Full text
| |
| Author(s): |
Ivette Raymunda Luna Huamaní
Total Authors: 1
|
| Document type: | Doctoral Thesis |
| Press: | Campinas, SP. |
| Institution: | Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação |
| Defense date: | 2007-05-10 |
| Examining board members: |
Secundino Soares Filho;
Aluizio Fausto Ribeiro Araujo;
Marinho Gomes de Andrade Filho;
Paulo Sergio Franco Barbosa;
Fernando José Von Zuben;
Takaaki Ohishi
|
| Advisor: | Secundino Soares Filho; Rosangela Ballini |
| Abstract | |
This work presents a methodology for time series modeling and forecasting. First, the methodology considers the data pre-processing and the system identification, which implies on the selection of a suitable set of input variables for modeling the time series. In order to achieve this task, this work proposes an algorithm for input selection and a set of approximations that are necessary for estimating the partia! mutual information criterion, which is the base of the algorithm used at this stage. Then, the mo deI is built and adjusted. With the aim of performing an automatic structure selection and parameters adjustment simultaneously, this thesis proposes two constructive learning algorithms, namely ofRine and online. These algorithms are based on the Expectation Maximization optimization technique, as well as on adding and pruning operators of fuzzy rules that are also proposed in this work. Finally, models are validated and applied to one-step ahead and multi-step ahead forecasting. Comparative analysis using synthetic and real time series are detailed. The results show the adequate performance of the proposed approach and presents it as a promising alternative for time series modeling and forecasting (AU) | |