
• /
• v.26 no.4
• /
• pp.435-452
• /
• 2015

Recent researches on Entity Linking(EL) have attempted to disambiguate entities by using a knowledge base to handle the semantic relatedness and up-to-date information. However, EL for tweets using a knowledge base is still unsatisfactory, mainly because the tweet data are mostly composed of short and noisy contexts and real-time issues. The EL system the present work builds up links ambiguous entities to the corresponding entries in a given knowledge base via exploring the news articles and the user history. Using news articles, the system can overcome the problem of Wikipedia coverage (i.e., not handling real-time issues). In addition, given that users usually post tweets related to their particular interests, the current system referring to the user history robustly and effectively works with a small size of tweet data. In this paper, we propose an approach to building an EL system that links ambiguous entities to the corresponding entries in a given knowledge base through the news articles and the user history. We created a dataset of Korean tweets including ambiguous entities randomly selected from the extracted tweets over a seven-day period and evaluated the system using this dataset. We use accuracy index(number of correct answer given by system/number of data set) The experimental results show that our system achieves a accuracy of 67.7% and outperforms the EL methods that exclusively use a knowledge base.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.36 no.2
• /
• pp.24-31
• /
• 2008

Studies for demarcation of urban areas by ecological type have been developed, but the demarcation of urban areas by ecological perception is thus far dependent on artificial land use. Therefore, the purpose of this study is to find factors that account for the urban area ecosystems by surveying a variety of ecosystem factors. By land use type, the urban area of Gangdong District, Seoul was defined. Then ecological factors in each polygon were surveyed. Ecological factors are associated with energy use(building coverage ratio, floor area ratio and ground temperature), water circulation(biotope area factors and impermeable pave ratio) and biological diversity(bird appearance index and green area ratio). The correlation between each factor was analyzed. The results indicate that urban ground temperature is divided into three groups(high, middle and low) by the biotope area factor. The bird population is divided into two groups(abundant and scarce) by the green area ratio. Therefore, demarcating the urban areas by ecological type is applicable to the biotope area factor and green area ratio.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.3
• /
• pp.69-81
• /
• 2009

This study was intended to evaluate the objective landscape of rural region using an additive integration index method in the Seondong region of Gochang-gun, Jeollabuk-do, Korea. This study consisted of the following three steps. First, this study developed an additive integration index calculation model for landscape assessment based on indicators and weight to each space type in accordance with three landscape fields which were developed by the expert Delphi method. Second, this study used NDVI (Normalized Difference Vegetation Index) and permeable area rate, which were available from high resolution satellite image, to calculate the green naturality degree, area rate, and building coverage respectively. Third, this study has calculated the landscape assessment index of rural regions using an additive integration index method made of assessment data and weight for each indicator. This study has found the following results: 1) landscape level was very poor in all 6 types of space, marking grade five; 2) while the highest level of natural landscape and mixed landscape was grade two, that of artificial landscape was grade five; 3) based on objective landscape, grade five showed the highest frequency, and grade one, two, three, and four followed in that order.