• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 2002년도 추계학술대회
• /
• pp.289-312
• /
• 2002

This study suggests the Link weight analysis approach to choose input variables and an integrated model to make more accurate bankruptcy prediction model. the Link weight analysis approach is a method to choose input variables to analyze each input node's link weight which is the absolute value of link weight between an input nodes and a hidden layer. There are the weak-linked neurons elimination method, the strong-linked neurons selection method in the link weight analysis approach. The Integrated Model is a combined type adapting Bagging method that uses the average value of the four models, the optimal weak-linked-neurons elimination method, optimal strong-linked neurons selection method, decision-making tree model, and MDA. As a result, the methods suggested in this study - the optimal strong-linked neurons selection method, the optimal weak-linked neurons elimination method, and the integrated model - show much higher accuracy than MDA and decision making tree model. Especially the integrated model shows much higher accuracy than MDA and decision making tree model and shows slightly higher accuracy than the optimal weak-linked neurons elimination method and the optimal strong-linked neurons selection method.

• 산업공학
• /
• 제16권spc호
• /
• pp.14-20
• /
• 2003

This paper presents a multi-criteria decision model and Multi-Criteria Generic Algorithm(MCGA) approach to improve backbone topology by leveraging the Virtual Link(VL) system in an hierarchical Link-State(LS) routing domain. Given that the sound backbone topology structure has a great impact on the overall routing performance in an hierarchical LS domain, the importance of this research is evident. The proposed decision model is to find an optimal configuration of VLs that properly meets two-pronged engineering goals in installing and maintaining VLs: i.e., operational costs and network reliability. The experiment results clearly indicates that it is essential to the effective operations of hierarchical LS routing domain to consider not only engineering aspects but also specific benefits from systematical layout of VLs, thereby presenting the validity of the decision model and MCGA.

• 대한가정학회지
• /
• 제47권4호
• /
• pp.111-119
• /
• 2009

The purpose of this study was to examine the moderating effect of self esteem on the link between social support(e.g. from family, friends and significant others) and career decision-making level of youth in residential care. Data for this study were collected from 14 nationwide institutions between June 10th to June 20th, 2008. Selfreporting surveys were employed to gather information from 412 sources within these institutions. Collected data were analyzed by SPSS program(12.0). The results were as follows: Stepwise multiple regression showed that self-esteem could be used to predict career decision-making level($\beta$ = -.262, p < .001). Furthermore, self-esteem had a moderating effect on the relationship between social support and career decision-making level($\beta$ = -.749, p < .001). Specifically, self-esteem and the scale of social support from family, friedns or significant others had a moderating effect on career decision-making level($\beta$ = - .118, p < .001). The implication of these findings on career decision-making intervention of youth in residential care and future research priorities are discussed.

• 지능정보연구
• /
• 제7권2호
• /
• pp.19-33
• /
• 2001

본 연구에서는 부도예측용 인공신경망의 입력노드 선정을 위한 휴리스틱으로 연결강도분석접근법을 제안한다. 연결강도분석은 학습이 끝난 인공신경망에서 입력노드와 은닉노드를 연결하는 연결가중치의 절대값 즉, 연결강도를 분석하여 입력변수를 선정하는 접근법으로, 선정기준에 따라 약체연결뉴론제거법과 강체연결뉴론선택법을 들 수 있다. 본 연구에서는 약체연결뉴론제거법, 강체연결뉴론선택법 그리고 이 두 기법을 통합한 통합 연결강도 모형을 제안하여 각각 의사결정트리 및 다변량판별분석에 의해 선정된 입력변수를 이용한 인공신경망 모형과 예측율을 비교한다. 실험 결과 본 연구에서 제안하고 있는 방법론이 의사결정트리나 다변량판별분석 기법보다 높은 예측율을 보여주었다. 특히 두 기법의 통합연결강도 모형의 경우에는 다른 단일 기법보다 높은 예측율을 보이고 있다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권1호
• /
• pp.30-39
• /
• 2007

기존의 내용기반 스팸메일 분류는 전자메일이 이미지를 많이 가지고 있고 텍스트는 적게 가지고 있을 경우에는 내용을 분석하기 어려우므로 스팸메일을 분류하는 데 한계가 있다. 이와 같은 문제를 해결하기 위하여 본 논문에서는 전자메일의 구조를 분석하는 링크구조분석 스팸메일 분류 알고리즘을 제안한다. 이것은 전자메일 안의 하이퍼링크의 개수와 하이퍼링크가 가리키는 웹 문서들이 다른 웹 문서에 의해 링크된 수를 측정하여 전자메일의 중요도를 계산한 후 의사결정트리를 학습하여 스팸메일과 정상메일을 분류한다. 또한 위의 링크구조분석 알고리즘과 하이퍼링크의 서버 주소만을 이용한 변형된 링크구조 분석 알고리즘, 그리고 SVM(support vector machine)을 이용한 내용기반 방법을 다수결 원칙으로 결합한 통합 스팸메일 분류 시스템을 제안한다. 실험 결과, 제안한 링크구조분석 알고리즘은 기존의 내용기반 방법 보다 스팸메일 분류 정확도가 94.8%로 약간 향상되었으며 또한 통합 스팸메일 분류 시스템도 내용기반 방법과 비교하여 향상된 97.7%를 나타냈다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.2095-2110
• /
• 2015

This paper presents a design for a throughput-efficient online relay selection scheme for dual-hop multi-relay cooperative networks. Problems arise with these networks due to unpredictability of the relaying link quality and high time-consumption to probe the dual-hop link. In this paper, we firstly propose a novel probing and relaying protocol, which greatly reduces the overhead of the dual-hop link estimation by leveraging the wireless broadcasting nature of the network. We then formulate an opportunistic relay selection process for the online decision-making, which uses a tradeoff between obtaining more link information to establish better cooperative relaying and minimizing the time cost for dual-hop link estimation to achieve higher throughput. Dynamic programming is used to construct the throughput-optimal control policy for a typically heterogeneous Rayleigh fading environment, and determines which relay to probe and when to transmit the data. Additionally, we extend the main results to mixed Rayleigh/Rician link scenarios, i.e., where one side of the relaying link experiences Rayleigh fading while the other has Rician distribution. Numerical results validate the effectiveness and superiority of our proposed relaying scheme, e.g., it achieves at least 107% throughput gain compared with the state of the art solution.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1338-1341
• /
• 2004

In this paper, we have proposed a new approach of routing and wavelength assignment algorithms, called Possible Available Wavelength (PAW) algorithm. The weight of a link is used as the main factor for routing decision in PAW algorithm. The weight of a link is defined as a function of hop count and available wavelengths. This function includes a determination factor of the number of wavelengths that are being used currently and are supposed to be available after a certain time. The session requests from users will be routed on the links that has the greatest number of link weight by using Dijkstra's shortest path algorithm. This means that the selected lightpath will has the least hop count and the greatest number of possible available wavelengths. The impact of proposed link weight computing function on the blocking probability and link utilization is investigated by means of computer simulation and comparing with the traditional mechanism. The results show that the proposed PAW algorithm can achieve the better performance in terms of the blocking probability and link utilization.

• 한국항해학회지
• /
• 제12권1호
• /
• pp.113-136
• /
• 1988

Decision Science or Decision Analysis can be described as a scientific methodolog to provide suitable quantitative information for the decision maker to be able to selected the best feasible alternative on the given decision environment and thus we can say that where there are decision problems, there needs the decision analysis to be applied to them. International shipping is generally said to be the cheapest and most widely used means of transport in international trade and each of the hundreds of seaport. So far as the decision makings in the shipping and port transportation are concerned, of real importance is to understand what the decision problems in each of shipping and port transportation really are and to recognize the meaning of relevance between shipping and seaport in the outworn phrase, that is to say, "The chain is as strong as its weakest link." This paper is intended to present a literature survey on the applied decision analysis to shipping and port transportation problems which have actually been involved in the wide variety of decision environment. At first, the author suggests four divisional framework such as decision analysis in each field of Shipping Economics, Management and Operations of Shipping, Port Economics, and Port Operation and Management, according to the main concern of the decision environment, and then the literature surveys on those four major divisions are described including the problems and solution approaches in each case. The author concludes the paper with the comment on the need of joint research around this area by citing the phrase of "a process of updating the decision makers' intuitions."s' intuitions."quot;

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.620-621
• /
• 2015

In this study, the multi-criteria decision-making model based on Quality Function Deployment Method is proposed. Multicriteria decision-making is an attempt to link QFD method with the TOPSIS. By this effort, a model that makes client's decision-making more rational and objective in design phase is suggested. The multi-criteria decisionmaking model confirming to the Owner's requirements will improve the productivity of the construction industry and the satisfaction of the customer. Further study extending the range of the requirements, not only the Owner's requirement will be necessary to cover the various factors as much as possible. And then, finally as a flexible platform to achieve a sustainable quality management, web-based multi-criteria decision-making model can be utilized by the relevant stakeholders simultaneously with the feed-back and sharing the necessary informations.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.982-985
• /
• 2000

This paper presents channel estimation of an asynchronous W-CDMA reverse link using the interpolation and moving average algorithm in frequency-selective Rayleigh fading channel. The proposed algorithm is an interpolated decision-directed (IDD) block-wise moving average (BWMA) algorithm. The IDD-BWMA algorithm performs two- stage processes. The first stage performs data decision to make a virtual pilot channel by using linear interpolation channel estimation scheme. Then, the second stage performs the channel estimation of the “block-wise moving average” type by using a virtual pilot channel obtained in the first stage. By using Monte-Carlo computer simulations, we show that the proposed channel estimator is superior to other estimation schemes such as the WMSA(K=1) and DD-RAKE at higher Doppler frequencies, especially.