Paper:
Language: English:

Anytime Evaluation of Regression-Type Algorithms

Annamária R. Várkonyi-Kóczy, Tamás Kovácsházy, Orsolya Takács, and Csaba Benedescik

Department of Measurement and Information Systems
Budapest University of Technology and Economics, H-1521 Budapest, Magyar Tudósok körùtia 2., Hungary

Received: October 20, 2000

Accepted: December 10, 2000

Keywords: anytime algorithms, regression-type algorithms, system modeling, complexity reduction, on-going signal processing, off-line signal processing

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.5, No.1 pp. 2-7, 2001

Abstract

Regression-type algorithms are widely used for system modeling and characterization. There are applications where such characterizations are to be performed online to support control mechanisms and other decisions. In embedded autonomous systems, robustness considerations ask for techniques that, in addition to reflecting the actual state of the system and its environment, can continuously provide immediate signal processing results even in case of abrupt changes and/or temporal shortage of computational power and/or loss of some data. In other words, in such situations, actual processing should be continued to ensure appropriate performance. Consequently there is a need for robust techniques called "anytime" algorithms, which can provide short response time and be very flexible with respect to the available input information and computational power. This paper presents some considerations concerning such flexibility in the case of regression-type algorithms.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: