• Land and Housing Review
• /
• v.14 no.2
• /
• pp.125-135
• /
• 2023

Drones are used in various fields, including land survey, transportation, forestry/agriculture, marine, environment, disaster prevention, water resources, cultural assets, and construction, as their industrial importance and market size have increased. In this study, image data for deep learning was collected using a mavic3 drone capturing images at a shooting altitude was 20 m with ×7 magnification. Swin Transformer and UperNet were employed as the backbone and architecture of the deep learning model. About 800 sheets of labeled data were augmented to increase the amount of data. The learning process encompassed three rounds. The Cross-Entropy loss function was used in the first and second learning; the Tversky loss function was used in the third learning. In the future, when the crack detection model is advanced through convergence with the Internet of Things (IoT) through additional research, it will be possible to detect patching or potholes. In addition, it is expected that real-time detection tasks of drones can quickly secure the detection of pavement maintenance sections.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.49-60
• /
• 2024

Ground-penetrating radar (GPR) enables rapid data acquisition over extensive areas, but interpreting the obtained data requires specialized knowledge. Numerous studies have utilized numerical analysis methods to examine GPR signal characteristics under various conditions. To develop more realistic numerical models, the heterogeneous nature of the ground, which causes clutter, must be considered. Clutter refers to signals reflected by objects other than the target. The Peplinski material model and fractal techniques can simulate these heterogeneous characteristics, yet there is a shortage of research on the necessary input parameters. Moreover, methods for quantitatively evaluating the similarity between field and analytical data are not well established. In this study, we calculated the autocorrelation coefficient of field data and determined the correlation length using the autocorrelation function. The correlation length represented the temporal or spatial distance over which data exhibited similarity. By comparing the correlation length of field data with that of the numerical model incorporating fractal weights, we quantitatively evaluated a numerical model for heterogeneous ground. Consequently, the results of this study demonstrated a numerical modeling technique that reflected the clutter characteristics of the field through correlation length.

• Journal of radiological science and technology
• /
• v.28 no.4
• /
• pp.317-325
• /
• 2005

The recent medical treatment guidelines and the development of information technology make hospitals reduce the expense in surrounding environment and it requires improving the quality of medical treatment of the hospital. That is, with the new guidelines and technology, hospital business escapes simple fee calculation and insurance claim center. Moreover, MIS(Medical Information System), PACS(Picture Archiving and Communications System), OCS(Order Communicating System), EMR(Electronic Medical Record), DSS(Decision Support System) are also developing. Medical Information System is evolved toward integration of medical IT and situation si changing with increasing high speed in the ICT convergence. These changes and development of ubiquitous environment require fundamental change of medical information system. Mobile medical information system refers to construct wireless system of hospital which has constructed in existing environment. Through RFID development in existing system, anyone can log on easily to Internet whenever and wherever. RFID is one of the technologies for Automatic Identification and Data Capture(AIDC). It is the core technology to implement Automatic processing system. This paper provides a comprehensive basic review of RFID model in Korea and suggests the evolution direction for further advanced RFID application services. In addition, designed and implemented DB server's agent program and Client program of Mobile application that recognized RFID tag and patient data in the ubiquitous environments. This system implemented medical information system that performed patient data based EMR, HIS, PACS DB environments, and so reduced delay time of requisition, medical treatment, lab.

• The Mathematical Education
• /
• v.62 no.2
• /
• pp.289-302
• /
• 2023

In today's digital information society, student knowledge and skills to analyze big data and make informed decisions have become an important goal of school mathematics. Integrating big data statistical projects with digital technologies in high school <Artificial Intelligence> mathematics courses has the potential to provide students with a learning experience of high impact that can develop these essential skills. This paper proposes a set of guidelines for designing effective big data statistical project-based tasks and evaluates the tasks in the artificial intelligence mathematics textbook against these criteria. The proposed guidelines recommend that projects should: (1) align knowledge and skills with the national school mathematics curriculum; (2) use preprocessed massive datasets; (3) employ data scientists' problem-solving methods; (4) encourage decision-making; (5) leverage technological tools; and (6) promote collaborative learning. The findings indicate that few textbooks fully align with these guidelines, with most failing to incorporate elements corresponding to Guideline 2 in their project tasks. In addition, most tasks in the textbooks overlook or omit data preprocessing, either by using smaller datasets or by using big data without any form of preprocessing. This can potentially result in misconceptions among students regarding the nature of big data. Furthermore, this paper discusses the relevant mathematical knowledge and skills necessary for artificial intelligence, as well as the potential benefits and pedagogical considerations associated with integrating technology into big data tasks. This research sheds light on teaching mathematical concepts with machine learning algorithms and the effective use of technology tools in big data education.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.437-442
• /
• 2020

Since the advent of the innovative information technology called the Internet, the dynamism of the information environment has brought about changes in information users' needs and behavior. It is essential to understand information users in this rapidly changing environment, and based on this, it is necessary to effectively build and operate an information service and a system therefor. The purpose of this study is to understand the characteristics according to the segmentation of users of the National Science and Technology Information Service System, and to derive improvements to customized services and content development through research and analysis of content usage. A total of 816 science and technology information service system users participated in online surveys from September to November. Collected data is applied to factor analysis and cluster analysis techniques to subdivide users of science and technology information service systems, to recognize new information technologies and information services, science technology information needs, and science and technology attributes that users consider important. We derived the results according to the segmented user group.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.764-768
• /
• 2015

Requirement of effective image handling methods such as image retrieval has been increasing with the rising production and consumption of multimedia data. In this paper, a method of constructing more effective descriptor is proposed for robust keypoint based image retrieval. The proposed method uses information embedded in the first order and second order derivative images, in addition to the scale space image, for the descriptor construction. The performance of multi-image descriptor is evaluated in terms of the similarities in keypoints with a public domain image database that contains various image transformations. The proposed descriptor shows significant improvement in keypoint matching with minor increase of the length.

• Bulletin of the Korean Space Science Society
• /
• 2010.04a
• /
• pp.36.4-36.4
• /
• 2010

이 논문에서는 신호감시국, 상향링크국, 감시제어 시스템으로 구성된 위성항법 지상국과 탐색구조단말기 관련 기술내용과 그 시험에 대한 내용을 기술하였다. 위성항법 지상국 시스템 및 탐색구조 단말기 기술 개발은 향상된 위치기반서비스와 재난시 신속한 탐색구조 서비스 제공을 위한 것으로 그 핵심기술 개발을 주요 목적으로 한다. 이를 통하여 개발된 신호감시국용 고정밀 위성항법 수신기 기술은 고정밀 전문용 위성항법 단말기의 상용화의 추진하며 감시제어시스템은 GPS 및 갈릴레오 신호 감시 데이터를 위성항법 통제센터(GNSS Control Center: GCC)에 제공하고, 향상된 위치 정확도를 제공하며, 위성항법 신호감시국의 장비를 감시 제어하며, GPS 및 갈릴레오 서비스를 위한 가용성을 제공하는 것이다. 상향링크국에서는 다중 중궤도 위성 추적시스템과 상향링크 데이터 처리를 목적으로 한다. 탐색구조 단말기 기술개발은 항법 칩셋을 탑재한 2세대 탐색구조 단말기를 개발 완료 함으로써 신속하고 정확한 조난구조가 가능하게 하는 단말기를 국내외 시장에 내놓을 수 있게 하였으며, 2세대 탐색구조 단말기의 소형화 저전력화에 성공하여 상용화 및 국제인증을 완료하였다. 이 논문에서는 이러한 기술개발 내용과 그검증을 위한 시험 결과에 대하여 소개하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.304-309
• /
• 2020

본 연구에서는 한국어 전자사전 DECO(Dictionnaire Electronique du COreen)와 다단어(Multi-Word Expressions: MWE) 개체명을 부분 패턴으로 기술하는 부분문법그래프(Local-Grammar Graph: LGG) 프레임에 기반하여 반자동으로 개체명주석 코퍼스 DecoNAC을 구축한 후, 이를 개체명 분석에 활용하고 또한 기계학습에 필요한 도메인별 학습 데이터로 활용하는 DecoNERO 개체명인식 플랫폼을 소개하는 데에 목적을 두었다. 최근 들어 좋은 성과를 보이는 것으로 보고되고 있는 기계학습 방법론들은 다양한 도메인을 기반으로한 대규모의 학습데이터를 필요로 한다. 본 연구에서는 정교하게 설계된 개체명 사전과 다단어 개체명 시퀀스에 대한 언어자원을 바탕으로 하는 반자동으로 학습데이터를 생성하는 방법론을 제안하였다. 본 연구에서 제안된 개체명주석 코퍼스 DecoNAC 기반 접근법의 성능을 실험하기 위해 온라인 뉴스 기사 텍스트를 바탕으로 실험을 진행하였다. 이 실험에서 DecoNAC을 적용한 경우, KoBERT 모델만으로 개체명을 인식한 결과에 비해 약 7.49%의 성능향상을 기대할 수 있음을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.35-43
• /
• 2021

Citrus quality is generally determined by its sugar content and acidity. In particular, sugar content is a very important factor because it determines the taste of citrus. Currently, the most commonly used method of measuring citrus sugar content in farms is a portable juiced sugar meter and a non-destructive sugar meter. This method can be easily measured by individuals, but the accuracy of the sugar content is inferior to that of the citrus NongHyup official machine. In particular, there is an error difference of 0.5 Brix or more, which is still insufficient for use in the field. Therefore, in this paper, we propose an AI model that predicts the citrus sugar content of unmeasured days within the error range of 0.5 Brix or less based on the previously collected citrus sugar content and meteorological data (average temperature, humidity, rainfall, solar radiation, and average wind speed). In addition, it was confirmed that the prediction model proposed through performance evaluation had an mean absolute error of 0.1154 for Seongsan area and 0.1983 for the Hawon area in Jeju Island. Lastly, the proposed model supports an error difference of less than 0.5 Brix and is a technology that supports predictive measurement, so it is expected that its usability will be highly progressive.

• Journal of the Korea Society for Simulation
• /
• v.32 no.1
• /
• pp.45-54
• /
• 2023

Under combat simulation environment when inputting the detection performance data of the real system into the simulated object the given data affects the simulation analysis result. ACQUIRE-Target Task Performance Metric (TTPM)-Target Angular Size (TAS) model is used as a target acquisition model to simulate the detection ability of entities in the main combat simulation tool. This model estimates the decomposition curve of the object sensor and output the detection distance according to the target type. However, it is not easy to apply the performance of the new detection object that the user wants to input to the target acquisition model. Users want to input the detection distance into the target acquisition model, but the target acquisition model requires sensor decomposition curve data according to encounter conditions. In this paper, we propose a method of inversely deriving the sensor decomposition curve data of the target acquisition model by taking the detection distance to the target as an input. Here, the sensor decomposition curve data simultaneously satisfies each detection distance for three types of targets: personnel, ground vehicles, and aircraft. Finally, the detection distance of various reconnaissance equipment is applied to the detection object, and the detection effect according to the reconnaissance equipment is analyzed.