Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence

Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence

Fuzzy attributes are used to quantify imprecise data that model real world objects. To effectively use fuzzy attributes, a fuzzy membership function must be defined to provide the boundaries for the fuzzy data. The initialization of these membership function values should allow the data to converg...

Full description

Bibliographic Details
Main Author: Lee, Stephanie Scheibe
Format: Others
Published: VCU Scholars Compass 2005
Subjects:
logic
convergence
initiliazation
database
fuzzy
Computer Sciences
Physical Sciences and Mathematics
Online Access:http://scholarscompass.vcu.edu/etd/852
http://scholarscompass.vcu.edu/cgi/viewcontent.cgi?article=1851&context=etd
id ndltd-vcu.edu-oai-scholarscompass.vcu.edu-etd-1851
record_format oai_dc
spelling ndltd-vcu.edu-oai-scholarscompass.vcu.edu-etd-18512017-03-17T08:29:42Z Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence Lee, Stephanie Scheibe Fuzzy attributes are used to quantify imprecise data that model real world objects. To effectively use fuzzy attributes, a fuzzy membership function must be defined to provide the boundaries for the fuzzy data. The initialization of these membership function values should allow the data to converge to a stable membership value in the shortest time possible. The paper compares three initialization methods, Random, Midpoint and Random Proportional, to determine which method optimizes convergence. The comparison experiments suggest the use of the Random Proportional method. 2005-01-01T08:00:00Z text application/pdf http://scholarscompass.vcu.edu/etd/852 http://scholarscompass.vcu.edu/cgi/viewcontent.cgi?article=1851&context=etd © The Author Theses and Dissertations VCU Scholars Compass logic convergence initiliazation database fuzzy Computer Sciences Physical Sciences and Mathematics
collection NDLTD
format Others
sources NDLTD
topic logic
convergence
initiliazation
database
fuzzy
Computer Sciences
Physical Sciences and Mathematics
spellingShingle logic
convergence
initiliazation
database
fuzzy
Computer Sciences
Physical Sciences and Mathematics
Lee, Stephanie Scheibe
Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
description Fuzzy attributes are used to quantify imprecise data that model real world objects. To effectively use fuzzy attributes, a fuzzy membership function must be defined to provide the boundaries for the fuzzy data. The initialization of these membership function values should allow the data to converge to a stable membership value in the shortest time possible. The paper compares three initialization methods, Random, Midpoint and Random Proportional, to determine which method optimizes convergence. The comparison experiments suggest the use of the Random Proportional method.
author Lee, Stephanie Scheibe
author_facet Lee, Stephanie Scheibe
author_sort Lee, Stephanie Scheibe
title Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
title_short Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
title_full Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
title_fullStr Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
title_full_unstemmed Fuzzy Membership Function Initial Values: Comparing Initialization Methods That Expedite Convergence
title_sort fuzzy membership function initial values: comparing initialization methods that expedite convergence
publisher VCU Scholars Compass
publishDate 2005
url http://scholarscompass.vcu.edu/etd/852
http://scholarscompass.vcu.edu/cgi/viewcontent.cgi?article=1851&context=etd
work_keys_str_mv AT leestephaniescheibe fuzzymembershipfunctioninitialvaluescomparinginitializationmethodsthatexpediteconvergence
_version_ 1718428240149741568

Similar Items