• 한국수자원학회논문집
• /
• 제43권1호
• /
• pp.81-94
• /
• 2010

본 연구는 인공신경망의 성능을 향상시키기 위한 여러 가지 방법들 중의 하나인 입력변수 선정기법에 관한 연구로서, 일반적으로 널리 사용되고 있는 상관계수를 이용한 입력변수 선정기법 외에 상호정보량을 활용한 방법을 적용하여 인공신경망의 성능을 향상시키고자 하였다. 대상자료는 기상청에서 제공하는 RDAPS자료의 152개 출력값으로 지상강우량의 예측값인 APCP를 포함하고 있으며, 강우관측값간의 상호정보량을 구해 가장 영향력이 큰 변수를 입력변수로 사용하였다. 기존연구결과, 그리고 상관계수만을 이용해서 입력변수를 선정한 결과와 비교해볼 때, 상호정보량을 적용한 경우 입력변수는 주로 바람과 관련된 변수들이 선정되었으며, 평균제곱근오차, 평균제곱근상대오차, 그룹별로 구분한 경우의 절대오차, 그리고 구간별로 구분한 경우의 상대오차를 비교한 경과 상호정보량을 이용한 입력변수 선정방법의 정확도가 전반적으로 높은 것으로 나타났으며, 특히 강우량이 상대적으로 큰 경우의 오차를 많이 감소시킬 수 있는 것으로 나타났다.

• 농업과학연구
• /
• 제48권4호
• /
• pp.1051-1065
• /
• 2021

Recent times have seen sustained increases in genetically modified (GM) crops not only for cultivation but also for the utility of food and feed worldwide. Domestically, commercial planting and the accidental or unintentional release of living modified (LM) crops into the environment are not approved. Many detection methods had been devised in an effort to realize effective management of the safety of agricultural genetic resources. In order to develop event-specific polymerase chain reaction (PCR) markers for LM crops, we analyzed the genetic information of LM crops. Genetic components introduced into crops are of key importance to provide a basis for the development of detection methods for LM crops. To this end, a total of 18 varieties from four major LM crop species (maize, canola, cotton, and soybeans) were subjected to an analysis. The genetic components included introduced genes, promoters, terminators and selection markers. Thus, if proper monitoring techniques and single or multiplex PCR strategies that rely on selection markers can be established, such an accomplishment can be regarded as a feasible solution for the safe management of staple crop resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.921-940
• /
• 2015

In this paper, we investigate the multi-resource allocation problem, a unique feature of which is that the multiple resources can compensate each other while achieving the desired system performance. In particular, power and time allocations are jointly optimized with the target of energy efficiency under the resource-limited constraints. Different from previous studies on the power-time tradeoff, we consider a multi-server case where the concurrent serving users are quantitatively restricted. Therefore user selection is investigated accompanying the resource allocation, making the power-time tradeoff occur not only between the users in the same server but also in different servers. The complex multivariate optimization problem can be modeled as a variant of 2-Dimension Bin Packing Problem (V2D-BPP), which is a joint non-linear and integer programming problem. Though we use state decomposition model to transform it into a convex optimization problem, the variables are still coupled. Therefore, we propose an Iterative Dual Optimization (IDO) algorithm to obtain its optimal solution. Simulations show that the joint multi-resource allocation algorithm outperforms two existing non-joint algorithms from the perspective of energy efficiency.

• 정보관리연구
• /
• 제28권4호
• /
• pp.59-75
• /
• 1997

이 글은 전자잡지의 선정, 예산, 정책결정, 장서평가, 보존 등 전자잡지에 관한 장서관리문제를 소개 분석하고 있다. 전자잡지와 관련한 직원과 예산이 주제별 접근방식이나 형태별 접근방식에 따라, 또는 이 두 접근방식을 병행하여 조직될 수 있다고 주장하고 있다. 전자잡지는 인쇄형태 잡지와 마찬가지로 자료식별, 평가, 선정이라는 3단계과정을 거쳐 선정된다. 전자잡지는 인쇄형태잡지에 적용되는 전통적 기준뿐만 아니라 또 다른 기준이 추가로 적용된다. 이 글은 전자잡지의 구독취소와 제적을 언급하고 있지 않지만, 그 중요성은 증가할 것이다. 잡지의 소유권보다는 이용가능성과 접근가능성에 중점을 둔 새로운 이용자위주 평가 방법기법에 대한 요구가 일고 있다.

• 한국도서관정보학회지
• /
• 제45권4호
• /
• pp.45-65
• /
• 2014

이 연구에서는 국립중앙도서관이 구축 및 운영하는 웹 아카이브 OASIS 콘텐츠의 특성과 현황을 살펴보았다. 2013년 12월-2014년 11월 OASIS에 공개된 웹사이트 55,581건의 수량적 성장과 주제 분포, '최신 수집자료'의 아카이빙 현황 등을 검토하였다. 급격한 수량적 성장에도 불구하고, '사회과학'(63.6%)에 집중한 주제 편향성, '정치학'(34.7%. 2003년 전체의 21.4%)의 과도한 편중, '최신 수집자료'의 저작자 권위 및 학술적 가치의 근거 미약, 웹사이트와 인스턴스의 혼용에 따른 통계의 중복 및 부정확성 등 문제점이 다시 확인되었다. 양적 성장에 동반하지 않는 질적 수준 문제가 지속되며, 시급한 수집정책 개선과 품질제어가 필요한 것으로 나타났다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2001년도 추계학술대회 논문집
• /
• pp.150-153
• /
• 2001

The selection of the optimal partners in supply chain management is one of the most critical success factors. In the past, partners for outsourcing production were selected repeatedly within a closed group of candidates due to the limited information and location of partners. But, the wide use of internet and the development of electronic commerce make it possible that the partners capable of providing the optimal services are selected regardless of their location or nationality. And the concept of partners was limited to the provider of production resources. In the supply chain management, the concept should be extended to the provider of transportation and warehouse due to the high portion of transportation cost among the total production cost Therefore, In this study, we propose an analytical approach to the selection of Production and transportation partners in supply chain management. For this purpose a mathematical model is developed, and then a heuristic algorithm based on tabu search is presented since the model belongs to the NP hard problem.

• 기록학연구
• /
• 제12호
• /
• pp.37-80
• /
• 2005

Archival appraisal has been a significant field and demanding task in thoughts and practice about modern archive, in particular, because of insufficiency of resources for the preservation in comparison with the large scale of recorded information. Appraising records does naturally go with the selecting and acquiring them. In the field of appraisal, however, comprehensive accountability on appraisal is much more important than selection and acquisition. The purpose of this study is the proposition of the theoretic approach to the analysis of the factors concerning the archival appraisal. For this purpose, I would try not the actual practice of the archival appraisal but theoretical categories of archival appraisal decision. The archival Characteristic, Value, and Context will be proposed as theoretical categories for the analysis of archival appraisal decision. Firstly, Characteristic category makes it clear to identify the reliable and authentic records, and then, Value provides us with elucidation about the appraisers' recognition of values. Lastly, Context explains the priority of selection throughout creating, using, interrelationship, and social meaning of archives.

• Plant Resources
• /
• 제5권2호
• /
• pp.118-123
• /
• 2002

In order to obtain the genetic information on the quantitative characters of black seeded soybeans, which would be needed to improve selection efficiency for breeding high yielding genotype, 45 varieties of black seeded soybeans collected in Chonnam, Korea were grown and variations of several important characters were observed. Heritability of each observed character, phenotypic and genotypic correlations among the characters and contribution of each yield component on grain yield through path coefficient analysis were estimated. Both number of pods per plant and 100-seed weight showed not only high heritability but also highly significant phenotypic and genotypic correlation with seed yield, and hence it was desirable to select plants with more number of pods per plant and higher 100-seed weight than raise seed yield of black seeded soybeans collected in Chonnam. In addition, number of pods per and 100-seed weight were proved to be the most influential variables on the viability of seed yield by path coefficient analysis. Since these showed the high heritability of number of pods per plant, selection of plants with higher 100-seed weight would be more efficient for breeding high yielding genotype.

• 대한전자공학회논문지TC
• /
• 제49권6호
• /
• pp.39-47
• /
• 2012

차세대 무선통신 시스템에서 다중 경로 페이딩의 영향을 효율적으로 감소시키기 위한 방법으로 최근 협력통신 시스템이 각광을 받고 있다. 협력통신 시스템은 정보를 전송하기 위해서 다양한 페이딩 계수를 가지고 있는 협력 릴레이를 사용하기 때문에, 모든 릴레이를 협력통신에 참여 시키는 것은 자원의 낭비를 초래한다. 그러므로 무선자원을 효율적으로 사용하기 위해서는 최적의 릴레이를 선택적으로 사용할 필요가 있다. 본 논문에서는 무선 협력통신 네트워크에서 발생하는 이러한 문제를 해결하기 위하여 Q-Learning 알고리즘을 이용한 협력 릴레이 선택 기법을 제안한다. Q-Learning에서는 자가 학습을 위해서 상태, 행동, 그리고 보상에 대한 파라미터를 정의한다. 이러한 파라미터가 잘 정의 될 때 Q-Learning을 이용하여 우수한 통신 성능을 얻을 수 있다. Q-Learning 알고리즘의 우수성을 보이기 위해서, 수학적인 분석을 통해서 최적의 협력 릴레이를 얻는 기법과 통신 성능을 비교하였다. 모의실험 결과, 제안된 기법에서 Q-Learning 알고리즘 내의 보상을 주는 방식에 따라, 비교 기법과 유사한 심벌오율 성능을 얻으면서 보다 더 적은 협력 릴레이를 선택하는 것을 보였다. 따라서 본 논문에서 제안된 기법은 다수의 릴레이를 사용하는 차세대 무선통신 시스템의 성능 향상을 위한 좋은 접근 방식의 하나로 판단된다.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.