• Journal of KIBIM
• /
• v.9 no.4
• /
• pp.75-83
• /
• 2019

Recent data development has made it possible to analyze each individual's daily commuting by using transportation card transaction. This research utilizes about 1 million observations from the subway line no.7 of Seoul metropolitan transportation data. By using such a massive dataset, the authors try to identify daily travel behavior of morning commute and its possible relationship between subway usage and socio-economic factors. There are 4 main types of users and their travel behavior, and top 15 stations with the most users for arrival and departure are selected. Accordingly, 15 stations have distinctive characteristics including population density and the number of businesses around stations. To identify this fact, the 4 most populated stations are selected and their socio-economic factors are examined. According to the analysis, the most departure stations are generally surrounded by hihgly populated residential areas, whereas the most arrival stations are stood within the job concentrated districts.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.784-792
• /
• 2018

In this study, we designed the area except the development market and the traditional market, where large scale shops were concentrated by realizing the real estate center of the alley commercial area. In addition, we have developed an area setting method for the alley area where reliability and rationality can be ensured by utilizing the actual data such as the business statistics, the survey data of the business, and the store business DB, which are managed by the local government or the state. The alley commercial areas were classified into five groups according to density. It is thought that users can distinguish the commercial areas from dense commercial areas to the commercial areas in order to utilize various commercial areas.

• Journal of Korean Society of Transportation
• /
• v.35 no.3
• /
• pp.220-233
• /
• 2017

Traffic volumes are fundamental data widely used in various traffic analysis, such as origin-and-destination establishment, total traveled kilometer distance calculation, congestion evaluation, and so on. The low number of links collecting the traffic-volume data in a large urban highway network has weakened the quality of the analyses in practice. This study proposes a method to estimate the traffic volume data on a highway link where no collection device is available by introducing a spatial statistic technique with (1) the traffic-volume data from TOPIS, and National Transport Information Center in the Ministry of Land, Infrastructure, and (2) the navigation data from private navigation. Two different component models were prepared for the interrupted and the uninterrupted flows respectively, due to their different traffic-flow characteristics: the piecewise constant function and the regression kriging. The comparison of the traffic volumes estimated by the proposed method against the ones counted in the field showed that the level of error includes 6.26% in MAPE and 5,410 in RMSE, and thus the prediction error is 20.3% in MAPE.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.80.1-80.1
• /
• 2011

It is well known that chromospheric features are fine structured, short lived, and dynamic. Spectrograph-based observation have obvious advantage of getting physical properties of solar chromosphere than filter-based one. We developed and installed Fast Imaging Solar Spectrograph (FISS) attached on New Solar Telescope in Big Bear Solar Observatory. FISS have capabilities to take data with high time, spatial and spectral resolution at two wavelengths(Ha $6563{\AA}$ and CaII $8542{\AA}$) simultaneously. After FISS installation, we observed various chromospheric features : active regions, quiet regions, filaments/prominences and so on. As one of chromospheric studies, we analyzed solar prominences and got physical parameters by using simple radiative transfer modeling. The ranges of temperature and non-thermal velocities are found to be 7500-13000K and 5-11km/s, respectively.

• The Bulletin of The Korean Astronomical Society
• /
• v.39 no.1
• /
• pp.71.2-71.2
• /
• 2014

For better understanding of the physics of pores, we have investigated horizontal and vertical motions of plasma in a pore obtained on 2013 August 24 by using high time and spatial resolution data from the Fast Imaging Solar Spectrograph (FISS) of the 1.6 meter New Solar Telescope (NST). We infer the LOS velocity by applying the bisector method to the wings of Ca II 8542 ${\AA}$ profile, and inspect oscillations of the intensity and the LOS velocity in the pore. In this presentation, we discuss the physical implications of our results in view of a connection between LOS and horizontal plasma flows in a concentrated magnetic flux.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.931-956
• /
• 2019

Documents contain information that can be used for various applications, such as question answering (QA) system, information retrieval (IR) system, and recommendation system. To use the information, it is necessary to develop a method of extracting such information from the documents written in a form of natural language. There are several kinds of the information (e.g., temporal information, spatial information, semantic role information), where different kinds of information will be extracted with different methods. In this paper, the existing studies about the methods of extracting the temporal information are reported and several related issues are discussed. The issues are about the task boundary of the temporal information extraction, the history of the annotation languages and shared tasks, the research issues, the applications using the temporal information, and evaluation metrics. Although the history of the tasks of temporal information extraction is not long, there have been many studies that tried various methods. This paper gives which approach is known to be the better way of extracting a particular part of the temporal information, and also provides a future research direction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.173-187
• /
• 2023

In an era of population decline, depopulated regions facing challenges in attracting inbound population migration must enhance urban vitality through the attraction of living populations. This study focuses on Busan, a city experiencing population decline, comparing the spatiotemporal distribution characteristics of registered residents and living populations in various administrative districts (Eup-Myeon-Dong) using mobile communication big data. Administrative districts are typified based on population change patterns, and regional characteristics are analyzed using indicators related to urban decline and vitality. Spatiotemporal distribution analysis reveals generally similar density patterns between registered residents and living populations; however, a distinctive feature is observed in the city center areas where the density of registered residents is low, while the density of living populations is high. Divergent trends in spatial patterns of change between registered residents and living populations show clusters of registered population decline in low-density areas and clusters of living population decline in high-density areas. Areas adjacent to declining living populations exhibit large clusters of population changes, indicating a spillover effect from high-density to neighboring areas. Typification results reveal that, even in areas with a decline in registered residents, there is active population influx due to commuting or visiting. These areas sustain an increase in the number of businesses, confirming the presence of industrial and economic growth. However, approximately 47% of administrative districts in Busan are experiencing a decline in both registered residents and living populations, indicating ongoing regional decline. Urgent measures are needed for enhancing urban vitality. The study emphasizes the necessity of utilizing living population data as an urban planning indicator, considering the increasing limit distance of urban activities and growing interregional interaction due to advancements in transportation and communication.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.498-500
• /
• 2022

CCTV protects people and assets safely by identifying dangerous situations and responding promptly. However, it is difficult to continuously monitor the increasing number of CCTV images. For this reason, there is a need for a device that continuously monitors CCTV images and notifies when abnormal behavior occurs. Recently, many studies using artificial intelligence models for image data analysis have been conducted. This study simultaneously learns spatial and temporal characteristic information between image data to classify various abnormal behaviors that can be observed in CCTV images. As an artificial intelligence model used for learning, we propose a multi-classification deep learning model that combines an end-to-end 3D convolutional neural network(CNN) and ResNet.

• Korea Science and Art Forum
• /
• v.34
• /
• pp.133-148
• /
• 2018

Korea's housing structure is predicted that one-person housing will be the most common type of housing in Korea. Therefore, this study intends to derive contents for designing a one-person housing space considering the life of a rapidly increasing one-person householder. For this purpose, this study objectively derives the social, economic and cultural influencing factors of one-person households through big data analysis, and analyzed the correlation between contents using social network analysis methodology. In this paper, 60 core contents related to one person housing space were derived by applying big data analysis methodology. And through social network analysis, the most influential contents were derived from the space editing and space composition categories. This means that the residential space is an important part of the design idea that can flexibly respond to changes in the user's life. Based on this study, future research will focus on the concept and design methodology of one-person housing space.