arrow
返回

IIR model identification using a modified inclined planes system optimization algorithm

delete2016-08-01
delete28
PRE
AI
A
Ali Mohammadi *
Z
Zahiri, Seyed Hamid
DOI:10.1007/s10462-016-9500-zdelete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Inclined planes system optimization (IPO) is a new optimization algorithm inspired by the sliding motion dynamic along a frictionless inclined surface. In this paper, with the aim of create a powerful trade-off between the concepts of exploitation and exploration, and rectify the complexity of their structural parameters in the standard IPO, a modified version of IPO (called MIPO) is introduced as an efficient optimization algorithm for digital infinite-impulse-response (IIR) filters model identification. The IIR model identification is a complex and practical challenging problem due to multimodal error surface entanglement that many researches have been reported for it. In this work, MIPO utilizes an appropriate mechanism based on the executive steps of algorithm with the constant damp factors. To do this, unknown filter parameters are considered as a vector to be optimized. In implementation, at first, to demonstrate the effectiveness of the proposed method, 10 well-known benchmark functions have been considered for evaluating and testing. In addition, statistical analysis on the powerfulness, efficiency and applicability of the MIPO algorithm are presented. Obtained results in compared to some other popular methods, confirm the efficiency of the MIPO algorithm that makes the best optimal solutions and has a better performance and acceptable solutions.
Keyword:
Digital infinite-impulse-response (IIR) filter
Global optimization
Model identification
Modified inclined planes system optimization (MIPO) algorithm
Performance
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Artificial Intelligence Review 封面图
Artificial Intelligence Review
IF:
13.9
论文数:
6.1K
被引数:
1.9W

机构

U
University of Birjand
学者数:
1.4K
论文数: 1.2K
被引数: 965
引用论文

引用论文

err分享
err收藏
err分享
err收藏
学者 查看更多内容