• 스마트미디어저널
• /
• 제11권4호
• /
• pp.62-68
• /
• 2022

수산 양식장 질병 감염의 확산을 사전에 차단을 위해서는 양식장의 수질 환경 및 생육 어류의 상태를 실시간 모니터링하면서 어류의 질병을 예측하는 시스템이 필요하다. 어류 질병 예측의 기존 연구는 이미지 처리 기법이 대부분이었으나 최근에는 딥러닝 기법을 통한 질병 예측방법의 연구가 활발히 진행되고 있다. 본 논문에서는 수산 양식장에서 발생할 수 있는 넙치의 질병을 딥러닝 기술로 예측하는 방법에 대한 연구결과를 소개하고자 한다. 이 방법은 양식장에서 수집된 카메라 영상에 데이터 증강과 전처리 포함하여 질병 인식률의 성능을 높인다. 이것을 통해 질병 어류를 조기 발견으로 양식 어업에서 어류 집단 폐사 등 어업 재해를 예방하고 지역 수산 양식장으로 어류의 질병 확산 피해를 줄여 매출액 감소 차단될 것으로 기대한다.

• 한국정보통신학회논문지
• /
• 제26권11호
• /
• pp.1630-1636
• /
• 2022

현재 교통 표지판 인식 기법들은 다양한 날씨, 빛의 변화 등과 같은 외부환경 뿐만 아니라 교통 표지판이 일부 훼손된 경우에는 인식 성능이 저하되는 경우가 발생한다. 따라서 본 논문에서는 이러한 문제점을 개선하기 위하여 홉필드 네트워크와 퍼지 Max-Min 신경망을 이용하여 손상된 교통 표지판의 인식 성능을 개선하는 방법을 제안한다. 제안된 방법은 손상된 교통 표지판에서 특징들을 분석한 후, 그 특징들을 학습 패턴으로 구성하여 퍼지 Max-Min 신경망에 적용하여 1차적으로 교통 표지판의 특징을 분류한다. 1차적 분류된 특징이 있는 학습 영상들을 홉필드 네트워크에 적용하여 손상된 특징을 복원한다. 홉필드 네트워크를 적용하여 복원된 교통 표지판의 특징들을 다시 퍼지 Max-Min 신경망에 적용하여 최종적으로 손상된 교통 표지판을 분류하고 인식한다. 제안된 방법의 성능을 평가하기 위하여 손상된 정도가 다른 다양한 교통 표지판 8개를 적용하여 실험한 결과, 제안된 방법이 퍼지 Max-Min 신경망에 비해 평균적으로 38.76%의 분류 성능이 개선되었다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• 대한한의학원전학회지
• /
• 제35권4호
• /
• pp.97-114
• /
• 2022

Objectives : Background research on the history of Huangbo's taste being written as 'pungent' was undertaken, after which its clinical meaning was examined from the medical perspective that was behind the medicinal's taste designation. Furthermore, through various understandings on the 'pungent' taste within the process of clinical application, the meaning of 'pungent' in Korean medicinal research was re-evaluated. Methods : Description of Huangbo's taste as 'pungent' as written in medical texts were chronologically examined to determine its origin. The clinical meaning of the pungent taste of Huangbo was examined within the broad medical perspective of doctors who were behind these descriptions. Results & Conclusions : The pungent taste of Huangbo was first described by Zhang Yuansu, followed by doctors of the Yishui School such as Li Dongyuan, Wang Haogu, etc., during which such knowledge was established and contributed to recognition of Huangbo's effect as tonifying Kidney deficiency and treatment of fire within water, after reaching the Kidney. Li Dongyuan understood the meaning of Huangbo's pungent taste as eliminating Yin fire and restoring the upward direction, ultimately restoring the general 'Rising-Falling-Floating-Sinking' mechanism within the context of his inner damage treatment. On the other hand, Zhu Danxi interpreted the pungentness of Huangbo based on his understanding of the nature of fire and action towards it. It seems as Huangbo's effects were understood within a relatively narrow frame, application of its pungent taste became vague, which gave rise to criticism by later period doctors, ultimately leading to an ambiguous understanding of the pungent taste of Huangbo.

• Clinical and Experimental Reproductive Medicine
• /
• 제50권1호
• /
• pp.26-33
• /
• 2023

Objective: Human exposure to multiple xenobiotics, over various developmental windows, results in adverse health effects arising from these concomitant exposures. Humans are widely exposed to bisphenol A, and acetaminophen is the most commonly used over-the-counter drug worldwide. Bisphenol A is a well-recognized male reproductive toxicant, and increasing evidence suggests that acetaminophen is also detrimental to the male reproductive system. The recent recognition of male reproductive system dysfunction in conditions of suboptimal reproductive outcomes makes it crucial to investigate the contributions of toxicant exposures to infertility and sub-fertility. We aimed to identify toxicity in the male reproductive system at the mitochondrial level in response to co-exposure to bisphenol A and acetaminophen, and we investigated whether melatonin ameliorated this toxicity. Methods: Male Wistar rats were divided into six groups (n=10 each): a control group and groups that received melatonin, bisphenol A, acetaminophen, bisphenol A and acetaminophen, and bisphenol A and acetaminophen with melatonin treatment. Results: Significantly higher lipid peroxidation was observed in the testicular mitochondria and sperm in the treatment groups than in the control group. Levels of glutathione and the activities of catalase, glutathione peroxidase, glutathione reductase, and manganese superoxide dismutase decreased significantly in response to the toxicant treatments. Likewise, the toxicant treatments significantly decreased the sperm count and motility, while significantly increasing sperm mortality. Melatonin mitigated the adverse effects of bisphenol A and acetaminophen. Conclusion: Co-exposure to bisphenol A and acetaminophen elevated oxidative stress in the testicular mitochondria, and this effect was alleviated by melatonin.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제6권6호
• /
• pp.103-110
• /
• 2016

최근 의료데이터의 유출사고가 빈번히 발생하여 환자의 프라이버시 침해 및 의료기관의 피해가 날로 증가하고 있다. 정부에서는 개인정보보호법등과 같은 법규를 제정하여 이러한 피해사례 예방하고 있다. 이중 의료기관 및 의료데이타에 대한 가이드라인은 보건복지부에서 발표한 '국내 의료기관 개인정보보호 가이드라인' 정도만 발표되어 있다. 환자개인의 민감정보를 포함한 의료데이타를 타의료기관 또는 제3의 연구기관등에 전달이 필요한 경우가 발생한다. 전달하고자 하는 의료 이미지 데이터를 일반적인 이미지파일 (JPG, JPEG, TIFF)의 포맷으로 자료의 교환이 이루어지고 있다. 이와같이 일반적인 이미지 포맷의 파일은 아무런 보호조치가 되어 있지 않아 외부로 유출시에는 파일내에 포함된 환자의 주요 식별정보가 노출되는 위험성이 존재한다. 본 연구에서는 이미지 파일에 대한 광학문자판독기술(OCR)을 적용하고 민감정보가 포함된 이미지파일에 암호화된 모자이크기술을 이용한 마스킹 기법을 도입하여 이러한 위험성을 해결하기 위한 이미지 비식별화 방안을 제시한다.

• 문화기술의 융합
• /
• 제8권3호
• /
• pp.571-580
• /
• 2022

해양침적쓰레기는 유령어업으로 인한 폐어구들로 인해 많은 피해와 쓰레기 추정량 편차 증가 등의 문제를 일으키는 주요 원인이 된다. 본 논문에서는 폐어구 사용량, 유통량, 유실량, 회수량에 대한 실태 파악을 위해 실시간 해양침적쓰레기 감지 인공지능 시스템을 구현하고, 성능 개선을 위한 방법에 대해 연구한다. 실시간 객체인식에 우수한 성능모델인 yolov5모델을 활용하여 시스템을 구현하였고, 성능개선 방법으로는 학습데이터의 '데이터 선별 과정'과 '클래스 세분화' 방법을 적용하였다. 결론적으로 비선별된 데이터셋과 클래스가 세분화된 데이터셋의 객체인식 결과보다 불필요한 데이터를 선별하거나 특징 및 용도에 따라 유사 항목을 세분화 하지 않은 데이터셋의 객체인식 결과는 해양침적쓰레기 인식에 개선된 결과를 보인다.

• 한국소프트웨어감정평가학회 논문지
• /
• 제15권2호
• /
• pp.121-128
• /
• 2019

컴퓨팅 시스템들은 사이버공격에 대한 다양한 취약점을 가지고 있다. 특히 정보화 사회에서 지능화된 다양한 사이버공격은 사회적으로 심각한 문제와 경제적 손실을 초래한다. 전통적인 침입탐지시스템은 오용침입탐지(misuse)기반의 기술로 사이버공격을 정확하게 탐지하기 위해서는 지속적인 새로운 공격 패턴 갱신과 수많은 보안 장비에서 생성되는 방대한 양의 데이터에 대한 실시간 분석을 해야만 한다. 하지만 전통적인 보안시스템은 실시간으로 탐지 및 분석을 통한 대응을 할 수 없기 때문에 침해 사고의 인지시점이 지체되어 많은 피해를 야기할 수도 있다. 따라서 머신 러닝과 빅데이터 분석 모델 기반으로 끊임없이 증가하는 사이버 보안 위협을 신속하게 탐지, 분석을 통한 대응과 예측할 수 있는 새로운 보안 시스템이 필요하다. 본 논문에서는 머신 러닝과 빅데이터 기술을 활용한 IDS 구축 방안을 제시한다.

• 한국중재학회지:중재연구
• /
• 제34권1호
• /
• pp.75-101
• /
• 2024

"ESG management" guides companies to prioritize corporate social responsibility and sustainable development as key management objectives, going beyond mere financial performance pursuits. This approach involves creating a sustainable and robust supply chain by urging companies, acting as 'supply chain managers', to implement ESG management practices alongside their 'supply chain partners'. The domestic business community has been quick to respond to this trend, recognizing that failure to adhere to ESG standards set by organizations such as the EU and SEC could lead to severe repercussions, including exclusion from international trade and reputational damage. POSCO and NAVER, two leading Korean companies, are at the forefront of practicing ESG management effectively. They have both produced and publicly disclosed ESG management reports, showcasing their success in enhancing supply chain ESG management. However, as supply chain managers enforce ESG-related obligations on their suppliers, the likelihood of disputes between the parties may increase. In scenarios where supply chain ESG management leads to conflicts between supply chain managers and suppliers, commercial arbitration emerges as a viable solution for dispute resolution. This method offers several advantages, including the arbitrators' expertise, time and cost efficiency, the binding nature of decisions akin to a court's final judgment, international recognition under the New York Convention, confidentiality, and ample opportunity for parties to be heard. Our analysis focuses on the emerging disputes between supply chain managers and suppliers within the context of supply chain ESG management, particularly examining the cases of POSCO and NAVER. By categorizing the expected types of disputes and assessing the appropriateness of commercial arbitration for their resolution, we highlight the effectiveness of this approach. Furthermore, we propose leveraging the Korean Commercial Arbitration Board's role to enhance the use of arbitration in resolving supply chain ESG disputes, underscoring its potential as a strategic tool for maintaining sustainable and harmonious supply chain relationships.