• Journal of the Society of Naval Architects of Korea
• /
• v.60 no.4
• /
• pp.248-255
• /
• 2023

In order to implement the autonomous navigation function, it is essential to track an object within a certain radius of the ship's route. This paper proposes the Multiple Probabilistic Data Association Filter (MPDAF), which can track multiple ships by extending Probabilistic Data Association Filter (PDAF), an existing single object tracking algorithm, using radar data obtained from real marine environments. The proposed MPDAF algorithm was developed to address the problem of tracking multiple objects in a complex environment where there can be significant uncertainty in the number and identification of objects to be tracked. Using real-world radar data provided by the German aerospace center (DLR), it has been verified that the proposed algorithm can track a large number of objects with a small position error.

• Journal of Powder Materials
• /
• v.30 no.3
• /
• pp.217-222
• /
• 2023

Machine learning-based data analysis approaches have been employed to overcome the limitations in accurately analyzing data and to predict the results of the design of Nb-based superalloys. In this study, a database containing the composition of the alloying elements and their room-temperature tensile strengths was prepared based on a previous study. After computing the correlation between the tensile strength at room temperature and the composition, a material science analysis was conducted on the elements with high correlation coefficients. These alloying elements were found to have a significant effect on the variation in the tensile strength of Nb-based alloys at room temperature. Through this process, a model was derived to predict the properties using four machine learning algorithms. The Bayesian ridge regression algorithm proved to be the optimal model when Y, Sc, W, Cr, Mo, Sn, and Ti were used as input features. This study demonstrates the successful application of machine learning techniques to effectively analyze data and predict outcomes, thereby providing valuable insights into the design of Nb-based superalloys.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.927-932
• /
• 2016

With the explosive increase in the number of online medical documents, the demand for question-answering systems is increasing. Recently, question-answering models based on machine learning have shown high performances in various domains. However, many question-answering models within the medical domain are still based on information retrieval techniques because of sparseness of training data. Based on various information retrieval techniques, we propose an answer snippet retrieval model for question-answering systems of medical documents. The proposed model first searches candidate answer sentences from medical documents using a cluster-based retrieval technique. Then, it generates reliable answer snippets using a re-ranking model of the candidate answer sentences based on various sentence retrieval techniques. In the experiments with BioASQ 4b, the proposed model showed better performances (MAP of 0.0604) than the previous models.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.197-219
• /
• 2023

The cataloging rules of AACR families and bibliographic structure, which are broadly used in describing resources, show limitations in reflecting the unique bibliographic characteristics of Korean old materials. Thus this research proposed a bibliographic structure optimized to the unique bibliographic characteristics of Korean old materials by establishing bibliographic relationships between bibliographic entities based on the FRBR LRM conceptual model. The bibliographic relationships should be established in the way of connecting related materials in the bibliographic structure. These relationships should sufficiently reflect the bibliographic characteristics of the materials, physical variations, and content variations. Through this structure, the bibliographic description can be separated and integrated into the bibliograhpic unit by applying LRM conceptual model. By using the proposed structure, the organization, management, and utilization of Korean old materials can be more efficient. Also, it can provide a new bibliographic environment that can be the foundation of creating BIBFRAME records for Korean old materials.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.16-22
• /
• 2020

The Korea Institute of Ocean Science & Technology is developing a free-fall cone penetration test system (FFCPT) that can acquire the characteristics of the seabed surface soil. To obtain the data through the FFCPT, a method of storing the signals for the entire time or a method of storing the signal for user-defined time can be considered. For efficient data storage and management, it is advantageous that data be stored by user definition. Therefore, this study analyzed the basic behavior using the signal acquired through a sensor mounted in the FFCPT and developed a trigger method to recognize the start and end of data storage using a depth sensor. The start and endpoints of the fall were determined using the moving average difference of 3 and 0.03 seconds of the depth signal. A real sea-trial test was performed using the FFCPT, and the developed trigger was operated normally.

• The Korean Journal of Archival Studies
• /
• no.70
• /
• pp.85-117
• /
• 2021

The purpose of this study is to investigate and analyze the current status of unit tasks, unit task operation, and record management problems used by local governments, and to present improvement measures using text-based big data technology based on the implications derived from the process. Local governments are in a serious state of record management operation due to errors in preservation period due to misclassification of unit tasks, inability to identify types of overcommon and institutional affairs, errors in unit tasks, errors in name, referenceable standards, and tools. However, the number of unit tasks is about 720,000, which cannot be effectively controlled due to excessive quantities, and thus strict and controllable tools and standards are needed. In order to solve these problems, this study developed a system that applies text-based analysis tools such as corpus and tokenization technology during big data analysis, and applied them to the names and construction terms constituting the record management standard. These unit task operation support tools are expected to contribute significantly to record management tasks as they can support standard operability such as uniform preservation period, identification of delegated office records, control of duplicate and similar unit task creation, and common tasks. Therefore, if the big data analysis methodology can be linked to BRM and RMS in the future, it is expected that the quality of the record management standard work will increase.

• Ocean and Polar Research
• /
• v.44 no.2
• /
• pp.113-126
• /
• 2022

This study was carried out to investigate the benthic polychaetous community and benthic ecosystem quality status on the adjacent continental shelf of Jeju Island, and field surveys were conducted at 31 stations in July and August, 2020. The surface sediment was generally composed of muddy sand facies and sandy mud facies, and the average particle size was medium silt (6.1±1.6∅). The benthic polychaetous community revealed a total of 73 species with a mean density of 242 ind./m². The major dominant species were Notomastus latericeus, Ampharete arctica and Onuphis shirikishinaiensis. By the cluster analysis and nMDS results based on species composition of the benthic polychaetous community, the study area was divided into three station groups arranged from east to west by the water depth and sedimentary facies. The station group located in the west was subdivided into two station groups from south to north. From results of correlation analysis and PCA, it was found that the benthic polychaetous community in the study area had a strong correlation with the sedimentary environment and water depth. The benthic faunal community (or ecosystem) on the adjacent continental shelf of Jeju Island was assessed to be in a healthy state by biotic indices such as AMBI and BPI.

• Journal of Korean Society of Archives and Records Management
• /
• v.24 no.1
• /
• pp.47-72
• /
• 2024

This study delves into the National Archives of Korea's service that provides information on changes in records-creating agencies, identifying the problems in an organizational relationship structure and exploring potential enhancements using the RiC-O. Drawing insights from the French PIAAF project, we applied RiC-O to integrate information on records and records creators, elucidating relationships between data entities. Our analysis demonstrated that leveraging RiC-O, coupled with technologies like linked data, amplifies the interoperability of authority records, substantially enhancing the service providing information on changes in records-creating agencies. Based on these findings, we propose an authority record service based on RiC-O, presenting a prototype designed to improve the National Archives of Korea's change information service and enhance user experience.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.2
• /
• pp.55-67
• /
• 2023

This study aims to develop a model that can automatically identify the rooftop shape of apartment buildings using GIS and machine learning algorithms, and apply it to analyze the relationship between rooftop shape and characteristics of apartment complexes. A database of rooftop data for each building in an apartment complex was constructed using geospatial data, and individual buildings within each complex were classified into flat type, tower type, and mixed types using the random forest algorithm. In addition, the relationship between the proportion of rooftop shapes, development density, height, and other characteristics of apartment complexes was analyzed to propose the potential application of geospatial information in the real estate field. This study is expected to serve as a basic research on AI-based building type classification and to be utilized in various spatial and real estate analyses.