文档介绍：ROUGHROUGH SETSSETS
ANDAND
CHALLENGESCHALLENGES
ININ DATADATA MININGMINING
Andrzej Skowron
Warsaw University
RSCTCRSCTC 2004,2004, Uppsala,Uppsala, JuneJune 2,2, 20042004
AGENDAAGENDA
: ExamplesExamples ofof domainsdomains andand problemsproblems
: plex phenomenaphenomena modelingmodeling
: GeneralGeneral issuesissues
: RoughRough setssets plex phenomenaphenomena modelingmodeling
AGENDAAGENDA
: HierarchicalHierarchical (layered(layered learning)learning) ofof
plex conceptsconcepts
: LearningLearning fromfrom sparsesparse datadata
: plex decisiondecision andand conditioncondition valuesvalues
: LearningLearning representationrepresentation ofof concurrentconcurrent
processesprocesses
: LearningLearning ofof cooperationcooperation protocolsprotocols
BIOINFORMATICSBIOINFORMATICS
: MicroarrayMicroarray datadata analysisanalysis
: MicroarrayMicroarray datadata analysisanalysis extendedextended byby
knowledgeknowledge basesbases
: ModelingModeling ofof genegene--works
: TheThe proteinprotein foldingfolding problemproblem
: puting
EXAMPLESEXAMPLES
– UAV
– SOJOURNER, MARS ROVERS
– ROBO-CUP
– WEB MINING
– OBSTACLE AVOIDANCE
– collaborative systems for logistic problem solving
– robo-cup-rescue simulation league
– drugs or new material discovery
– sensor fusion in robotics
–...
WITASWITAS PROJECTPROJECT
/ext/witas/ext/witas//
CONTROLCONTROL OFOF AUVAUV
UAVUAV
IDENTIFICATIONIDENTIFICATION
U possible situations training cases
granule
defined
by t
dangerous
situations
t
perception term
inclusion degree testing
y y y
sensors 1 2 3
SOJOURNERSOJOURNER
ROBOROBO--CUPCUP