본문 바로가기
HOME> 저널/프로시딩 > 저널/프로시딩 검색상세

저널/프로시딩 상세정보

권호별목차 / 소장처보기

H : 소장처정보

T : 목차정보

Neurocomputing 15건

  1. [해외논문]   Wavelet fuzzy cognitive maps   SCIE SCOPUS

    Wu, K. , Liu, J. , Chi, Y.
    Neurocomputing v.232 ,pp. 94 - 103 , 2017 , 0925-2312 ,

    초록

    Fuzzy cognitive maps (FCMs) are fuzzy influence graphs which consist of concepts and weighted edges. Various transfer functions have been applied in modelling and simulating the dynamic system of FCMs. In FCMs, transfer function is used to bound the expression level of nodes to a certain range. Therefore, in this paper, we first use wavelet transfer function, and then combine it with FCMs to form wavelet FCMs (WFCM). The wavelet function is a kind of local functions that has limited duration and an average value of zero. Then, we conduct comprehensive analyses over existing transfer functions using synthetic data, real data and pattern classification problems. Finally, according to analysis, a new method involving the selection of transfer functions in the optimization process for pattern classification problems is proposed. The experimental results demonstrate the effectiveness of the proposed method. Still, findings show how the existing functions offer different capacities to deal with both problems.

    원문보기

    원문보기
    무료다운로드 유료다운로드

    회원님의 원문열람 권한에 따라 열람이 불가능 할 수 있으며 권한이 없는 경우 해당 사이트의 정책에 따라 회원가입 및 유료구매가 필요할 수 있습니다.이동하는 사이트에서의 모든 정보이용은 NDSL과 무관합니다.

    NDSL에서는 해당 원문을 복사서비스하고 있습니다. 아래의 원문복사신청 또는 장바구니담기를 통하여 원문복사서비스 이용이 가능합니다.

    이미지

    Fig. 1 이미지
  2. [해외논문]   Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets   SCIE SCOPUS

    Salmeron, J.L. , Rahimi, S.A. , Navali, A.M. , Sadeghpour, A.
    Neurocomputing v.232 ,pp. 104 - 112 , 2017 , 0925-2312 ,

    초록

    Rheumatoid Arthritis (RA) is a chronic autoimmune disease that affect joints and muscles, and can result in noticeable disruption of joint structure and function. Early diagnosis of RA is very crucial in preventing disease's progression. However, it is a complicated task for General Practitioners (GPs) due to the wide spectrum of symptoms, and progressive changes in disease's direction over time. In order to assist physicians, and to minimize possible errors due to fatigued or less-experienced physicians, this study proposes an advanced decision support tool based on consultations with a group of experienced medical professionals (i.e. orthopedic surgeons and rheumatologists), and using a well-known soft computing method called Fuzzy Cognitive Maps (FCMs). First, a set of criteria for diagnosis of RA, based on previous studies and consultation with medical professionals have been selected. Then, Particle Swarm Optimization (PSO) and FCMs along with medical experts' knowledge were used to model this problem and calculate the severity of the RA disease. Finally, a small-scale test has been conducted at Shohada University Hospital, Iran, for evaluating the accuracy of the proposed tool. Accuracy level of the tool reached to 90% and the results closely matched the medical professionals' opinions. Considering obtained results in real practice, we believe that the proposed decision support tool can assist GPs in an accurate and timely diagnosis of patients with RA. Ultimately, the risk of wrong or late diagnosis will be diminished, and patients' disease may be prevented from moving through the advanced stages.

    원문보기

    원문보기
    무료다운로드 유료다운로드

    회원님의 원문열람 권한에 따라 열람이 불가능 할 수 있으며 권한이 없는 경우 해당 사이트의 정책에 따라 회원가입 및 유료구매가 필요할 수 있습니다.이동하는 사이트에서의 모든 정보이용은 NDSL과 무관합니다.

    NDSL에서는 해당 원문을 복사서비스하고 있습니다. 아래의 원문복사신청 또는 장바구니담기를 통하여 원문복사서비스 이용이 가능합니다.

    이미지

    Fig. 1 이미지
  3. [해외논문]   A two-stage model for time series prediction based on fuzzy cognitive maps and neural networks   SCIE SCOPUS

    Papageorgiou, E.I. , Poczeta, K.
    Neurocomputing v.232 ,pp. 113 - 121 , 2017 , 0925-2312 ,

    초록

    This paper proposes a two-stage prediction model, for multivariate time series prediction based on the efficient capabilities of evolutionary fuzzy cognitive maps (FCMs) enhanced by structure optimization algorithms and artificial neural networks (ANNs). In the first-stage, an evolutionary FCM is constructed automatically from historical time series data using the previously proposed structure optimization genetic algorithm, while in the second stage, the produced FCM defines the inputs in an ANN which next is trained by the back propagation method with momentum and Levenberg-Marquardt algorithm on the basis of available data. The structure optimization genetic algorithm for automatic construction of FCM is implemented for modeling complexity based on historical time series data, selecting the most important nodes (attributes) and interconnections among them thus providing a less complex and efficient FCM-based model. This model is used next as input in an ANN. ANNs are used at the final process for making time series prediction considering as inputs the concepts defined by the produced FCM. The previously proposed structure optimization genetic algorithm for FCM construction by historical data as well as the ANN have been already proved their efficacy on time series forecasting. The performance of the proposed approach is presented through the analysis of multivariate historical data of benchmark datasets for making predictions. The multivariate analysis of historical data is held for a large number of input variables, like season, month, day or week, holiday, mean and high temperature, etc. The whole approach was implemented in an intelligent software tool initially deployed for FCM prediction. Through the experimental analysis, the usefulness of the new two-stage approach in time series prediction is demonstrated, by calculating seven prediction performance indicators which are well known from the literature.

    원문보기

    원문보기
    무료다운로드 유료다운로드

    회원님의 원문열람 권한에 따라 열람이 불가능 할 수 있으며 권한이 없는 경우 해당 사이트의 정책에 따라 회원가입 및 유료구매가 필요할 수 있습니다.이동하는 사이트에서의 모든 정보이용은 NDSL과 무관합니다.

    NDSL에서는 해당 원문을 복사서비스하고 있습니다. 아래의 원문복사신청 또는 장바구니담기를 통하여 원문복사서비스 이용이 가능합니다.

    이미지

    Fig. 1 이미지
  4. [해외논문]   Causal effect analysis for fuzzy cognitive maps designed with non-singleton fuzzy numbers   SCIE SCOPUS

    Dodurka, M.F. , Yesil, E. , Urbas, L.
    Neurocomputing v.232 ,pp. 122 - 132 , 2017 , 0925-2312 ,

    초록

    In this study, a new static analysis approach is proposed for enhanced Fuzzy Cognitive Maps (FCMs), which have non-singleton fuzzy numbers in casual relation strength representation. Cognitive Maps (CMs) are proposed as a type of directed graph that offers a means to model interrelationships or causalities among concepts, and have a clear way to visually represent them. They graphically describe a system in terms of concepts, and causal beliefs, and are powerful graphical tools to represent knowledge of the experts. Fuzzy cognitive maps, which are weighted cognitive maps, are proposed also as graphical modelling technique that follows a reasoning approach similar to processes of human reasoning and human decision-making. In FCMs, the casual relations and its strengths are assigned in a unit interval with a sign. The assigned casual strengths in conventional FCMs are singleton fuzzy (crisp) numbers, and only allow to interpret the effects linguistically but do not represent the uncertainty or ambiguity in causality. In this paper, a new analysis is presented for finding the indirect effects and total effects between the concepts of enhanced FCMs that are represented with non-singleton fuzzy numbers, especially for triangular or trapezoidal fuzzy numbers. Firstly, the mathematical approach about fuzzy numbers and the proposed analysis is presented, then secondly an experimental study on modelling ERP maintenance risks via FCM is presented. The results of the proposed causal effect analysis are discussed for this model and the outcomes are compared with a conventional FCM model where the casual strengths are singleton fuzzy numbers. The results of the experiment show the benefit of using triangular fuzzy numbers when a group of experts are involved in modelling. The uncertainty and varieties between the experts' knowledge are easily captured and the casual effect between the concepts are successfully shown with the presented static analysis.

    원문보기

    원문보기
    무료다운로드 유료다운로드

    회원님의 원문열람 권한에 따라 열람이 불가능 할 수 있으며 권한이 없는 경우 해당 사이트의 정책에 따라 회원가입 및 유료구매가 필요할 수 있습니다.이동하는 사이트에서의 모든 정보이용은 NDSL과 무관합니다.

    NDSL에서는 해당 원문을 복사서비스하고 있습니다. 아래의 원문복사신청 또는 장바구니담기를 통하여 원문복사서비스 이용이 가능합니다.

    이미지

    Fig. 1 이미지
  5. [해외논문]   A framework for static and dynamic analysis of multi-layer fuzzy cognitive maps   SCIE SCOPUS

    Christoforou, A. , Andreou, A.S.
    Neurocomputing v.232 ,pp. 133 - 145 , 2017 , 0925-2312 ,

    초록

    Fuzzy Cognitive Maps (FCMs) have progressively become a well-researched and extensively used set of tools for modeling real-world, complex decision making problems. Despite their fast growth, researchers and modelers are faced with the lack of a framework to analyze such models and help them assess their performance and efficiency. Moreover, when multi-layered FCM (ML-FCM) structures are used, which consist of a rich number of nodes and interconnections organized in different layers, this need becomes imperative. The present paper introduces an integrated analysis framework and a series of steps to gather useful static and dynamic information regarding ML-FCM models, as well as to interpret the corresponding results. The proposed type of analysis provides significant information on the model's complexity, the strength of its nodes and its tendency to promote or inhibit activation levels as a result of the presence of positive or negative cycles. In addition, it offers the means to perform dynamic analysis in the form of what-if scenarios. The framework is described and assessed using real-world problems from the engineering and political decision-making domains, which demonstrate its power and usefulness.

    원문보기

    원문보기
    무료다운로드 유료다운로드

    회원님의 원문열람 권한에 따라 열람이 불가능 할 수 있으며 권한이 없는 경우 해당 사이트의 정책에 따라 회원가입 및 유료구매가 필요할 수 있습니다.이동하는 사이트에서의 모든 정보이용은 NDSL과 무관합니다.

    NDSL에서는 해당 원문을 복사서비스하고 있습니다. 아래의 원문복사신청 또는 장바구니담기를 통하여 원문복사서비스 이용이 가능합니다.

    이미지

    Fig. 1 이미지

논문관련 이미지