Earticle

제조업 분야에서는 경쟁력 강화를 위하여 다품종 생산으로의 전환이 이루어지고 있으며, 하이브리드 제조 기술이 증가하고 있다. 특히 제조실행시스템과 ERP 등의 도입을 통하여 생산 품질 향상에 많은 노력을 기울이고 있기에, 신속하고 효과적인 관리를 위한 MES 운영이 필요하다. MES는 제품 생산과 관련된 모든 단계를 관리하면 서, 생산 활동에 비효율적인 부분은 개선하고, 공정 변경의 경우에 시스템에 변경 사항을 반영해야 한다. 그러나 대부분의 MES는 시스템 관리자를 통하여 수동적이고, 반복적으로 비효율적인 작업을 계속 하고 있는 상황이다. 본 논문에서는 생산과 관련된 요구사항을 시스템 관리자가 특정 라인의 장비에 대한 참조 정보를, 다른 라인의 동일한 장비에도 일괄 적용할 수 있는 모델을 제안한다. 제안 모델을 통하여 참조 정보의 일괄 적용과 선택 적용의 구분으로 생산 라인에 대한 유연한 대처가 가능할 것으로 기대된다.

In the manufacturing industry, there is a transition to multi-item production for reinforcement of competitiveness. Therefore, the hybrid manufacturing technology is increasing. Especially, many efforts in production quality improvement are made through the adoption of the manufacturing execution system and ERP, so it is necessary to operate MES for prompt and effective management. MES should improve ineffective parts in production activities while managing all stages related to production of products. If there is change in the process, the changed items should be reflected to the system. However, most manufacturing execution systems are operated passively and repetitively by system administrators. This study presents a model that system administrators can comprehensively apply reference information about production related requirements on specific line’s equipment to the same equipment of other lines. The flexible response for application to production lines is possible thanks to the division of blanket application and selective application of reference information through proposed model.

본 연구에서는 딥러닝 기반의 U-Net++ 모형을 활용하여 강우 레이더 예측 모델을 개발하고, 기존의 U-Net 모형과의 성능을 정량적으로 비교하였다. 강우 예측의 성능 평가는 CSI(Critical Success Index)와 RMSE(Root Mean Square Error)를 이용하여 강우 임계치에 따라 선행시간별로 수행되었다. 연구 결과, U-Net++ 모형은 U-Net 모형에 비해 RMSE가 전반적으로 낮아, 양적 예측 성능이 향상되었음을 확인하였다. 반면, CSI의 경우 기존 U-Net 모형이 더 높은 값을 보여 강우 발생 여부 예측에 있어 우수한 성능을 나타냈다. 그러나 임계치가 커지고 선행시간이 증가함에 따라 두 모델 모두 CSI가 감소하고 RMSE가 증가하는 경향을 보였다. 또한, 소양강 유역의 유역 면적 강수량을 지상 강우, 강우 레이더, U-Net++ 모형, 그리고 U-Net 모형을 활용하여 비교하였다. 총 8개의 강우사상을 대상으로 10분 간격으로 누적 유역 면적 강수량을 산정한 결과, U-Net++ 모형은 선행시간이 길어질수록 다소 과대 추정되는 경향이 있었지만, 60분까지의 누적 유역 면적 강수량 예측 성능에서는 U-Net 모형보다 우수함을 보였다. 특히, 강우량이 상대적으로 많은 사상에서 U-Net++ 모형은 지상 강우 및 강우 레이더와의 높은 유사도를 나타내었으며, RMSE 분석에서도 더 낮은 중앙값과 적은 변동성을 보여 예측 성능이 우수함을 확인하였다.

This study developed a rainfall radar nowcasting model using the deep learning based U-Net++ model and quantitatively compared its performance with the U-Net model. Performance evaluation of rainfall prediction was performed by the lead time according to the rainfall threshold using CSI(Critical success index), RMSE(Root Mean Square Error). As a result of the study, it was confirmed that the overall RMSE of the U-Net++ model was lower than that of the U-Net model, and thed quantitative prediction performance of rainfall was improved. On the other hand, in the case of CSI, the existing U-Net model showed a higher value, showing excellent performance in predicting the occurrence of rainfall. However, both models showed a tendency to decrease CSI and increase RMSE as the threshold increased and the lead time increased. In addition, the areal rainfall in the Soyang river basin was compared using ground rainfall, radar data, U-Net model, and U-Net++ model. As a result of calculating cumulative areal rainfall every 10 minutes for a total of 8 rainfall events, the U-Net++ model tended to be slightly overestimated as the lead time increased, but it was shown to be superior to the U-Net model in the cumulative areal rainfall prediction performance up to 60 minutes. In particular, the U-Net++ model showed high similarity to ground rainfall and rainfall and radar data in events with relatively high rainfall, and the RMSE analysis also showed lower median and less variability, confirming excellent prediction performance.

이 연구의 목적은 국립중앙도서관 KOLIS-NET의 단순 키워드 검색창과 패싯 네비게이션의 기능을 검토하고, 개선 방안을 제안하는 것이다. KOLIS-NET에서 '김훈'의 검색 결과 3,702건 중 '발행시기' 패싯의 '2011-2020 (776)' 레코드 그룹을 살펴보았다. 주요한 발견은 다음과 같다: (1) '자료유형', '발행시기', '주제별', '언어' 및 '발행국'의 5개 패싯은 검색 결과 첫 단계만 적용 및 복수 패싯의 교차 미적용; (2) 10년 단위 '발행시기' 패싯에서 개별 발행연도 미식별; (3) KDC의 10개 주류 및 '기타'로 구분된 '주제별' 패싯은 하위 패싯이 없어 주제 구체화 곤란; (4) '자료유형' 패싯의 '일반도서'에서 큰 활자 도서 등 특수 자료유형의 집합과 식별 곤란; (5) 저자 패싯 부재로 저자명으로 집합 및 식별 곤란; (6) '발행시기' 패싯의 '발행년불명', '언어' 패싯의 '언어불명' 및 '주제명' 패싯의 '기타' 그룹은 디스플레이 미작동, 서지 리스트와 개별 레코드 간 이동 불편 등 시스템 기능적 제한점. 이에 따라 원활한 패싯 네비게이션 위한 패싯 간 이동 개선, '발행시기' 패싯의 1년 단위 하위 패싯 및 '주제별' 패싯의 강목류 수준 하위 패싯 구성, 서지 레코드 작성 시 '자료유형표시'의 정확한 입력과 코딩 활용 및 OPAC 디스플레이 조정, 이름표목에 기반한 저자 패싯 추가 등 KOLIS-NET 시스템 기능성 및 레코드의 품질 개선을 제안하였다.

The purpose of this study is to examine and propose to improve the features of a simple keyword search box and faceted navigations of KOLIS-NET operated by the National Library of Korea. A record group of '2011-2020 (776)' under 'Publication date' facet, out of 3,702 records retrieved from a search of '김훈', were examined. Major findings are as follows: (1) Five facets including 'Format', 'Publication date', 'Subject', 'Language' and 'Country' are used to limit search results only in the first step, and multiple facets cannot be simultaneously used; (2) With 'Publication date' facet formed in the span of ten years, a separate publication year cannot be identified; (3) 'Subject' facet based on KDC limits the results only in broad subject classes without sub-facets; (4) Under 'Format' facet, a special format such as large print texts cannot be identified; (5) Without 'Author' facet, authors cannot be identified; and (6) 'Publication date missing', 'Language missing', and 'Miscellaneous subject' record groups cannot be clicked and displayed, a navigation to-and-fro between a brief list and bibliographic records is not smooth, etc. Therefore an application of multiple facets in all stages of limiting the search result, a construction of sub-facets for 'Publication date' and 'Subject' facets, an accurate description and coding of 'General Material Designation', etc. are suggested to improve KOLIS-NET's faceted navigation.

본 연구는 한국 성인의 PTSD 증상을 예측하는 사건(DSM-5 진단기준사건(직접경험), DSM-5 비진단기준 사건(직접경험), 간접경험 사건)을 확인하고자 수행되었다. 이를 위해 국내 성인 1,136명의 자료를 기계학습 기법인 Elastic Net 회귀분석을 통해 분석하였다. 본 연구에서는 DSM-5 진단기준사건(직접경험) 19개, DSM-5 비진단기준사건(직접경험) 17개, 간접경험사건 19개, 총 55개의 사건 경험 여부를 PTSD 증상에 대한 독립변수로 투입하였다. 연구 결과, DSM-5 진단기준사건(직접경험) 6개, DSM-5 비진단기준사건(직접경험) 9개, 간접경험사건 4개, 총 19개의 사건이 PTSD 증상을 예측하는 것으로 나타났다. 본 연구의 결과는 DSM-5 진단기준사건(직접경험)뿐만 아니라 DSM-5 비진단기준사건(직접경험)과 간접경험 사건이 PTSD 증상을 예측할 수 있음을 확인하였다는 것에 의의가 있다.

This study aimed to identify events that predict PTSD symptoms in Korean adults, including DSM-5 diagnostic criteria events(direct experience events), DSM-5 non-diagnostic criteria events(direct experience), and indirect experience events. Data from 1,136 Korean adults were analyzed using the machine learning technique of Elastic Net regression analysis. In this study, a total of 55 events were included as independent variables for PTSD symptoms: 19 DSM-5 diagnostic criteria events(direct experience), 17 DSM-5 non-diagnostic criteria events(direct experience), and 19 indirect experience events. The results showed that 19 events predicted PTSD symptoms, including 6 DSM-5 diagnostic criteria events(direct experience), 9 DSM-5 non-diagnostic criteria events(direct experience), and 4 indirect experience events. The significance of this study lies in confirming that not only DSM-5 diagnostic criteria events(direct experience) but also DSM-5 non-diagnostic criteria events(direct experience) and indirect experience events can predict PTSD symptoms.

환경부에서는 위성영상과 항공영상을 이용하여 토지피복지도를 1998년부터 제작하여 배포하고 있으나, 권역별 제작 주기가 달라 활용성이 저하된다. 이에, 본 연구에서는 항공정사영상과 Landsat 8 위성영상을 이용하여, 토지피복지도를 자동으로 생성하기 위한 연구를 수행하였다. 토지피복지도를 자동적으로 제작하기 위하여 딥러닝 기반 세그먼테이션 방법의 하나인 Residual U-Net을 활용하였다. 토지피복지도의 제작 시기와 가장 근접한 시기의 항공 및 위성영상을 신경망을 통하여 학습하고, 학습결과를 3가지 실험군으로 나누어 토지피복지도와 비교하여 정확도 평가를 수행하였다. 첫 번째 군으로 대분류 7개 전체를 활용한 결과의 경우, 선행연구에서 대분류 4개에만 적용된 결과보다도 향상된 86.6 %의 분류 정확도를 나타내었다. 중분류를 일부 포함한 2개의 실험군의 경우에는 71 %의 정확도를 나타내었다. 본 연구 결과를 바탕으로 신경망을 활용한 대분류 항목에 대한 자동 분류 가능성을 제시하였으며, 중분류 및 세분류에 대한 기초연구로 활용이 가능할 것으로 판단된다.

Land cover maps are derived from satellite and aerial images by the Ministry of Environment for the entire Korea since 1998. Even with their wide application in many sectors, their usage in research community is limited. The main reason for this is the map compilation cycle varies too much over the different regions. The situation requires us a new and quicker methodology for generating land cover maps. This study was conducted to automatically generate land cover map using aerial ortho-images and Landsat 8 satellite images. The input aerial and Landsat 8 image data were trained by Residual U-Net, one of the deep learning-based segmentation techniques. Study was carried out by dividing three groups. First and second group include part of level-II (medium) categories and third uses group level-III (large) classification category defined in land cover map. In the first group, the results using all 7 classes showed 86.6 % of classification accuracy The other two groups, which include level-II class, showed 71 % of classification accuracy. Based on the results of the study, the deep learning-based research for generating automatic level-III classification was presented.

본 논문에서는 알려진 침입방법에 대한 탐지 규칙을 생성하는 정형화된 방법을 제안하였다. 그리고, 변형 공격 등의 다양한 공격 방법에 대응할 수 있도록 퍼지(fuzzy) 이론을 적용한 퍼지 Petri-net을 제안하였다. 침입탐지에서 이용할 탐지 모듈을 생성할 때, 새로운 패턴이 발견될 때마다 입력하여 새로운 모듈을 추가할 수 있도록 하였다. 또한, 침입 탐지의 정확성을 높이기 위해 시스템 호출 로깅 방법을 사용하였다.

In this paper, we ropose formalized method to create detection rules for known intrusion method and the fuzzy Petri-net using fuzzy theory to cope with varied attack. On producing the detection module for using intrusion detection, we can add new found pattern. And also, we use system call logging for increasing correctness of detection.

본 연구에서는 학교폭력 문제해결을 위해 원스톱지원센터로 지정된 CYS-Net과 학교 그리고 Wee프로젝트(위센터와 위클래스) 각 기관들이 학교폭력이라는 공동사안의 해결을 위해 성공적으로 연계해 나가기 위해 필요한 핵심요인들이 무엇인지를 밝히는 데 목적이 있다. 이를 위해 학교폭력 관련업무를 담당한 경험이 있는 CYS-Net(청소년상담복지센터) 현장전문가, 학교의 교사, 그리고 Wee프로젝트의 현장전문가 총 27명을 대상으로 2차례에 나누어 포커스 그룹 인터뷰를 하였고, 수집된 자료는 내용분석방법으로 분석하였다. 분석결과는 학교폭력 관련업무, 연계실태, 연계핵심요인과 제언 4개의 주제로 나뉘며, 학교폭력 관련업무는 ‘현실을 적극 수용하고 자구책 마련하기’, ‘수용과 의뢰’, ‘어설픈 대응과 빨리 마무리짓기’의 3개 하위주제로, 연계실태는 ‘실질적인 업무를 가지고 역할 나누기’, ‘따로 또 같이 만들어나가기’의 2개 하위주제로, 연계핵심요인은, ‘연계의 선순환을 만들어나가는 지속적인 노력 필요’, ‘여전히 너무 먼 그대’의 2개 하위주제로, 제언으로는 ‘성공적인 연계를 위하여’ 1개 하위주제로 구분되며, 총 23개의 하위범주가 도출되었다.

Recently school violence is being a serious issue in Korea. So the government announced ‘Comprehensive measures for the elimination of School Violence’ for a resolution of the problem of school violence. The aim of this study is to understand linkage experiences of field practitioners of CYS-Net, Wee Project and Schools and to analyzed to a couple of linkages of the key success factors and risk factors focus on the status of each inter-agency linkages - CYS-Net, School, Wee Project. Focus group interviews were conducted with 27 practitioners of each agencies and was carried out 2 times. The content were analyzed as 4 themes as the work for school violence solution, linkage state, linkages of the key success factors and risk factors, suggestion. Each themes have 23 sub themes. The results provides implications for linkages for the solution of school violence.

전자상거래 사용자의 폭발적인 증가는 전자상거래 시스템의 급격한 로드 증가와 네트워크 트래픽을 증가시키고 있다. 또한 전자상거래 시스템에서 동영상을 포함한 자료가 점차 늘어나고 있고 이에 따라 인터넷 서비스 제공업자들은 시스템의 관리와 회선의 유지를 위해 막대한 비용을 지불하고 있다. 이러한 시스템의 로드와 네트워크의 트래픽 증가는 웹 고객의 서비스 요청에 대한 응답 속도의 지연을 가져오게 되며 이는 고객만족도를 감소시켜 e-비지니스 기업의 경쟁력을 떨어뜨리는 중대한 요인으로 작용하고 있다. 본 연구에서는 마이크로소프트사의 최신 버전인 닷넷을 기반으로 한 전자상거래 시스템에서, 응답 지연 속도를 개선한 전자상거래 시스템을 설계하고 실험을 통해 성능을 분석하였다. 실험 결과 제안한 시스템은 웹 고객의 다양한 요구에 대해 개선된 응답 속도와 빠른 적응성을 가질 수 있으며, 특히 전자상거래 시스템에 대해 동시에 발생하는 다수의 다중 사용자의 요구로 인해 발생되는 응답 속도의 지연을 막을 수 있을 것으로 기대된다.

A electronic business user is increased rapidly, and load of a electronic business system and network traffic are increased rapidly. Also, the data which included an audio and video is increasing in a electronic business system gradually, and According to this an Internet service businessman is paying for an enormous cost for management of a system and a maintenance of a line. It is brought a delay of a response speed about a service wish of a Web customer this system load and network traffic raise. Also, this decreases customer satisfaction and becomes an important factor to decrease competitive power of an e-business enterprise. In this study, we proposed the electronic business system that improved answer delay time about a Web customer in an e-business system based on the .net which was a the latest version of Microsoft company, and analyzed performance of a proposal system through an experiment. In the experiment result, the system that proposed it can have response time to have been improved and fast adaptability about various requests of a Web customer. Also, in a proposed system, a decrease gets a delay of a response speed to occur because of the multiple user done.

User preferences and ratings may be anticipated by recommendation systems, which are widely used in social networking, online shopping, healthcare, and even energy efficiency. Constructing trustworthy recommender systems for various applications, requires the analysis and mining of vast quantities of user data, including demographics. This study focuses on holding elections with vague voter and candidate preferences. Collaborative user ratings are used by filtering algorithms to provide suggestions. To avoid information overload, consumers are directed towards items that they are more likely to prefer based on the profile data used by recommender systems. Better interactions between governments, residents, and businesses may result from studies on recommender systems that facilitate the use of e-government services. To broaden people's access to the democratic process, the concept of "e-democracy" applies new media technologies. This study provides a framework for an electronic voting advisory system that uses machine learning.

The net income per unit area from crop production could be the most critical consideration for agricultural producers during cultivation planning. This paper proposes a scheme for predicting the net income per unit area based on machine learning and related calculations. This scheme predicts rice production and operation costs by applying climate and price index data. The rice price is also predicted by applying rice production and operation cost data. Finally, these predicted results are employed to calculate the predicted net income, which is compared with the actual net income. Consequently, the proposed scheme shows a meaningful degree of conformity, which indicates the potential of machine learning for predicting various aspects of agricultural production.

이 연구는 국립중앙도서관을 중심으로 전국의 공공도서관들이 소장하고 있는 자료를 구축해 놓은 국가자료종합목록시스템(KOLIS-NET) DB의 품질을 평가하는데 그 목적이 있다. 국가자료 종합목록 DB의 품질평가는 선행연구에서 제시된 품질평가모델을 참조하여 포괄성, 중복성, 최신성, 정확성, 일관성 그리고 완전성의 6개의 항목에 대해 사례에 의한 발견적 평가를 시도하였다 실행모델에 근거한 평가를 통해 국가자료 종합목록 DB의 품질을 종합적으로 검증하고, 품질을 열악하게 만드는 요인을 진단하였으며 KOLIS-NET 종합목록 DB의 품질수준 제고를 위한 개선방안을 평가에서 나타난 구체적 문제점을 중심으로 제시하였다.

The research purpose for this study is to evaluate the quality of the KOLIS-NET DB which builded bibliographic data of the holding collections of nationwide public libraries. The quality evaluation of the KOLIS-NET DB was inspired by the successful experience from researches precedent and tried to approach the case study focuses on six quality dimensions : coverage, duplication. currentness. accuracy, consistency completeness. The study verified comprehensively the quality of the KOLIS-NET DB through a quality evaluation model and analyzed the factors causing such inferior and substandard bibliographic records in the KOLIS-NET DB. Based on the results of the quality evaluation, the quality improvements of the KOLIS-NET DB was suggested.

이 연구는 현재 운영되고 있는 KOLIS-NET의 두 가지 핵심 시스템인 KOLIS-NET 클라이언트 통합형 시스템 과 KOLIS-NET 일반이용자 검색용 시스템 의 품질 수준을 유용성과 사용성의 평가기준을 적용하여 평가하고 개선과제를 제시한 것이다. 'KOLIS-NET 클라이언트 통합형' 시스템의 경우 업무 프로세스별 시스템의 유용성 평가로서, 검색성과 사용용이성, 사용자 지원성을 주된 평가항목으로 설정하였으며, 각각의 평가 항목에 대해 연구팀과 실제 업무를 하고 있는 사서들 간의 브레인스토밍 기법과 심층면담 기법을 통해 평가결과를 도출하였다. 한편 '일반이용자 검색용 시스템' 에 대한 평가는 시스템 사용의 편이성 관점에서 진행되었으며, 다양한 사용성 평가 방법 중에서 인지평가 방법을 사용하였다. 마지막으로 도출된 문제점과 개선 과제를 화면 재설계, 용어 표준화, 기능 개선, 신규 기능의 네 가지로 범주화하여 제시하였다.

This study aims to evaluate KOLIS-NET system by usefulness testing of 'KOLIS-NET client integrated system' and by usability testing of 'KOLIS-NET web site'. For evaluating the usefulness of the system, we used searching, ease of use, customer support as criteria, and used brainstorming and in-depth interview as evaluation method. On the other hand, for usability testing of the web site, we used cognitive walkthrough. Evaluation results are categorized and represented as page redesign, term consistency, function improvement and new functionality.

The Radio Map (RM) stands as a powerful tool in wireless communication and radio regulation. Currently, several RM construction models based on Convolutional Neural Networks (CNNs) have been proposed. However, due to the inherent limitations of vanilla convolutions, capturing distant-range information of the radio propagation environment becomes challenge. Therefore, this letter introduces a novel RM construction model called Distant-range Content interaction Network (DC-Net) and validates its effectiveness using the RadioMapSeer dataset. Experiment results reveal that DC-Net achieves state-of-the-art performance in mapping accuracy for both known and unknown transmitter locations in RM construction.

Critical elements in the China's Lunar Exploration reside in that the lunar rover travels over the surrounding undetermined environment and it conducts scientific exploration under the ground control via teleoperation system. Such an interplanetary transportation mission teleoperation system belongs to the ground application system in deep space mission, which performs terrain reconstruction, visual positioning, path planning, and rover motion control by receiving telemetry data. It plays a vital role in the whole lunar exploration operation and its so-called trustworthy evidence must be assessed before and during its implementation. Taking ISO standards and China's national military standards as trustworthy evidence source, the net assessment model and net assessment method of teleoperation system are established in this paper. The multi-dimensional net assessment model covering the life cycle of software is defined by extracting the trustworthy evidences from trustworthy evidence source. The qualitative decisions are converted to quantitative weights through the net assessment method (NAM) combined with fuzzy analytic hierarchy process (FAHP) and entropy weight method (EWM) to determine the weight of the evidence elements in the net assessment model. The paper employs the teleoperation system for interplanetary transportation as a case study. The experimental result drawn shows the validity and rationality of net assessment model and method. In the final part of this paper, the untrustworthy elements of the teleoperation system are discovered and an improvement scheme is established upon the "net result". The work completed in this paper has been applied in the development of the teleoperation system of China's Chang'e-3 (CE-3) "Jade Rabbit-1" and Chang'e-4 (CE-4) "Jade Rabbit-2" rover successfully. Besides, it will be implemented in China's Chang'e-5 (CE-5) mission in 2019. What's more, it will be promoted in the Mars exploration mission in 2020. Therefore it is valuable to the development process improvement of aerospace information system.

공격 시나리오의 그래프 표현은 서버의 취약성 분석 및 공격의 방어를 위한 설계에 필수적인 방법이다. 이를 위해 다양한 요구사항 분석 모델이 이용되고 있으나, 복잡한 시나리오간의 결합을 표현할 수 있는 모델은 제한적이다. 본 논문에서 제안하는 역할 기반 페트리 넷(Role Based Petri Net)은 동시성과 시각적인 장점을 가진 페트리 넷을 역할 기반으로 구성하여 효과적 표현 모델을 제공하고 알려지지 않은 공격에 대한 시나리오를 효율적으로 표현할 수 있다.

Graph expression of attack scenarios is a necessary method for analysis of vulnerability in server as well as the design for defence against attack. Although various requirement analysis model are used for this expression, they are restrictive to express combination of complex scenarios. Role Based Petri Net suggested in this paper offer an efficient expression model based role on Petri Net which has the advantage of concurrency and visuality and can create unknown scenarios.

Federated learning (FL) enables decentralized model training without sharing data, but most existing methods assume homogeneous model architectures across clients, limiting applicability in heterogeneous real-world environments. We propose FedUNet, a lightweight and architecture-agnostic FL framework that introduces an additive U-Net-inspired module attached to each client’s backbone. By sharing only the compact bottleneck of the U-Net, FedUNet enables efficient knowledge transfer without architectural alignment, shared data, or costly distillation. The encoder?decoder structure with skip connections integrates multi-scale features into a shared latent space, promoting client-invariant representation alignment across heterogeneous models. Experimental results on CIFAR-10 and CIFAR-100 with VGG and ResNet backbones show that FedUNet achieves high accuracy with significantly reduced communication and computational overhead. Notably, a full U-Net attains 93.92% accuracy while requiring only 0.89 MB of communication per round, highlighting its practicality for resource-constrained FL systems.

The degradation of recognition rates in low-light environments is a critical issue in terms of security when using object and face recognition technologies in various locations. Existing low-light enhancement models have shown limitations in terms of computational cost and performance. However, this paper overcomes these limitations. The experimental results demonstrate that our model achieves the same performance as existing models with 13 times lower computational cost and a face detection performance of 82.2%. The structure of this paper is as follows: Introduction, which provides the background and explains the limitations of existing models. Proposed Method, which details the structure and working principles of A4R-Net. Experimental Results, which present the evaluation of low-light enhancement performance and the comparison of face detection using YOLOv4 [1]. Conclusion, which discusses the contributions of this research and future research directions. The source code and dataset is https://github.com/Obiru2698/obiru2698.github.io/

This study was carried out to investigate spectral irradiance characteristics of blue, yellow, and blue-black colored polyethylene (PE) shading net and the effect on growth characteristics and yield in ginseng seedling. The spectral irradiance (μmol/m2/s/㎚) showed the peak at 498 ㎚ in both of blue and blue-black PE shading net, and 606 ㎚ under yellow PE one. The intensity of blue light in blue shading was more strong than that of blue-black shading, control. Blue shading was increased by 17% and 23% in accumulated quantum for daytime, 0.5℃ and 0.2℃ in maximum temperature on June 2 than that of yellow and blue-black shading, respectively, but heat injury ratio of the former was lower than that of the latter. Chlorophyll content and stem length in blue shading were decreased more significantly than those of yellow and blue-black shading. The specific leaf weight was higher under blue and yellow shading than that of blue-black shading. Ginseng seedling harvested in blue shading was increased by 13~17% in the number of root, and 17~20% in root weight per ㎡ compared to yellow and blue-black shading owing to the increase of survived plant, and the decrease of specific leaf weight, heat injury ratio, and stem length.

The mass-spring model has been typically employed in physical-based simulators for clothes or patches. The mass-spring model frequently utilizes equal mass and the gravity factor. The model structure of masses supports a shape applicable to fishing nets. Therefore, to create a simulation model of a fishing net, we consider the mass-spring model and adopt the tidal-current and buoyancy effects in underwater environments. These additional factors lead to a more realistic visualization of fishing-net simulations. In this paper, we propose a new mass-spring model for a fishing-net and a method to simplify the calculation equations for a real-time simulation of a fishing-net model. Our 3D mass-spring model presents a mesh-structure similar to a typical mass-spring model except that each intersection point can have different masses. The motion of each mass is calculated periodically considering additional dynamics. To reduce the calculation time, we attempt to simplify the mathematical equations that include the effect of the tidal-current and buoyancy. Through this research, we expect to achieve a real-time and realistic simulation for the fishing net.