DocumentCode :
2866064
Title :
Non-Euclidean locally monotonic regression
Author :
Retrepo, A. ; Sandberg, Irwin W. ; Bovik, Alan C.
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
fYear :
1990
fDate :
3-6 Apr 1990
Firstpage :
1201
Abstract :
The concept of locally monotonic regression is extended by considering metrics on rn that are different from the Euclidean metric. The existence of regressions for a large class of metrics is shown. Algorithms that show the computability of locally monotonic regressions are given. A general algorithm that computes regressions for the lp metrics is given; considered in detail are the cases corresponding to the metrics l1 and l∞, where the sample median and the sample midrange play important roles
Keywords :
computerised signal processing; filtering and prediction theory; locally monotonic regressions; median filtering; nonEuclidean metric; signal processing; Euclidean distance; Filters; Periodic structures; Skeleton; Smoothing methods; Topology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.1990.115586
Filename :
115586
Link To Document :
https://search.ricest.ac.ir/dl/search/defaultta.aspx?DTC=49&DC=2866064
بازگشت