High-Order Fuzzy Time Series Forecasting by Using Membership Values Along with Data and Support Vector Machine
- PDF / 1,580,307 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 25 Downloads / 183 Views
RESEARCH ARTICLE-COMPUTER ENGINEERING AND COMPUTER SCIENCE
High‑Order Fuzzy Time Series Forecasting by Using Membership Values Along with Data and Support Vector Machine Radha Mohan Pattanayak1 · Sibarama Panigrahi2 · H. S. Behera1 Received: 18 February 2020 / Accepted: 14 June 2020 © King Fahd University of Petroleum & Minerals 2020
Abstract In the past few years, non-stochastic fuzzy time series (FTS) models have drawn remarkable attention of researchers from different domains. Unlike traditional stochastic models, FTS models do not require any strict assumption on the characteristics of data to be modeled and are applicable to time series even with uncertainty. However, the effectiveness of FTS models largely depends on the determination of effective length of interval and modeling of fuzzy logical relationships (FLRs). Motivated by this, in this paper, we have developed a novel method using fuzzy c-means clustering to determine the unequal-length of interval. Additionally, for the first-time membership values are considered while modeling the FLRs using support vector machine (SVM). The order of the model is determined by analyzing the autocorrelation function and partial autocorrelation function of the time series. To measure the accuracy of the proposed model, ten different time series datasets are considered. Four recently developed fuzzy time series forecasting models and two popular crisp time series forecasting models using MLP and SVM are considered for comparative performance analysis. From the experimental result analysis, it is observed that the proposed model outperforms other alternatives and shows statistically better forecasting accuracy based on the popular Wilcoxon signed-rank test; and Friedman and Nemenyi hypothesis test. Keywords Fuzzy time series forecasting (FTSF) · Support vector machine (SVM) · Universe of discourse (UOD) · Length of interval (LOI) · Number of intervals (NOIs)
1 Introduction Fuzzy time series (FTS) has been considered as an interesting and most demanding topic of research in recent time. It has the capability to handle different forecasting issues encountered in our day-to-day life, including temperature forecasting, weather forecasting, stock index forecasting, rainfall forecasting, growth rate forecasting in share market * H. S. Behera [email protected] Radha Mohan Pattanayak [email protected] Sibarama Panigrahi [email protected] 1
Department of Information Technology, Veer Surendra Sai University of Technology, Burla, Odisha 768018, India
Department of Computer Science Engineering and Application, Sambalpur University Institute of Information Technology, Jyoti Vihar, Burla, Odisha 768019, India
2
and many more. While dealing with different forecasting problems, FTS models deal with ambiguous, incomplete and linguistic data. Zadeh [1] proposed the fuzzy set theory and found solutions for problems incorporating human linguistic terms. But in some cases, fuzzy set theory fails when the time series data are a collection of numeric
Data Loading...
