• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• Atmosphere
• /
• v.29 no.4
• /
• pp.417-427
• /
• 2019

The purpose of this study is to build urban canopy model (Met Office Reading Urban Surface Exchange Scheme, MORUSES) based to Unified Model (UM) by using urban building information data in Seoul, and then to compare the improving urban canopy model simulation result with that of Seoul Automatic Weather Station (AWS) observation site data. UM-MORUSES is based on building information database in London, we performed a sensitivity experiment of UM-MOURSES model using urban building information database in Seoul. Geographic Information System (GIS) analysis of 1.5 km resolution Seoul building data is applied instead of London building information data. Frontal-area index and planar-area index of Seoul are used to calculate building height. The height of the highest building in Seoul is 40m, showing high in Yeoido-gu, Gangnam-gu and Jamsil-gu areas. The street aspect ratio is high in Gangnam-gu, and the repetition rate of buildings is lower in Eunpyeong-gu and Gangbuk-gu. UM-MORUSES model is improved to consider the building geometry parameter in Seoul. It is noticed that the Root Mean Square Error (RMSE) of wind speed is decreases from 0.8 to 0.6 m s^-1 by 25 number AWS in Seoul. The surface air temperature forecast tends to underestimate in pre-improvement model, while it is improved at night time by UM-MORUSES model. This study shows that the post-improvement UM-MORUSES model can provide detailed Seoul building information data and accurate surface air temperature and wind speed in urban region.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.974-992
• /
• 2021

Recently, the healthcare field has undergone rapid changes owing to the accumulation of health big data and the development of machine learning. Data mining research in the field of healthcare has different characteristics from those of other data analyses, such as the structural complexity of the medical data, requirement for medical expertise, and security of personal medical information. Various methods have been implemented to address these issues, including the machine learning model and cloud platform. However, the machine learning model presents the problem of opaque result interpretation, and the cloud platform requires more in-depth research on security and efficiency. To address these issues, this paper presents a recent technology for Internet-of-Things-based (IoT-based) health big data processing. We present a cloud-based IoT health platform and health big data processing technology that reduces the medical data management costs and enhances safety. We also present a data mining technology for health-risk prediction, which is the core of healthcare. Finally, we propose a study using explainable artificial intelligence that enhances the reliability and transparency of the decision-making system, which is called the black box model owing to its lack of transparency.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.407-414
• /
• 2009

The foundation fieldbus(FF) is one of the fieldbuses most widely used for process control and automation, In order for system designer to optimize medium management, it is imperative to predict transmission delay time of data. In a former research, mathematical modeling to analyze transmission delay of FF token-passing system has been developed based on the assumption that a device node has only one priority data(1Q model), From 1Q model, all of the device nodes, which are connected on the FF system, are defined priority level in advance, and as system operates, data are generated based on given priority level. However, in practice, some non-periodic data can have different priority levels from one device. Therefore, new mathematical model is necessary for the case where different priority levels of data are created under one device node(2Q model). In this research, the mathematical model for 2Q model is developed using the equivalent queue model. Furthermore, the characteristics of transmission delay of 2Q model which is presented in this paper were compared with 1Q model. The validity of the analytical model was verified by using a simulation experiment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.3
• /
• pp.165-176
• /
• 2018

To solve the inconsistencies between realistic boundaries and the cadastral record boundaries, the cadastral resurvey project has been funded by a large budget since 2012 and executed over a long period of time until 2030. However, if the causes of inconsistencies are not analyzed and addressed, these inconsistencies could possibly reoccur. Even though the causes of inconsistencies can be defined in several aspects, including regulations, surveying methods, and management of cadastre maps or survey results, and so on, this study focuses on analyzing the inconsistency problems in the management of cadastre maps or survey results. In order to resolve the problems in inconsistencies between the cadastre maps and survey results, the study proposes to develop the cadastre data model based on LADM (Land Administration Domain Model) to manage the cadastre maps and survey results in better ways. In order to proposed the Cadastre Data Model, we analyzed the cadastre management system implemented in Korea and identified requirements to resolve the problems in inconsistencies, which are considered in the proposed data model as follows: 1) cadastral management system based on individual parcels, 2) synthesis of a realistic boundary and cadastral record boundary, 3) management of official and sharing reference data, 4) consistent management of survey results and parcel boundaries, 5) temporal managements of parcel boundaries. In the end, this study proposes a cadastral data model based on the LADM to integrate and manage the cadastral surveying results of the new cadastral management system.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.3
• /
• pp.575-584
• /
• 2004

We propose a Bayesian model-based approach using a mixture of Dirichlet processes model with discrete wavelet transform, for curve clustering in the microarray data with time-course gene expressions.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.10 no.3
• /
• pp.11-18
• /
• 2010

Cost estimation through fast and correct quantity take offs are crucial in the process of construction project. The existing methods for cost estimation are mainly based on 2D-based drawings and the estimation result tends to be different according to the estimator's experience, the quality and quantity of used information and estimation time. To solve these problems, the domestic construction industry have recently tried to use the data extracted from 3D data modeling based on BIM(Building Information Modeling) in order to achieve more accurate and objective cost estimation. However it tends to increase dramatically the quantity of information that can be used in cost estimation by estimators. Therefore in order to achieve quality information data from 3D data modeling, the characteristics of the project should be reflected on the 3D model and it is most important to extract information only for cost estimation from the whole 3D model fast and accurately. Thus this study aims to propose the 3D modeling method through Data Normalization which maximizes the usability of 3D Data modeling in cost estimation process.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.96-99
• /
• 2008

When the design modification is occurred, at present, design process based on 2-D spend more time and effort than that based on 3-D to modify related structural details. To improve and develop these processes, therefore, the design possibility of civil structures based on virtual model of 3-D must be investigated. We designed reinforced concrete pier of 3-D model, containing parameters. The parameters was defined as structural details like area of the section, reinforcement specification for design modification and structural analysis. In this paper, we researched about the processes modeling of reinforced concrete bridge pier based on parameters, the extracting data from the virtual model of 3-D, and the reflection of data to virtual model throughout structural analysis.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.5
• /
• pp.101-111
• /
• 2015

Establishment of appropriate data in certain formats is essential for agricultural water cycle analysis, which involves complex interactions and uncertainties such as climate change, social & economic change, and watershed environmental change. The main objective of this study was to develop web-based Data processing and Model linkage Techniques for Agricultural Water-Resource analysis (AWR-DMT). The developed techniques consisted of database development, data processing technique, and model linkage technique. The watershed of this study was the upper Cheongmi stream and Geunsam-Ri. The database was constructed using MS SQL with data code, watershed characteristics, reservoir information, weather station information, meteorological data, processed data, hydrological data, and paddy field information. The AWR-DMT was developed using Python. Processing technique generated probable rainfall data using non-stationary frequency analysis and evapotranspiration data. Model linkage technique built input data for agricultural watershed models, such as the TANK and Agricultural Watershed Supply (AWS). This study might be considered to contribute to the development of intelligent watercycle analysis by developing data processing and model linkage techniques for agricultural water-resource analysis.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1407-1416
• /
• 2018

The purpose of this study was to train a model for the ulna and radius bone segmentation based on Convolutional Neural Networks and to verify the segmentation model. The data consisted of 840 training data, 210 tuning data, and 200 verification data. The learning model for the ulna and radius bone bwas based on U-Net (19 convolutional and 8 maximum pooling) and trained with 8 batch sizes, 0.0001 learning rate, and 200 epochs. As a result, the average sensitivity of the training data was 0.998, the specificity was 0.972, the accuracy was 0.979, and the Dice's similarity coefficient was 0.968. In the validation data, the average sensitivity was 0.961, specificity was 0.978, accuracy was 0.972, and Dice's similarity coefficient was 0.961. The performance of deep convolutional neural network based models for the segmentation was good for ulna and radius bone.