000753978 000__ 02803cam\a2200481Ii\4500
000753978 001__ 753978
000753978 005__ 20230306141530.0
000753978 006__ m\\\\\o\\d\\\\\\\\
000753978 007__ cr\cn\nnnunnun
000753978 008__ 160226s2016\\\\sz\a\\\\ob\\\\001\0\eng\d
000753978 020__ $$a9783319288628$$q(electronic book)
000753978 020__ $$a3319288628$$q(electronic book)
000753978 020__ $$z9783319288611
000753978 0247_ $$a10.1007/978-3-319-28862-8$$2doi
000753978 035__ $$aSP(OCoLC)ocn941134370
000753978 035__ $$aSP(OCoLC)941134370
000753978 040__ $$aN$T$$beng$$erda$$epn$$cN$T$$dGW5XE$$dYDXCP$$dN$T$$dIDEBK$$dCDX$$dOCLCF$$dEBLCP$$dUPM$$dCOO
000753978 049__ $$aISEA
000753978 050_4 $$aQA76.9.S63
000753978 08204 $$a006.3$$223
000753978 1001_ $$aSanchez, Daniela,$$eauthor.
000753978 24510 $$aHierarchical modular granular neural networks with fuzzy aggregation$$h[electronic resource] /$$cDaniela Sanchez, Patricia Melin.
000753978 264_1 $$aSwitzerland :$$bSpringer,$$c2016.
000753978 300__ $$a1 online resource (viii, 101 pages) :$$billustrations.
000753978 336__ $$atext$$btxt$$2rdacontent
000753978 337__ $$acomputer$$bc$$2rdamedia
000753978 338__ $$aonline resource$$bcr$$2rdacarrier
000753978 4901_ $$aSpringerBriefs in applied sciences and technology, Computational intelligence
000753978 504__ $$aIncludes bibliographical references and index.
000753978 5050_ $$aIntroduction -- Background and Theory -- Proposed Method -- Application to Human Recognition -- Experimental Results -- Conclusions.
000753978 506__ $$aAccess limited to authorized users.
000753978 520__ $$aIn this book, a new method for hybrid intelligent systems is proposed. The proposed method is based on a granular computing approach applied in two levels. The techniques used and combined in the proposed method are modular neural networks (MNNs) with a Granular Computing (GrC) approach, thus resulting in a new concept of MNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL) and hierarchical genetic algorithms (HGAs) are techniques used in this research work to improve results. These techniques are chosen because in other works have demonstrated to be a good option, and in the case of MNNs and HGAs, these techniques allow to improve the results obtained than with their conventional versions; respectively artificial neural networks and genetic algorithms.
000753978 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed March 1, 2016).
000753978 650_0 $$aGranular computing.
000753978 650_0 $$aNeural networks (Computer science)
000753978 650_0 $$aGenetic algorithms.
000753978 7001_ $$aMelin, Patricia,$$d1962-$$eauthor.
000753978 77608 $$iPrint version:$$z9783319288611
000753978 830_0 $$aSpringerBriefs in applied sciences and technology.$$pComputational intelligence.
000753978 852__ $$bebk
000753978 85640 $$3SpringerLink$$uhttps://univsouthin.idm.oclc.org/login?url=http://link.springer.com/10.1007/978-3-319-28862-8$$zOnline Access$$91397441.1
000753978 909CO $$ooai:library.usi.edu:753978$$pGLOBAL_SET
000753978 980__ $$aEBOOK
000753978 980__ $$aBIB
000753978 982__ $$aEbook
000753978 983__ $$aOnline
000753978 994__ $$a92$$bISE