• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1156-1170
• /
• 2019

In recent years, the problem of data drifted of the smart grid due to manual operation has been widely studied by researchers in the related domain areas. It has become an important research topic to effectively and reliably find the reasonable data needed in the Supervisory Control and Data Acquisition (SCADA) system has become an important research topic. This paper analyzes the data composition of the smart grid, and explains the power model in two smart grid applications, followed by an analysis on the application of each parameter in density-based spatial clustering of applications with noise (DBSCAN) algorithm. Then a comparison is carried out for the processing effects of the boxplot method, probability weight analysis method and DBSCAN clustering algorithm on the big data driven power grid. According to the comparison results, the performance of the DBSCAN algorithm outperforming other methods in processing effect. The experimental verification shows that the DBSCAN clustering algorithm can effectively screen the power grid data, thereby significantly improving the accuracy and reliability of the calculation result of the main grid's theoretical line loss.

• Journal of the Economic Geographical Society of Korea
• /
• v.17 no.2
• /
• pp.385-401
• /
• 2014

This research analyses spatial and temporal characteristics of the academic performances of high school students by using all 2,065,166 SAT scores for 3 years. The spatial inequalities in Seoul are analysed by DBMS and GIS. Based on three-year raw data of Korean SAT scores, the spatial and temporal characteristics of academic performances are scrutinized: 868,029 SAT scores cases of 2000 academic year on Novemver 17, 1999, 609,258 cases in 2005 academic year on November 17, 2004 and 587,890 cases in 2009 on November 13. The result shows that there are significant spatial disparities of the level of academic performance in Seoul by Gu level, also indicating that the disparities are getting wider over the course of time. The widening disparities by Gu level means that educational spatial inequality is intensified in spite of the increasing overall trend of academic performance of Seoul. It is also notable that disparities between regions are distinctive, while those in regions are not significant and sustained constant as time flows.

• Journal of the Economic Geographical Society of Korea
• /
• v.18 no.4
• /
• pp.539-555
• /
• 2015

This study proposes the methodology for measuring the time-distance accessibility on the Seoul bus system based on the T-card transaction databases and analyzes the results. T-card transaction databases contain the time/space information of each passenger's locations and times of the departure, transfers, and destination. We introduce the bus network graph and develop the algorithms for time-distance accessibility measurement. We account the average speed based on each passenger's get-in and getoff information in the T-card data as well as the average transfer time from the trip chain transactions. Employing the modified Floyd APSP algorithm, the shortest time distance between each pair of bus stops has been accounted. The graph-theoretic nodal accessibility has been given by the sum of the inverse time distance to all other nodes on the network. The results and spatial patterns are analyzed. This study is the first attempt to measure the time-distance accessibility for such a large transport network as the Seoul bus system consists of 34,934 bus stops on the 600 bus routes, and each bus route can have different properties in terms of speed limit, number of lanes, and traffic signal systems, and thus has great significance in the accessibility measurement studies.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.6
• /
• pp.1-9
• /
• 2016

Place names of road sign mean various place names being used on road signs for path guidance of drivers such as administrative district, facility, road, etc. It is very important that not only the choice method of place names for connectivity of road signs but standard establishment of spatial impact zone according to place names. However this standard are not established currently, so it is difficult to fix the spatial range for changing place names around the main facility according to the new construction or relocation of main facility in urban region. Considering the use of big data, one of the Government 3.0, we need to utilize actively the road sign management system database. This paper suggested a methodology for standard establishment of spatial impact zone according to place names of road sign in urban regions based on the road sign management system database. To perform a case study, we selected a major facility ("City Hall") which is the most frequently used the place name of road signs and presented standard of spatial impact zone by urban size in 84 cities.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.2 s.32
• /
• pp.29-37
• /
• 2005

The compensation data for submerged land have been filed in the form of document or managed with spread sheet like Excell up to now. In the case of dam or highway construction, huge compensation data for the submerged or included land have been managed inefficiently by the administrative manpower. Moreover, where and how to keep the enormous data becomes big problems. In response to the requirements, an submerged land compensation management system based on the location and property information of parcels was developed. The compensation management system has many functions including site searching for compensation, compensation money computing, and compensation data managing. It is expected that the submerged land compensation management system creates various information effects.

• Spatial Information Research
• /
• v.19 no.3
• /
• pp.1-9
• /
• 2011

The vulnerability of ocean should be assessed to establish the climate change adaptation policy in field of the ocean, which has big effect on human and natural system. In this study, the criteria for assessing vulnerability of ocean to climate change were employed in terms of sensitivity, adaptative capacity and exposure. And suitable indicators for the criteria were selected and spatial data set for the indicators was prepared. In the ocean sector, the data for indicators were divided into two types, such as the inland and ocean data. The inland data were extrapolated and integrated to the coordinate of ocean data for the vulnerability assessment to climate change. As a result, the spatially diverse distribution of vulnerability on the ocean could be derived from the integration of two types of data. The results showed that southwestern ocean is much more sensitive than west and east ocean. Also southwestern ocean of exposure ratio of change is higher than the other part of ocean. On the other hand the adaptative capacity found that the highest in east ocean. The vulnerability assessment result showed southwestern ocean is more vulnerable than the other part of ocean.

• Journal of the Economic Geographical Society of Korea
• /
• v.17 no.1
• /
• pp.98-113
• /
• 2014

The purpose of this study is to investigate the changes in the accessibility of the Metropolitan Seoul Transit systems since 2000, in which many new subway lines have been constructed as well as other urban transit lines have been connected to the systems. We suggest an accessibility measure model for Un-fixed Transportation Networks. In order to measure the nodal accessibility based on the mobility, we apply path-distance, physical-distance, and time-distance as the distance impedance measurement. Specifically, we develop time-distance algorithms to measure the time-distance between each pairs of transit stations based on the T-card transaction databases. We apply the model to the Metropolitan Seoul Transit systems in two time points(2005 and 2011). We examine the results in terms of three distance accessibility measures. Time-distance accessibility explains better the urban land use patterns in the Metropolitan Seoul area than the other two. We visualize the spatial patterns of time-distance accessibility by applying GIS, and analyze the spatial structures of accessibility in the Metrropolitan Seoul area between two time points.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5095-5111
• /
• 2019

A multi-rotor Unmanned Aerial Vehicle (UAV) system is developed to solve the manhole cover detection problem for the infrastructure maintenance in the suburbs of big city. The visible light sensor is employed to collect the ground image data and a series of image processing and machine learning methods are used to detect the manhole cover. First, the image enhancement technique is employed to improve the imaging effect of visible light camera. An imaging environment perception method is used to increase the computation robustness: the blind Image Quality Evaluation Metrics (IQEMs) are used to percept the imaging environment and select the images which have a high imaging definition for the following computation. Because of its excellent processing effect the adaptive Multiple Scale Retinex (MSR) is used to enhance the imaging quality. Second, the Single Shot multi-box Detector (SSD) method is utilized to identify the manhole cover for its stable processing effect. Third, the spatial coordinate of manhole cover is also estimated from the ground image. The practical applications have verified the outdoor environment adaptability of proposed algorithm and the target detection correctness of proposed system. The detection accuracy can reach 99% and the positioning accuracy is about 0.7 meters.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.2 s.8
• /
• pp.91-98
• /
• 1996

Transportation impact assessment which can take precaution for the traffic problem to control a plan on to expand traffic facilities through these results analyzed with the business for making a big problem of traffic is a very important course on the traffic management system as well as the traffic plan and it is necessary to collect and to edit and to analyze a great deal of data fully in object zone. So it is worth while to treat the collected data on to computer. Therefore Geographic Information System will give a remarkable result to Traffic Influence Evaluation everywhere. GIS not only can join the graphic or attribute data correctly and fast, but can achieve it prominent function for intention decision means. Then total system for Landuse of surrounding district, development-plan state, traffic-facility state, traffic-development public plan state and traffic demand is animated on Traffic Influence Evolution.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.819-834
• /
• 2022

Artificial Intelligence (AI) techniques have been effectively used for image classification, object detection, and image segmentation. Along with the recent advancement of computing power, deep learning models can build deeper and thicker networks and achieve better performance by creating more appropriate feature maps based on effective activation functions and optimizer algorithms. This review paper examined technical and academic trends of Convolutional Neural Network (CNN) and Transformer models that are emerging techniques in remote sensing and suggested their utilization strategies and development directions. A timely supply of satellite images and real-time processing for deep learning to cope with disaster monitoring will be required for future work. In addition, a big data platform dedicated to satellite images should be developed and integrated with drone and Closed-circuit Television (CCTV) images.