• Title/Summary/Keyword: 기술 분류

Search Result 6,612, Processing Time 0.032 seconds

Jaundice in Young Children (소아 황달의 영상 평가)

  • Young Hun Choi;Seul Bi Lee;Yeon Jin Cho;Seung Hyun Lee;Su-Mi Shin;Jung-Eun Cheon
    • Journal of the Korean Society of Radiology
    • /
    • v.83 no.5
    • /
    • pp.966-978
    • /
    • 2022
  • Jaundice in children have various etiologies. Among them, physiological jaundice is a very common disease observed in more than half of full-term neonates. When jaundice persists or develops after 2 weeks of age, the total/direct bilirubin is measured in consideration of the possibility of cholestasis. In case of cholestasis, imaging studies differentiate biliary atresia and other disorders of the extrahepatic bile ducts. In this review, we briefly presented the major differential diseases of cholestasis in children and introduced diagnostic imaging techniques, including normal findings.

A Study on Predicting Credit Ratings of Korean Companies using TabNet

  • Hyeokjin Choi;Gyeongho Jung;Hyunchul Ahn
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.5
    • /
    • pp.11-20
    • /
    • 2024
  • This study presents TabNet, a novel deep learning method, to enhance corporate credit rating accuracy amidst growing financial market uncertainties due to technological advancements. By analyzing data from major Korean stock markets, the research constructs a credit rating prediction model using TabNet. Comparing it with traditional machine learning, TabNet proves superior, achieving a Precision of 0.884 and an F1 score of 0.895. It notably reduces misclassification of high-risk companies as low-risk, emphasizing its potential as a vital tool for financial institutions in credit risk management and decision-making.

Autoencoder Based N-Segmentation Frequency Domain Anomaly Detection for Optimization of Facility Defect Identification (설비 결함 식별 최적화를 위한 오토인코더 기반 N 분할 주파수 영역 이상 탐지)

  • Kichang Park;Yongkwan Lee
    • The Transactions of the Korea Information Processing Society
    • /
    • v.13 no.3
    • /
    • pp.130-139
    • /
    • 2024
  • Artificial intelligence models are being used to detect facility anomalies using physics data such as vibration, current, and temperature for predictive maintenance in the manufacturing industry. Since the types of facility anomalies, such as facility defects and failures, anomaly detection methods using autoencoder-based unsupervised learning models have been mainly applied. Normal or abnormal facility conditions can be effectively classified using the reconstruction error of the autoencoder, but there is a limit to identifying facility anomalies specifically. When facility anomalies such as unbalance, misalignment, and looseness occur, the facility vibration frequency shows a pattern different from the normal state in a specific frequency range. This paper presents an N-segmentation anomaly detection method that performs anomaly detection by dividing the entire vibration frequency range into N regions. Experiments on nine kinds of anomaly data with different frequencies and amplitudes using vibration data from a compressor showed better performance when N-segmentation was applied. The proposed method helps materialize them after detecting facility anomalies.

Inspection of A Deteriorated Bridge Pier Cap Using Common Nondestructive and Destructive Test (파괴 및 비파괴 검사를 이용한 노후 교량의 교각 두부 조사)

  • Kim, Tae Wan;Hong, Sung Nam;Han, Kyoung Bong;Park, Sun Kyu
    • Journal of the Korea institute for structural maintenance and inspection
    • /
    • v.12 no.2
    • /
    • pp.91-102
    • /
    • 2008
  • Nondestructive testing techniques have been historically and commonly used to evaluate the quality of existing concrete structures. The techniques utilized included visual inspection, hammer sounding, Schmidt hammer rebounding, and ultrasonic pulse velocity testing including tomographic imaging. Results of the nondestructive tests were used to determine areas to be tested with local destructive tests. These tests included concrete compressive strengths, chloride testing, and petrographic testing. The overall results indicate that inside core of each of the pier caps are healthy. On all of the pier caps, extensive exterior concrete layer rehabilitation needs to be completed. This paper shows the application and interpretation of common nondestructive testing techniques and the consequent repair, rehabilitation, maintenance decisions and safety assesment.

A study on the weighting of influence factors for tunnel collapse risk analysis (터널 붕괴 위험도 분석을 위한 영향인자 가중치 산정에 관한 연구)

  • Jeong-Heum Kim
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.26 no.4
    • /
    • pp.315-326
    • /
    • 2024
  • In this study, the Delphi method and AHP (analytic hierarchy process) were used to evaluate tunnel collapse risk from a comprehensive and multifaceted perspective. Influence factors were established through literature reviews, previous studies, and brainstorming sessions with expert groups, resulting in the construction of five main classification systems. A panel of 21 experts was formed, and three rounds of Delphi surveys were conducted to prevent errors and biases in the expert judgment process, thereby enhancing reliability. Ultimately, 14 influence factors were identified through CVR (content validity ratio) and COV (coefficient of variation) analyses of the experts' responses. Subsequently, the AHP method was applied to assess the relative importance of each influence factor and calculate the final composite weights. The timing of support and reinforcement had the highest priority, followed by groundwater inflow, joint conditions, support pattern levels, and auxiliary methods. These findings help identify the key factors affecting tunnel collapse risk and provide a foundation for developing strategies to improve tunnel safety.

Trends in Antidote Technologies for Nerve Agents (신경작용제 해독 기술 동향)

  • Sungyiel Kim;Jinkwang Jeong;Dongwook Kim;Seungyul Hwang;Yoonje Cho;Yeongwook Yoon;Taein Ryu;Keunhong Jeong
    • Applied Chemistry for Engineering
    • /
    • v.35 no.4
    • /
    • pp.284-295
    • /
    • 2024
  • Chemical agents are classified according to their mechanism of toxicity into categories such as nerve agents, choking agents, blood agents, blister agents, etc. Among them, nerve agents cause toxic symptoms by binding with acetylcholinesterase (AChE) in the body, which breaks down neurotransmitters, thus disrupting the autonomic nervous system. In severe cases, this can lead to death, making it a critical chemical agent. Therefore, once it has penetrated into the human body, it is important to detoxify it swiftly. Antidotes used for detoxification include chemical medicines such as pretreatment agents, post-treatment agents, anticonvulsants, and bioscavengers. This review will address the uses, forms, components, and principles of detoxification of nerve agent antidotes and the association with bioscavengers.

Named entity normalization for traditional herbal formula mentions

  • Ho Jang
    • Journal of the Korea Society of Computer and Information
    • /
    • v.29 no.10
    • /
    • pp.105-111
    • /
    • 2024
  • In this paper, we propose methods for the named entity normalization of traditional herbal formula found in medical texts. Specifically, we developed methodologies to determine whether mentions, such as full names of herbal formula and their abbreviations, refer to the same concept. Two different approaches were attempted. First, we built a supervised classification model that uses BERT-based contextual vectors and character similarity features of herbal formula mentions in medical texts to determine whether two mentions are identical. Second, we applied a prompt-based querying method using GPT-4o mini and GPT-4o to perform the same task. Both methods achieved over 0.9 in Precision, Recall, and F1-score, with the GPT-4o-based approach demonstrating the highest Precision and F1-Score. The results of this study demonstrate the effectiveness of machine learning-based approaches for named entity normalization in traditional medicine texts, with the GPT-4o-based method showing superior performance. This suggests its potential as a valuable foundation for the development of intelligent information extraction systems in the traditional medicine domain.

Model Type Inference Attack against AI-Based NIDS (AI 기반 NIDS에 대한 모델 종류 추론 공격)

  • Yoonsoo An;Dowan Kim;Dae-seon Choi
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.34 no.5
    • /
    • pp.875-884
    • /
    • 2024
  • The proliferation of IoT networks has led to an increase in cyber attacks, highlighting the importance of Network Intrusion Detection Systems (NIDS). To overcome the limitations of traditional NIDS and cope with more sophisticated cyber attacks, there is a trend towards integrating artificial intelligence models into NIDS. However, AI-based NIDS are vulnerable to adversarial attacks, which exploit the weaknesses of algorithm. Model Type Inference Attack is one of the types of attacks that infer information inside the model. This paper proposes an optimized framework for Model Type Inference attacks against NIDS models, applying more realistic assumptions. The proposed method successfully trained an attack model to infer the type of NIDS models with an accuracy of approximately 0.92, presenting a new security threat to AI-based NIDS and emphasizing the importance of developing defence method against such attacks.

Technique to Generate Sterile Males of Striped Fruit Flies, Zeugodacus scutellata, using Electron Beam Irradiation and their Application to Genetic Control (전자빔 조사를 이용한 호박꽃과실파리의 불임 수컷 제조 기술과 유전방제 응용)

  • Kim, Yonggyun;Al Baki, Md. Abdullah;Kwon, Gimyeon
    • Korean journal of applied entomology
    • /
    • v.59 no.1
    • /
    • pp.25-35
    • /
    • 2020
  • The striped fruit fly, Zeugodacus scutellata, is endemic in Korea, but it has been regarded as one of the serious quarantine pests throughout the world. Sterile insect release technique (SIT) has been used to eradicate quarantine fruit flies. This study developed a technique to generate sterile males and applied SIT to control Z. scutellata. First of all, the reproductive systems of Z. scutellata adults were examined with fluorescent microscope. Polytrophic ovaries comprises of around 100 follicles with developing oocytes. Each follicle contains an oocyte with several nurse cells and are surrounded with follicular epithelium. Oocyte development began at 10 days after adult emergence (DAE) and formed chorionated oocytes after 20 DAE. On the other hand, male testes were well developed just after adult emergence. The vas deferens was filled with motile sperms. To generate sterile males, different doses (0~1,000 Gy) doses of electron beam were irradiated to 3~5 days old pupae of Z. scutellata. When male pupae were irradiated with electron beam at 200 Gy, they developed and mated with females without any significant difference compared to untreated males. Although the untreated females mated with the 200 Gy-irradiated males laid eggs, no eggs did not hatch. The 200 Gy-irradiated males were then applied to untreated male and female flies in a density ratio of 1:9 (untreated males : treated males). The laid eggs suffered significant infertility. These results suggest that electron beam-irradiated pupae at 200 Gy resulted in male sterility and the resulting males would be applied to SIT.

Technique and Type of Line Expression in Goryeo Dynasty Metal Craft Engraving (고려시대 금속공예 선각(線刻)기법의 기술과 유형)

  • Kim, Serine
    • Korean Journal of Heritage: History & Science
    • /
    • v.53 no.3
    • /
    • pp.24-41
    • /
    • 2020
  • The engraved line expression in metal crafts is a detailed technique of carving or decorating metal surfaces. This technique engraves a line using a tool on the surface of a metal craft. This technique was used extensively in articles made of various metal materials during the Goryeo Dynasty, and the range of patterns that could be expressed and the width of users was wide. In this paper, based on relics and literature, the concept of line representation of this engraving technique used in the metal crafts of the Goryeo Dynasty and the perceptions and terms of the Goryeo Dynasty were examined. In addition, the users engaged in this craft and the specific patterns and patterns of decoration were reviewed. Through these means, it was possible to confirm various aspects of a technique that was thought previously to involve just simple expression of lines using tools. In addition, through the literature, Geumseokmun Gate, and relics currently being transmitted, it was possible to confirm the utilization patterns of techniques used in various types of objects. Various uses have led to the combination with other metal craft techniques that were popular at the time, and while utilizing unique characteristics of the techniques, this maximized the molding of various patterns. In the meantime, it is true that the intaglio technique in metal crafts has not received much attention compared to the decoration techniques of other metal crafts, such as inlay, embossing, and openwork techniques in which decorative effects are maximized due to the recognition that the technique was used so widely in relics. However, the universality of the technique is premised on its wide use across all eras. As such, it was used in metal craft relics that reflect the various cultural characteristics of Korea and various cultural aspects that are currently passed down. On the one hand, technology has been passed down as a form of intangible heritage that embodies a longstanding craft culture which continues to the present in the fields of sculpture and intangible cultural properties. As such, the universality of Seongak contains many cultural meanings. In addition, the uniqueness of the technique is distinct, and it is deeply related to Goryeo, who was in charge of the use of technology and craftsmanship of the Joseon Dynasty and the metal craft technology that is currently handed down. I think research on future techniques should be continued in depth.