DocumentCode :
3587912
Title :
Exploring upper bounds on the number of distinguishable classes
Author :
Keller, Catherine M. ; Whipple, Gary H.
Author_Institution :
MIT Lincoln Lab., Lexington, MA, USA
fYear :
2014
Firstpage :
1358
Lastpage :
1364
Abstract :
Information theoretic upper bounds on the number of distinguishable classes enable assessments of feasibility when applying classification techniques [1][2]. A goal of this paper is to examine the behavior of these upper bounds as the items being classified become more complex in the sense that the number of degrees of freedom increases. We synthesize filters with different numbers of stages to represent items with various levels of complexity. Using a typical distribution for component tolerances, we study whether different instantiations of filters with greater numbers of components (stages) are more distinguishable than filters with fewer components. We examine the behavior of the Fano upper bound for the number of distinguishable classes as a function of signal-to-noise ratio (SNR), to make the comparisons.
Keywords :
filtering theory; information theory; signal classification; Fano upper bound; SNR; classification technique; degrees of freedom; distinguishable class; filter instantiation; filters synthesis; information theoretic upper bound; signal-to-noise ratio; Covariance matrices; Cutoff frequency; Eigenvalues and eigenfunctions; Passband; Signal to noise ratio; Training; Upper bound;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signals, Systems and Computers, 2014 48th Asilomar Conference on
Print_ISBN :
978-1-4799-8295-0
Type :
conf
DOI :
10.1109/ACSSC.2014.7094682
Filename :
7094682
Link To Document :
بازگشت