• Nuclear Engineering and Technology
• /
• 제50권5호
• /
• pp.738-744
• /
• 2018

Fuel failure due to debris is a major cause of failure in pressurized water reactors. Fuel vendors have developed various filtering devices to reduce debris-induced failure and have evaluated filtering performance with their own test facilities and methods. Because of the different test facilities and methods, it is difficult to compare filtering performances objectively. This study presents an improved filtering test and an efficiency calculation method to fairly compare fuel-filtering efficiency regardless of the vendor's filtering features. To enhance the reliability of our evaluation, we established requirements for the test method and had a facility constructed according to the requirements. This article describes the debris specimens, the amount of debris, and the replicates for the proposed test method. A calculation method of comprehensive debris-filtering efficiency using a weighted mean is proposed. The test method was verified by repeated tests, and the tests were carried out using the PLUS7 and 17ACE7 test fuels to calculate the comprehensive debris-filtering efficiencies. The evaluation results revealed that the filtering performance of PLUS7 is better than that of 17ACE7. The proposed method can be used on any kind of debris-filtering devices and is appropriate for use as a standard.

• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.187-192
• /
• 2022

많은 대학교에서 다양한 교과 및 비교과 활동을 통해 학생들의 취업 역량을 향상하기 위해 노력하고 있지만, 취업을 준비하는 학생마다 목표와 하고자 하는 활동이 다르다. 따라서 기존에 획일적이고 종합적으로 제공하고 있는 프로그램이 실제로 학생들에게 적합한지 여부를 판단하기 어려우므로 개인화 추천 시스템의 도입이 필요하다. 본 연구에서는 충북대학교의 모든 학생에게 일괄적으로 제안되고 있는 비교과 프로그램을 학년 및 학과별로 분류하여 제시하는 방법을 제안하였다. 또한, 비교과 프로그램에 참여한 학생의 평점 데이터를 사용하여 협업 필터링 모델 3가지를 구현하고, 성능을 비교해 가장 정확도가 높은 모델로 개인화된 맞춤형 추천을 제안한다.

• 한국컴퓨터정보학회논문지
• /
• 제17권4호
• /
• pp.83-90
• /
• 2012

대규모의 상품을 다루는 전자상거래 시스템에서 개인화된 추천은 필수적인 기능이 되고 있다. 대표적 추천 알고리즘인 협업필터링은 내용기반 추천에 비하여 뛰어난 추천성능을 제공해 주고 있으나, 희박성, 신규 아이템 문제(Cold-start), 확장성 등의 근본적인 한계를 갖고 있다. 본 연구에서는 추가적으로 협업필터링이 목표 대상자에 따라 비일관된 예측 능력의 차이를 보이는 추천 성능의 편차 문제를 제기하고자 한다. 추천성능의 편차는 기존의 Mean Absolute Error(MAE)에 의해서는 측정되기 어려우며 또한 정확도, 재현율 지표와도 독립적으로 평가되고 있다. 협업알고리즘의 정확한 성능평가를 위해서 본 연구에서는 MAE, MAE 편차, 정확도, 재현율을 포괄적으로 평가할 수 있는 확장 성능평가모델을 제안하고 이를 클러스터링 기반 협업필터링에 적용하여 성능을 비교 분석한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1260-1272
• /
• 2024

This paper tackles the prevalent challenges faced by existing tourism route recommendation methods, including data sparsity, cold start, and low accuracy. To address these issues, a novel intelligent tourism route recommendation method based on collaborative filtering is introduced. The proposed method incorporates a series of key steps. Firstly, it calculates the interest level of users by analyzing the item attribute rating values. By leveraging this information, the method can effectively capture the preferences and interests of users. Additionally, a user attribute rating matrix is constructed by extracting implicit user behavior preferences, providing a comprehensive understanding of user preferences. Recognizing that user interests can evolve over time, a weight function is introduced to account for the possibility of interest shifting during product use. This weight function enhances the accuracy of recommendations by adapting to the changing preferences of users, improving the overall quality of the suggested tourism routes. The results demonstrate the significant advantages of the approach. Specifically, the proposed method successfully alleviates the problem of data sparsity, enhances neighbor selection, and generates tourism route recommendations that exhibit higher accuracy compared to existing methods.

• 대한기계학회논문집A
• /
• 제41권2호
• /
• pp.149-156
• /
• 2017

핵연료는 고도의 신뢰성과 안전성이 요구되는 구조물로서 손상유발 이물질이 유입되지 않도록 이물질여과 기구를 포함하고 있다. 핵연료의 이물질여과 성능은 건전성에 가장 중요한 영향 인자로 합리적이고 객관적으로 평가되어야 하는 지표이다. 본 연구에서는 표준 여과효율 성능지수를 수립하고자 가중평균을 이용하여 종합 이물질여과 효율 계산 방법을 제시하였다. 제안된 방법의 적합성을 확인하기 위해 대표 이물질 시편을 선정하고 이물질여과 실험을 통해 가중평균 여과 효율을 산술평균 여과 효율과 비교하였다. 가중평균법은 성능의 변별력을 강화하고자 이물질의 통과 가능 정도를 가중인자로 사용하였다. 부가적으로 이물질 시편의 크기와 여과 기구의 주요 치수에 따른 상용 핵연료의 여과 거동 분석을 수행하였다.

• Computers and Concrete
• /
• 제23권6호
• /
• pp.445-457
• /
• 2019

Cracks are an important distress of concrete bridges, and may reduce the life and safety of bridges. However, the traditional manual crack detection means highly depend on the experience of inspectors. Furthermore, it is time-consuming, expensive, and often unsafe when inaccessible position of bridge is to be assessed, such as viaduct pier. To solve this question, the real-time automatic crack detecting system with unmanned aerial vehicle (UAV) become a choice. This paper designs a new automatic detection system based on real-time comprehensive image processing for bridge crack. It has small size, light weight, low power consumption and can be carried on a small UAV for real-time data acquisition and processing. The real-time comprehensive image processing algorithm used in this detection system combines the advantage of connected domain area, shape extremum, morphology and support vector data description (SVDD). The performance and validity of the proposed algorithm and system are verified. Compared with other detection method, the proposed system can effectively detect cracks with high detection accuracy and high speed. The designed system in this paper is suitable for practical engineering applications.

• 한국측량학회지
• /
• 제30권1호
• /
• pp.39-48
• /
• 2012

수치표고모델(DEM : Digital Elevation Model)을 생성하거나 지상의 객체를 추출하기 위해서 라이다 자료에서 지면점과 비지면점을 분리하는 필터링(filtering) 과정은 중요하다. 본 연구에서는 라이다 자료에서 지면점을 추출하는 데 사용되는 기존의 필터링 방법을 대상으로 정성적 분석과 정량적 분석을 통해 가장 효과적인 필터링 알고리즘을 선정하는 것을 목적으로 하였다. 이를 위해 Adaptive TIN, Perspective Center Based Filtering Algorithm, Elevation Threshold with Expand Window, Progressive Morphology의 4가지 필터링 방법을 산악지역, 도시지역, 건물과 산이 공존하는 3가지 지역에 적용하여 각각의 방법에 대한 특징을 분석하였다. 실험에 사용된 4가지 필터링 방법의 정성적인 비교는 음영기복도를 생성한 후 시각적인 방법을 적용하였고 정량적인 비교는 GPS로 관측한 검사점을 이용한 절대적인 비교와 국토지리정보원의 수치표고모델을 이용하여 상대적인 비교를 수행하였다. 라이다 필터링 실험을 통하여 Adaptive TIN 알고리즘은 산악지역과 도시지역에서 지면점을 가장 효율적으로 추출하였고 건물과 산이 공존하는 지역에서는 Progressive Morphology 알고리즘이 가장 양호한 결과를 나타내었다. 또한 정성적, 정량적 비교 결과 전반적으로 지역적 특성에 관계없이 적용가능한 필터링 알고리즘은 ATIN 알고리즘으로 나타났다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제18권2호
• /
• pp.143-156
• /
• 2014

This paper aims to give a quick view on denoising without comprehensive details. Denoising can be understood as removing unwanted parts in signals and images. Noise incorporates intrinsic random fluctuations in the data. Since noise is ubiquitous, denoising methods and models are diverse. Starting from what noise means, we briefly discuss a denoising model as maximum a posteriori estimation and relate it with a variational form or energy model. After that we present a few major branches in image and signal processing; filtering, shrinkage or thresholding, regularization and data adapted methods, although it may not be a general way of classifying denoising methods.

• BMB Reports
• /
• 제45권2호
• /
• pp.120-125
• /
• 2012

We have developed a biologist-friendly, Java GUI application (GoBean) for GO term enrichment analysis. It was designed to be a comprehensive and flexible GUI tool for GO term enrichment analysis, combining the merits of other programs and incorporating extensive graphic exploration of enrichment results. An intuitive user interface with multiple panels allows for extensive visual scrutiny of analysis results. The program includes many essential and useful features, such as enrichment analysis algorithms, multiple test correction methods, and versatile filtering of enriched GO terms for more focused analyses. A unique graphic interface reflecting the GO tree structure was devised to facilitate comparisons of multiple GO analysis results, which can provide valuable insights for biological interpretation. Additional features to enhance user convenience include built in ID conversion, evidence code-based gene-GO association filtering, set operations of gene lists and enriched GO terms, and user -provided data files. It is available at http://neon.gachon.ac.kr/GoBean/.