• 제목/요약/키워드: Collaborative training

검색결과 139건 처리시간 0.03초

Prediction of the remaining time and time interval of pebbles in pebble bed HTGRs aided by CNN via DEM datasets

  • Mengqi Wu;Xu Liu;Nan Gui;Xingtuan Yang;Jiyuan Tu;Shengyao Jiang;Qian Zhao
    • Nuclear Engineering and Technology
    • /
    • 제55권1호
    • /
    • pp.339-352
    • /
    • 2023
  • Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

"Belt and Road" and Arbitration Law Teaching and Education System Theory

  • Fuyong, Zhu
    • 한국중재학회지:중재연구
    • /
    • 제30권3호
    • /
    • pp.47-66
    • /
    • 2020
  • Due to the division of China's departmental laws, the disconnect between theory and practice, and the influence of traditional academic thinking on the understanding of the knowledge structure of arbitration legal talents in practice, the construction of law school colleges, teaching teams, and research centers mostly revolves around departmental laws, tearing the connection of the arbitration legal system. The student-centered, process-guaranteed, and result-oriented arbitration master of law training model is "virtualized," the shaping of arbitration professionalism is ignored, the coverage of practical teaching is narrowed, and the arbitration legal profession is mostly formalized. The prevalence of specialized curriculum systems shortage, single faculty, formalized practical teaching, outdated curriculum settings, unsuitable curriculum system design for development, and inaccurate professional curriculum standards and positioning renders it difficult to integrate the "Belt and Road." The cutting-edge, the latest research results, and practical experience cannot reflect the connotation, goals, and requirements of "Entrepreneurship" education, as well as arbitral issues such as the ineffective monitoring of practical education and the inconsistent evaluation of standards and scales. Under the background of the "Belt and Road," based on system theory and practice and through training goals that innovate and initiate organizational form, activity content, management characteristics, assessment and support conditions, etc., the arbitration law teaching curriculum system is gradually improved and integrated. Through the establishment of a "Belt and Road" arbitration case file database and other measures, a complete arbitration law theory and practice teaching guarantee system has been established. Third parties are introduced, arbitration law experimental modules are developed, students are guided how to discover new knowledge, new contents are mastered, solidarity, cooperation, and problem-solving capabilities are cultivated in the practice of the "Belt and Road," and quality education, vocational education, and innovation education are organically integrated. In order to implement the requirements of arbitration law education, innovation development and collaborative management of arbitration law teaching practice base should be cultivated, thus giving full play to the effect of collaborative education between universities and arbitration institutions.

A personalized exercise recommendation system using dimension reduction algorithms

  • Lee, Ha-Young;Jeong, Ok-Ran
    • 한국컴퓨터정보학회논문지
    • /
    • 제26권6호
    • /
    • pp.19-28
    • /
    • 2021
  • 코로나로 인해 건강관리에 대한 관심이 증가하고 있는 요즘, 여러 사람이 함께 이용하는 헬스장이나 공용시설을 이용하는데 어려움이 늘어남에 따라 홈 트레이닝을 하는 이들이 늘어나고 있다. 이에 본 연구에서는 홈 트레이닝 사용자들에게 좀 더 정확하고 의미 있는 운동 추천을 제공하기 위해 개인 성향 정보를 활용한 개인화된 운동 추천 알고리즘을 제안한다. 이를 위해 식습관 정보, 육체적 조건 등 개인을 나타낼 수 있는 개인 성향 정보를 사용해 k-최근접 이웃 알고리즘으로 데이터를 비만의 기준에 따라 분류하였다. 또한, 운동 데이터 셋을 운동의 레벨에 따라 등급을 구별하였으며 각 데이터 셋의 이웃 정보를 바탕으로 모델 기반 협업 필터링 방법 중 차원 축소모델인 특이값 분해 알고리즘(SVD)을 통해 사용자들에게 개인화된 운동 추천을 제공한다. 따라서 메모리 기반 협업 필터링 추천 기법의 데이터 희소성과 확장성의 문제를 해결할 수 있고, 실험을 통해 본 연구에서 제안하는 알고리즘의 정확도와 성능을 검증한다.

통합형디지털참고봉사를 위한 기반 연구: 대학도서관을 중심으로 (A Study on the Preparation for Collaborative Digital Reference Service in Korea University Libraries)

  • 김휘출
    • 한국문헌정보학회지
    • /
    • 제37권2호
    • /
    • pp.169-186
    • /
    • 2003
  • 국내 대부분의 대학도서관이 디지털참고봉사를 제공하고 있지만 그 이용률은 매우 저조하다. 저조한 원인에는 주제전문 사서의 부족, 홍보부족 기타 관리자의 인식부족 둥으로 나타났다. 국내 대학도서관들의 환경에서 이러한 문제를 각 도서관 별로 해결하기는 어렵다. 이를 효과적으로 해결하기 위한 방법으로 각 도서관의 디지털참고봉사를 통합하는 방법을 제기하였다. 디지털참고봉사를 통합하기 위해서는 먼저 주제전문사서 양성, 이용자들이 인지하기 쉬운 인터페이스, 프로그램 개발, 관리기관 설립 등이 필요한데, 이 중에서도 주제전문사서의 양성이 우선적으로 준비되어야 할 것으로 판단된다.

협력적 추천을 위한 사용자와 항목 모델의 효율적인 통합 방법 ((Efficient Methods for Combining User and Article Models for Collaborative Recommendation))

  • 도영아;김종수;류정우;김명원
    • 한국정보과학회논문지:소프트웨어및응용
    • /
    • 제30권5_6호
    • /
    • pp.540-549
    • /
    • 2003
  • 협력적 추천에서는 일반적으로 사용자 모델과 항목 모델이 사용되어진다. 사용자 모델은 사용자들간의 선호도 상관관계를 학습하고, 추천하고자 하는 항목에 대한 다른 사용자들의 선호도를 기반으로 그 항목을 추천한다. 이와 유사한 방식으로 항목 모델은 항목들간의 선호도 상관관계를 학습하고, 다른 항목들간의 선호도를 기반으로 추천 받는 사용자에게 항목을 추천한다. 본 논문에서는 추천 성능의 향상을 위해서 사용자 모델과 항목 모델간의 다양한 통합 방법을 제안한다. 제안하는 통합 방법으로는 순차적, 병렬적 통합 방법, 퍼셉트론 또는 다층 퍼셉트론을 이용한 통합 방법, 퍼지 규칙을 이용한 통합 방법 그리고 BKS를 적용한 방법이다. 본 실험에서는 통합 모델을 위해서 다층 퍼셉트론을 이용하여 사용자와 항목 모델을 각각 학습한다. 다층 퍼셉트론은 최근접 이웃방법이나 연관 규칙을 이용한 방법과 같은 기존의 추천 방법보다 연관된 항목들간의 가중치를 학습할 수 있고, 기호 데이타와 수치 데이타를 쉽게 처리할 수 있는 장점이 있다. 본 논문에서는 통합된 모델이 어떠한 단일 모델보다도 우수하고, 실험을 통하여 다층 퍼셉트론을 이용한 통합 방법이 다른 통합 방법보다 효율적인 통합 방법임을 보여주고 있다.

벤처기업의 외부협력이 경영성과에 미치는 영향 (The Effects of Korean Ventures' External Collaborations on their Performance)

  • 김종운
    • 벤처창업연구
    • /
    • 제7권1호
    • /
    • pp.215-224
    • /
    • 2012
  • 본 연구는 국내 벤처기업들의 외부 협력이 그 협력의 대상 및 협력 내용별로 벤처기업의 경영성과에 미치는 영향을 "벤처기업실태조사" 중 1,567개 벤처기업 자료를 활용하여 실증적으로 분석하였다. 분석 결과, 연구기관과 외국기업과의 협력은 벤처기업의 매출성장에 유의한 정(+)의 영향을 미쳤고, 다른 중소기업과의 협력이 미치는 영향은 유의하지 않은 반면, 대기업과의 협력은 유의하게 부정정인 영향을 끼치는 것으로 나타났다. 그런데, 대기업과의 협력 내용별로는, 공동기술개발 신제품 공동개발은 벤처기업의 경영성과에 매우 유의하게 긍정적인 영향을 미치고, 직원교육훈련 인력교류 및 공동마케팅 해외동반진출도 유의하게 벤처기업 성과에 긍정적인 영향을 미치고 반면, 자금지원 대출알선은 매우 유의하게 벤처기업 성과에 부정적인 영향을 미치고, 기술지도 정보제공 기술이전 및 성과공유제 시행은 유의한 영향을 미치지 못한 것으로 나타났다. 본 연구의 결과는 벤처기업의 혁신능력을 제고시키거나 새로운 시장개척과 관련한 협력 유형이 경영성과에 좋은 영향을 미친다는 것으로, 향후 대 중소기업간 협력정책의 추진방향에 시사점을 주고 있다.

  • PDF

Improving Accuracy and Completeness in the Collaborative Staging System for Stomach Cancer in South Korea

  • Lim, Hyun-Sook;Won, Young-Joo;Boo, Yoo-Kyung
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제15권21호
    • /
    • pp.9529-9534
    • /
    • 2014
  • Background: Cancer staging enables planning for the best treatments, evaluation of prognosis, and predictions for survival. The Collaborative Stage (CS) system makes it possible to significantly reduce the proportion of patients labeled at an "unknown" stage as well as discrepancies among different staging systems. This study aims to analyze the factors that influence the accuracy and validity of CS data. Materials and Methods: Data were randomly selected (233 cases) from stomach cancer cases enrolled for CS survey at the Korea Central Cancer Registry. Two questionnaires were used to assess CS values for each case and to review the cancer registration environment for each hospital. Data were analyzed in terms of the relationships between the time spent for acquisition and registration of CS information, environments relating to cancer registration in the hospitals, and document sources of CS information for each item. Results: The time for extracting and registering data was found to be shorter when the hospitals had prior experience gained from participating in a CS pilot study and when they were equipped with full-time cancer registrars. Evaluation of the CS information according to medical record sources found that the percentage of items missing for Site Specific Factor (SSF) was 30% higher than for other CS variables. Errors in CS coding were found in variables such as "CS Extension," "CS Lymph Nodes," "CS Metastasis at Diagnosis," and "SSF25 Involvement of Cardia and Distance from Esophagogastric Junction (EGJ)." Conclusions: To build CS system data that are reliable for cancer registration and clinical research, the following components are required: 1) training programs for medical records administrators; 2) supporting materials to promote active participation; and 3) format development to improve registration validity.

Improving a newly adapted teaching and learning approach: Collaborative Learning Cases using an action research

  • Lee, Shuh Shing;Hooi, Shing Chuan;Pan, Terry;Fong, Chong Hui Ann;Samarasekera, Dujeepa D.
    • Korean journal of medical education
    • /
    • 제30권4호
    • /
    • pp.295-308
    • /
    • 2018
  • Purpose: Although medical curricula are now better structured for integration of biomedical sciences and clinical training, most teaching and learning activities still follow the older teacher-centric discipline-specific formats. A newer pedagogical approach, known as Collaborative Learning Cases (CLCs), was adopted in the medical school to facilitate integration and collaborative learning. Before incorporating CLCs into the curriculum of year 1 students, two pilot runs using the action research method was carried out to improve the design of CLCs. Methods: We employed the four-phase Kemmis and McTaggart's action research spiral in two cycles to improve the design of CLCs. A class of 300 first-year medical students (for both cycles), 11 tutors (first cycle), and 16 tutors (second cycle) were involved in this research. Data was collected using the 5-points Likert scale survey, open-ended questionnaire, and observation. Results: From the data collected, we learned that more effort was required to train the tutors to understand the principles of CLCs and their role in the CLCs sessions. Although action research enables the faculty to improve the design of CLCs, finding the right technology tools to support collaboration and enhance learning during the CLCs remains a challenge. Conclusion: The two cycles of action research was effective in helping us design a better learning environment during the CLCs by clarifying tutors' roles, improving group and time management, and meaningful use of technology.

재난 탈출 협동 훈련 기능성 게임의 메타버스 플랫폼 구현 (A collaborative Serious Game for fire disaster evacuation drill in Metaverse)

  • 이상호;하규태;김홍석;김시호
    • Journal of Platform Technology
    • /
    • 제9권3호
    • /
    • pp.70-77
    • /
    • 2021
  • 기능성 게임은 사용자에게 재미와 함께 특정한 학습 목표를 달성하기 위한 훈련 또는 교육의 경험을 제공하는 것이다. 본 연구에서는 몰입형 메타버스 플랫폼에서 여러 훈련생과 감독자 들이 서로 실시간 동기화된 자신들의 아바타들 간 협업을 통해 화재 탈출 훈련을 제공하는 기능성 게임을 제안하고 구현하였다. 제작된 시스템 아키텍처는 착용형 동작 센서와 헤드 마운트 디스플레이로 구성되어 메타버스 사이버 공간에서 각 사용자의 의도된 행동을 사용자의 아바타의 동작과 동기화시킨다. 개인화된 착용형 시스템은 사이버 체험 기반의 화재 대피 훈련 시스템에 편리한 사용자 인터페이스와 몰입형 환경을 저렴한 구성 비용으로 제공할 수 있도록 한다. 본 연구의 기능성 게임은 건물의 화재 현장에 대해서만 구현되었으나 제안하는 플랫폼은 공공의 안전을 위한 다양한 재난 상황에 대해 구성을 확장할 수 있다. 본 시스템의 실험 결과를 통하여 제작된 시스템이 화재 탈출에 필요한 능력을 향상시키는 훈련 효과를 검증하였다.

Network Anomaly Traffic Detection Using WGAN-CNN-BiLSTM in Big Data Cloud-Edge Collaborative Computing Environment

  • Yue Wang
    • Journal of Information Processing Systems
    • /
    • 제20권3호
    • /
    • pp.375-390
    • /
    • 2024
  • Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.