دانلود مقاله ISI انگلیسی شماره 52613
ترجمه فارسی عنوان مقاله

سیستم خبره فازی-عصبی مرتبه بالا برای پیش بینی سری ها

عنوان انگلیسی
High-order fuzzy-neuro expert system for time series forecasting
کد مقاله سال انتشار تعداد صفحات مقاله انگلیسی
52613 2013 10 صفحه PDF
منبع

Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)

Journal : Knowledge-Based Systems, Volume 46, July 2013, Pages 12–21

ترجمه کلمات کلیدی
سری زمانی فازی - مرتبه بالا - درجه حرارت - بورس - بازه - ارتباط منطقی فازی - شبکه های عصبی مصنوعی
کلمات کلیدی انگلیسی
Fuzzy time series; High-order; Temperature; Stock exchange; Interval; Fuzzy logical relation; Artificial neural network
پیش نمایش مقاله
پیش نمایش مقاله   سیستم خبره فازی-عصبی مرتبه بالا برای پیش بینی سری ها

چکیده انگلیسی

In this article, we present a new model based on hybridization of fuzzy time series theory with artificial neural network (ANN). In fuzzy time series models, lengths of intervals always affect the results of forecasting. So, for creating the effective lengths of intervals of the historical time series data set, a new “Re-Partitioning Discretization (RPD)” approach is introduced in the proposed model. Many researchers suggest that high-order fuzzy relationships improve the forecasting accuracy of the models. Therefore, in this study, we use the high-order fuzzy relationships in order to obtain more accurate forecasting results. Most of the fuzzy time series models use the current state’s fuzzified values to obtain the forecasting results. The utilization of current state’s fuzzified values (right hand side fuzzy relations) for prediction degrades the predictive skill of the fuzzy time series models, because predicted values lie within the sample. Therefore, for advance forecasting of time series, previous state’s fuzzified values (left hand side of fuzzy relations) are employed in the proposed model. To defuzzify these fuzzified time series values, an ANN based architecture is developed, and incorporated in the proposed model. The daily temperature data set of Taipei, China is used to evaluate the performance of the model. The proposed model is also validated by forecasting the stock exchange price in advance. The performance of the model is evaluated with various statistical parameters, which signify the efficiency of the model.