Hosted by: Dr. Miri Weiss Cohen, Department of Software Engineering, Braude College of Engineering, Karmiel, Israel.
Speaker: Prof. Frederico Gadelha Guimarães, MINDS UFMG, Brazil.
Abstract: Fuzzy Time Series (FTS), introduced in the early 1990s by Song and Chissom, can be viewed as a way to represent time series from the perspective of fuzzy logic. Numerical data is translated into fuzzy sets generating a fuzzy representation of the time series. Then, temporal patterns are extracted according to the number of past observations (lags) that are considered in the model to produce a rule-based knowledge base. The knowledge base is the model that is then used for forecasting. In this talk, I will review the latest developments in FTS methods, including interval and probabilistic forecasting, multivariate forecasting, adaptive and evolving models and hybrid methods. I will also present the pyFTS library, an open source Python library for FTS developed in the MINDS laboratory.
Негізгі бет New developments in fuzzy time series methods
Пікірлер: 1