Vector quantization based long-term intuitionistic fuzzy time series prediction method

Abstract

The invention discloses a vector quantization based long-term intuitionistic fuzzy time series prediction method. The method includes the steps of A, intuitionistic fuzzification preprocessing of serial data and B, vector quantization based long-term intuitionistic fuzzy time series prediction. A long-term intuitionistic fuzzy time series prediction model built by the method expands single output of the serial data into multiple outputs, a predicated value is converted from a scalar into a vector, and accordingly long-term predication performance of a time series system is improved to a great extent. A sliding window mechanism is introduced into the method, fuzzy change characteristics of the serial data are acquired accurately and rapidly; a discourse domain internal is divided dynamically by the aid of an IFCM (intuitionistic fuzzy C-means) algorithm to be more close to the actual uncertain data distribution; by the aid of vector quantization based long-term time range prediction, the problems of zero matching of intuitionistic fuzzy rules and system error accumulation can be well solved; through example verification and result analysis, the model has good predication performance.

Description

technical field [0001] The invention relates to a long-term intuitive fuzzy time series prediction method based on vector quantization. Background technique [0002] Time series refers to a dynamic data sequence that changes with time and is random and interrelated. Time series analysis is an important application branch of stochastic mathematics. It uses probability theory and mathematical statistics to extract relevant information from sequence historical data. , to reveal the structural characteristics of the time series itself, so as to grasp the correlation law between the sequence data, and use the past value of the sequence to predict and control the future value [1] . Fuzzy time series analysis is a scientific theory that sets sequence variables as fuzzy numbers and uses fuzzy reasoning to predict time series. Because it can better deal with vague and incomplete fuzzy information, the model has strong robustness and compatibility. Fuzzy time series prediction has r...

AI Technical Summary

Problems solved by technology

However, with the maturity of the fuzzy time series forecasting theory, its limitations are gradually emerging: the single membership degree of ordinary fuzzy sets cannot effectively describe and characterize the real-time fuzzy change trend of sequence data; Uneven characteristics; when dealing with the logical relationship between fuzzy time series, it is often accompanied by multiple uncertain fuzzy states, and the prediction accuracy of the system will decrease accordingly; most fuzzy time series predictions are limited to short-term time range predictions, even if a few models try to perform long-term Forecasts are all based on the mapping of multiple inputs and single outputs, and different models are established for different time ranges. This not only increases the complexity of the system, but also ignores the random dependence between predicted values ​​and easily causes error accumulation.

Images