• Journal of the Korean Operations Research and Management Science Society
• /
• 제40권4호
• /
• pp.83-105
• /
• 2015

Taxi, one of the passenger services, is an essential transportation system in our society. In spite of the importance of taxi service, deterioration of the service quality is continuously reported. In particular, taxi service failures due to traffic accidents have emerged as the most serious social problem which may incur a considerable amount of social costs. In this study, we focus on analyzing the causes of service quality deterioration-traffic accidents of both corporately owned and privately owned taxies in Seoul. The research objective is to find out the determinants of service quality deterioration of Taxi industry and to suggest policies for improving the taxi service in Seoul. We collected the archival data from KTSA (Korea Transportation Safety Authority) and ODP (Open Data Portal), which span from 2005 to 2014. Hierarchical regression analyses and a set of mediation tests are conducted. The root factors inducing traffic accidents of taxies are divided into competitive, and profitability factors. The statistical results indicate that the accident ratio per taxi is not only affected by competitive/profitability factors such as number of active taxi drivers, number of bus passengers, and taxi fare, but also mediated by the traffic violation ratio. To alleviate the current problems with taxi service in Seoul, we conclude that the number of taxies be reduced and the taxi fare be increased. Finally, we suggest several policies to improve the endemic taxi industry problems, over-supply and the low profitability by enhancing the linkage between service quality and profitability.

• Spatial Information Research
• /
• 제20권2호
• /
• pp.35-44
• /
• 2012

Recently, Web map service is actively accomplished in both private companies and public offices. As a platform, it exists variously from desktop to smartphone. The technology being used has a trend to develop continuously. Also, Web map system provides various open API for people who use geospatial service and data mashup. In this paper, RIA technology which is popularly used recently in web map service w ill be applied to introduce the functions different language map services are mostly using. Based on users' feeling about different web browser's speed, test and analysis have been accomplished. The result is that there are different characteristics according to different functions such as JavaScript, Silverlight, Flex. Actual test has been personally carried out on map service in Seoul GIS portal system. The comprehensive conclusion is that Silverlight has more outstanding function compared with other RIA techniques under the test environment.

• Journal of People, Plants, and Environment
• /
• 제24권5호
• /
• pp.519-527
• /
• 2021

Background and objective: This study was conducted to establish a Plant Hardiness Zone (PHZ) map, investigate the effect of global warming on changes in PHZ, and elucidate the difference in the distribution of evergreen trees between the central and southern region within hardiness Zone 7b in Korea. Methods: Mean annual extreme minimum temperature (EMT) and related temperature fluctuation data for 40 years (1981 to 2020) in each of the meteorological observation points were extracted from the Open MET Data Portal of the Korea Meteorological Administration. Using EMT data from 60 meteorological observation points, PHZs were classified according to temperature range in the USDA Plant Hardiness Zone Map. Changes in PHZs for each decade related to the effects of global warming were analyzed. Temperature fluctuation before and after the day of EMT were analyzed for 4 areas of Seoul, Suwon, Suncheon, and Jinju falling under Zone 7b. For statistical analysis, descriptive statistics and ANOVA were performed using the IBM SPSS 22 Statistics software package. Results: Plant hardiness zones in Korea ranged from 6a to 9b. Over four decades, changes to warmer PHZ occurred in 10 areas, especially in colder ones. Based on the analysis of daily temperature fluctuation, the duration of sub-zero temperatures was at least 2 days in Seoul and Suwon, while daily maximum temperatures were above zero in Suncheon and Jinju before and after EMT day. Conclusion: It was found that the duration of sub-zero temperatures in a given area is an important factor affecting the distribution of evergreen trees in PHZ 7b.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.274-283
• /
• 2022

Korea is facing a number difficulties arising from rising housing prices. As 'housing' takes the lion's share in personal assets, many difficulties are expected to arise from fluctuating housing prices. The purpose of this study is creating housing price prediction model to prevent such risks and induce reasonable real estate purchases. This study made many attempts for understanding real estate instability and creating appropriate housing price prediction model. This study predicted and validated housing prices by using the LSTM technique - a type of Artificial Intelligence deep learning technology. LSTM is a network in which cell state and hidden state are recursively calculated in a structure which added cell state, which is conveyor belt role, to the existing RNN's hidden state. The real sale prices of apartments in autonomous districts ranging from January 2006 to December 2019 were collected through the Ministry of Land, Infrastructure, and Transport's real sale price open system and basic apartment and commercial district information were collected through the Public Data Portal and the Seoul Metropolitan City Data. The collected real sale price data were scaled based on monthly average sale price and a total of 168 data were organized by preprocessing respective data based on address. In order to predict prices, the LSTM implementation process was conducted by setting training period as 29 months (April 2015 to August 2017), validation period as 13 months (September 2017 to September 2018), and test period as 13 months (December 2018 to December 2019) according to time series data set. As a result of this study for predicting 'prices', there have been the following results. Firstly, this study obtained 76 percent of prediction similarity. We tried to design a prediction model of real estate transaction price with the LSTM Model based on AI and Bigdata. The final prediction model was created by collecting time series data, which identified the fact that 76 percent model can be made. This validated that predicting rate of return through the LSTM method can gain reliability.

• Journal of the Korean Institute of Landscape Architecture
• /
• 제45권4호
• /
• pp.131-142
• /
• 2017

This study aims to create a Local Climate Zone(LCZ) map of Seoul by using World Urban Database and Access Portal Tools(WUDAPT) protocol, and to analyze the characteristics of the Seoul LCZs. For this purpose, training samples of 17 LCZ types were collected by using Landsat images and Google Earth. LCZ Classification and Filtering were performed by SAGA GIS. An ArcGIS was used to analyze the characteristics of each LCZ type. The characteristics of the LCZ types were analyzed by focusing on building surface fraction ratio, impervious surface fraction ratio, pervious surface fraction ratio, building stories and air temperature. The results show that one filtering was found to be most appropriate. While Yangcheongu and Yeongdeungpogu with the higher annual and maximum mean air temperature than other areas have the higher rate of LCZ 3(compact low-rise) and LCZ 4(open high-rise), Jongnogu, Eunpyeonggu, Nowongu and Gwanakgu with the lower value have the higher rate of LCZ A(Dence trees). The values of building surface fraction ratio, impervious surface fraction ratio and building stories of each LCZ were included in the range of WUDAPT for most LCZs. However, the values of pervious surface fraction ratio were out of the range, in particular, in the LCZs 4~6 and 9~10. This study shows the usability and applicability of the WUDAPT methodology and its climate zone classification used in many countries as a basic data for the landscape planning and policy to improve the thermal environment in urban areas.

• Journal of Digital Convergence
• /
• 제12권12호
• /
• pp.313-321
• /
• 2014

In current society, the digital era that makes enormous amount of data, and the diversified city, the smart space, which has characteristics of creating, collecting and representing data, is appeared. After 2012, in the social media environment called hyper-connected society with wide-spread smart phone, people started to get interested in public data and big data by generalized mobile device and SNS. At first, development of forming platform of data was focused, but now, many different idea from diverse area have been suggested about data analysis and usage to visualize the space intellectualization service. To focus on the visualization process to increase the usage of this public data for ordinary people more than specialized people, this research grasps the present condition of open data and public data service from the current public data portal and considers the applicability of them. As the result of research, the analysis and application of data to ordinary people decrease the use of paper documents, and this research will help to develop the application which is fast and accurate about individual behavior and demand to utilize public data service in intellectual space.

• Journal of Korean society of Dental Hygiene
• /
• 제24권1호
• /
• pp.9-16
• /
• 2024

Objectives: The demand for dental care is expected to increase as the population ages. This study aimed to predict the utilization of dental implant care following the expansion of national health insurance benefits for dental implants. Methods: Multiple linear regression analysis was performed on HIRA big data open portal data and DNN-based artificial intelligence models to forecast the utilization of dental care in relation to the national health insurance coverage for dental implants. Results: National health insurance coverage of dental implants was found to be associated with the number of patients using dental implant services and demonstrated a statistical significance. The dental implant services utilization increased with the increased dental implant health insurance benefits for the elderly population, increased mean by region, increased number of dental institutions by region, and increased health insurance coverage rate for dental implants. However, the dental implant services utilization decreased with the increased number of older people living alone and increased size of dental institutions. Conclusions: With the expansion of the national health insurance coverage for dental implants, it is predicted that the utilization of dental implant medical services will increase in the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• 제40권5호
• /
• pp.429-437
• /
• 2022

Recently, the demand for a QA (Question Answering) system for human-machine communication has increased. Among the QA systems, a closed domain QA system that can handle spatial-related questions is called GeoQA. In this study, a new type of graph database, LPG (Labeled Property Graph) was used to overcome the limitations of the RDF (Resource Description Framework) based database, which was mainly used in the GeoQA field. In addition, GraphQL (Graph Query Language), an API-type query language, is introduced to address the fact that the LPG query language is not standardized and the GeoQA system may depend on specific products. In this study, database was built so that answers could be retrieved when spatial-related questions were entered. Each data was obtained from the national spatial information portal and local data open service. The spatial relationships between each spatial objects were calculated in advance and stored in edge form. The user's questions were first converted to GraphQL through FOL (First Order Logic) format and delivered to the database through the GraphQL server. The LPG used in the experiment is Neo4j, the graph database that currently has the highest market share, and some of the built-in functions and QGIS were used for spatial calculations. As a result of building the system, it was confirmed that the user's question could be transformed, processed through the Apollo GraphQL server, and an appropriate answer could be obtained from the database.