• Journal of Korea Water Resources Association
• /
• v.55 no.10
• /
• pp.707-721
• /
• 2022

In this study, a state-of-the-art review on urban inundation simulation technology was presented summarizing major achievements and limitations, and future research recommendations and challenges. More than 160 papers published in major domestic academic journals since the 2000s were analyzed. After analyzing the core themes and contents of the papers, the status of technological development was reviewed according to simulation methodologies such as physically-based and data-driven approaches. In addition, research trends for application purposes and advances in overseas and related fields were analyzed. Since more than 60% of urban inundation research used Storm Water Management Model (SWMM), developing new modeling techniques for detailed physical processes of dual drainage was encouraged. Data-based approaches have become a new status quo in urban inundation modeling. However, given that hydrological extreme data is rare, balanced research development of data and physically-based approaches was recommended. Urban inundation analysis technology, actively combined with new technologies in other fields such as artificial intelligence, IoT, and metaverse, would require continuous support from society and holistic approaches to solve challenges from climate risk and reduce disaster damage.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.55-65
• /
• 2023

In this paper, we apply KeyBERT(Keyword extraction with Bidirectional Encoder Representations of Transformers) algorithm-driven topic extraction and topic frequency analysis to deep learning and reinforcement learning research to discover the rapidly changing trends in them. First, we crawled abstracts of research papers on deep learning and reinforcement learning, and temporally divided them into two groups. After pre-processing the crawled data, we extracted topics using KeyBERT algorithm, and then analyzed the extracted topics in terms of topic occurrence frequency. This analysis reveals that there are distinct trends in research work of all analyzed algorithms and applications, and we can clearly tell which topics are gaining more interest. The analysis also proves the effectiveness of the utilized topic extraction and topic frequency analysis in research trend analysis, and this trend analysis scheme is expected to be used for research trend analysis in other research fields. In addition, the analysis can provide insight into how deep learning will evolve in the near future, and provide guidance for select research topics and methodologies by informing researchers of research topics and methodologies which are recently attracting attention.

• Bulletin of the Korean Space Science Society
• /
• 2009.10a
• /
• pp.42.3-43
• /
• 2009

Triplets of identical cubesats will be built to carry out the following scientific objectives: i) multi-observations of ionospheric ENA (Energetic Neutral Atom) imaging, ii) ionospheric signature of suprathermal electrons and ions associated with auroral acceleration as well as electron microbursts, and iii) complementary measurements of magnetic fields for particle data. Each satellite, a cubesat for ion, neutral, electron, and magnetic fields (CINEMA), is equipped with a suprathermal electron, ion, neutral (STEIN) instrument and a 3-axis magnetometer of magnetoresistive sensors. TRIO is developed by three institutes: i) two CINEMA by Kyung Hee University (KHU) under the WCU program, ii) one CINEMA by UC Berkeley under the NSF support, and iii) three magnetometers by Imperial College, respectively. Multi-spacecraft observations in the STEIN instruments will provide i) stereo ENA imaging with a wide angle in local times, which are sensitive to the evolution of ring current phase space distributions, ii) suprathermal electron measurements with narrow spacings, which reveal the differential signature of accelerated electrons driven by Alfven waves and/or double layer formation in the ionosphere between the acceleration region and the aurora, and iii) suprathermal ion precipitation when the storm-time ring current appears. In addition, multi-spacecraft magnetic field measurements in low earth orbits will allow the tracking of the phase fronts of ULF waves, FTEs, and quasi-periodic reconnection events between ground-based magnetometer data and upstream satellite data.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.2
• /
• pp.21-35
• /
• 2020

Due to the coronavirus pandemic and diplomatic disputes, governments are actively developing a policy to revitalize·reshore manufacturing and to diversify international cooperations. In order to develop such a policy, it is very important to compare and analyze domestic·international geospatial information. Over the decade, the US·EC governments have conducted a series of national researches to build data-based tools that can monitor·analyze regional geospatial information driven by government R&D investments. In the case of the EC system, it can compare geospatial information in domestic and international(including Korea) regions. Compared to US·EC cases, Korean examples of national researches with available data analplatform need future improvements. Current study is investigating an automated analysis methodologies using "National Institute of Science and Technology Information (NTIS)" DB, which was national security data until recently. Research on data-mining regional geospatial information can contribute to support policy fields that need to discover new issues in response to unexpected social problems such as recently faced corona and trade disputes.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.3
• /
• pp.1-10
• /
• 2004

Video-On-Demand servers use compression techniques to reduce the storage and bandwidth requirements. The compression techniques make the bit rates of compressed video data significantly variable from frame to frame. Consequently, Video-On-Demand servers with a constant bit rate retrieval can not maximize the utilization of resources. It is possible that when variable bit rate video data is stored, accurate description of the bit rate changes could be computed a priori. In this paper, I propose a buffer management scheme called MAX for Video-On-Demand server using variable bit rate continuous media. By caching and prefetching the data, MAX buffer management scheme reduces the variation of the compressed data and increases the number of clients simultaneously served and maximizes the utilization of system resources. Results of trace-driven simulations show the effectiveness of the scheme.

• Journal of Aerospace System Engineering
• /
• v.10 no.4
• /
• pp.67-74
• /
• 2016

The primary aim for using a Korean Condition Based Maintenance (CBM) system is to maintain military operational readiness using Interactive Collection Analysis Systems (ICAS) installed on naval vessels. Other aims are to preemptively provision maintenance and supply functions, to guarantee economical management of logistical assets, and to implement data driven equipment life cycle management. In order to accomplish these aims, it is necessary to establish standard system conditions. However, because manufacturers do not provide the technology necessary for maintenance management, it is required to retain component performance maps for each piece of equipment, and to accumulate data about frequently occurring fault patterns. This study confirms the validity of component performance maps using micro gas turbines and provides accumulated data on machine break downs. This would allow real time equipment performance checks and present performance trends. Then analysis would provide solutions for maintaining the best machine operating conditions with detailed maintenance manuals for operators. This study is a basis for further research to investigate additional ways to develop CBM using data obtained from naval vessels used in actual military operations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.180-186
• /
• 2022

Agrophotovoltaic (APV) system is an integrated system producing crops as well as solar energy. Because crop production underneath Photovoltaic (PV) modules requires delicate management of crops, smart farming equipment such as real-time remote monitoring sensors (e.g., soil moisture sensors) and micro-climate monitoring sensors (e.g., thermometers and irradiance sensors) is installed in the APV system. This study aims at introducing a decision support system (DSS) for smart farming in an APV system. The proposed DSS is devised to provide a mobile application service, satellite image processing, real-time data monitoring, and performance estimation. Particularly, the real-time monitoring data is used as an input of the DSS system for performance estimation of an APV system in terms of production yields of crops and monetary benefit so that a data-driven function is implemented in the proposed system. The proposed DSS is validated with field data collected from an actual APV system at the Jeollanamdo Agricultural Research and Extension Services in South Korea. As a result, farmers and engineers enable to efficiently produce solar energy without causing harmful impact on regular crop production underneath PV modules. In addition, the proposed system will contribute to enhancement of the smart farming technology in the field of agriculture.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• The Research Journal of the Costume Culture
• /
• v.32 no.2
• /
• pp.247-259
• /
• 2024

This study assessed the effectiveness of brand image communication on consumer perceptions of cruelty-free fashion brands. Brand messaging data were gathered from postings on the official Instagram accounts of three cruelty-free fashion brands and consumer perception data were gathered from Tweets containing keywords related to each brand. Web crawling and natural language processing were performed using Python and sentiment analysis was conducted using the BERT model. By analyzing Instagram content from Stella McCartney, Patagonia, and Freitag from their inception until 2021, this study found these brands all emphasize environmental aspects but with differing focuses: Stella McCartney on ecological conservation, Patagonia on an active outdoor image, and Freitag on upcycled products. Keyword analysis further indicated consumers perceive these brands in line with their brand messaging: Stella McCartney as high-end and eco-friendly, Patagonia as active and environmentally conscious, and Freitag as centered on recycling. Results based on the assessment of the alignment between brand-driven images and consumer-perceived images and the sentiment evaluation of the brand confirmed the outcomes of brand communication performance. The study revealed a correlation between brand image and positive consumer evaluations, indicating that higher alignment of ethical values leads to more positive consumer assessments. Given that consumers tend to prioritize search keywords over brand concepts, it's important for brands to focus on using visual imagery and promotions to effectively convey brand communication information. These findings highlight the importance of brand communication by emphasizing the connection between ethical brand images and consumer perceptions.

• The KIPS Transactions:PartD
• /
• v.14D no.1 s.111
• /
• pp.121-130
• /
• 2007

in a software development, the design or architecture prior to implementing the software is essential for the success. This paper presents a case that we successfully designed a software architecture of radiation monitoring system (RMS) for HANARO research reactor currently operating in KAERI by applying the quality attribute-driven design method which is modified from the attribute-driven design (ADD) introduced by Bass[1]. The quality attribute-driven design method consists of following procedures: eliciting functionality and quality requirements of system as architecture drivers, selecting tactics to satisfy the drivers, determining architectures based on the tactics, and implementing and validating the architectures. The availability, maintainability, and interchangeability were elicited as duality requirements, hot-standby dual servers and weak-coupled modulization were selected as tactics, and client-server structure and object-oriented data processing structure were determined at architectures for the RMS. The architecture was implemented using Adroit which is a commercial off-the-shelf software tool and was validated based on performing the function-oriented testing. We found that the design method in this paper is an efficient method for a project which has constraints such as low budget and short period of development time. The architecture will be reused for the development of other RMS in KAERI. Further works are necessary to quantitatively evaluate the architecture.