主成分模糊神經(jīng)網(wǎng)在高?？蒲袆?chuàng)新能力評價中的研究與應(yīng)用.pdf

1、聲明本學(xué)位論文是我在導(dǎo)師的指導(dǎo)下取得的研究成果，盡我所知，在本學(xué)位論文中，除了加以標(biāo)注和致謝的部分外，不包含其他人已經(jīng)發(fā)表或公布過的研究成果，也不包含我為獲得任何教育機(jī)構(gòu)的學(xué)位或?qū)W歷而使用過的材料。與我一同工作的同事對本學(xué)位論文做出的貢獻(xiàn)均已在論文中作了明確的說明。研究生簽名：勛『1年I9月f日學(xué)位論文使用授權(quán)聲明南京理工大學(xué)有權(quán)保存本學(xué)位論文的電子和紙質(zhì)文檔，可以借閱或上網(wǎng)公布本學(xué)位論文的部分或全部內(nèi)容，可以向有關(guān)部門或機(jī)構(gòu)送交并授權(quán)

2、其保存、借閱或上網(wǎng)公布本學(xué)位論文的部分或全部內(nèi)容。對于保密論文，按保密的有關(guān)規(guī)定和程序處理。研究生簽名：博哆吼：夕J1年細(xì)月f日AbS仃act碩士論文AbstractD戚ngthecourseofbuildinga11i11noVatiVecoun時andeIlllancingtheindependentiIulovationcapability，universitiesarethemainforceandtheimportamsour

3、ceofhi曲。techinnovationTheevaluationontheuniversity’sinnovationability，notonlymayimproVeumvers毋’sefjficiencyandlevelofscientificresearch，butalsomakeasignificantsensetoperfectthecllina’scientificresearchinnoVationsystemBas

4、edonRefIe玎ingtotherecentresearchachievementsathomea11dabmad，researchajlddesignworkwasca圩iedoutinthefollowingarea：(1)Thepaperdesignsthemulti—uniVersityresearchinnoVation￡lbilityeValuatingindicatorsystemBytheprincipleofsci

5、enceandjustice，throughquestionnaires，expenopiniona11dreferencetorelevantresearchresults，thepaperdesignedthemultiuniVersity’sresearchinnovationabili夠evaluatingindicatorsystem(2)Thep印erstudiesaVariet)，oftypicaleValuationmo

6、delsandmethodsThepaperstudiedmaIlytypicaleValuationmodelsa11dmethodsAndfocusedonstudyingtheseevaJuationmethods，suchasPrincipalComponentAnalysis(PCA)，BPNeuralNetwork，Tal(agi—Su瑪玲on(T—S)modelbasedFuzzyNeuralNetwork(Fl、『N)a

7、ndSOMNeuralNetworkThou曲comprehensiVeanalysis，twoeValllationmodelswasputfor、Vard0newasbasedonthePrincipalComponentAnalysisandBPNeuralNetwork(PCA—BP)TheotherwaSbaSedonthethePrincipalComponentAnalysisandFuzzyNeuralNetwork(P

8、CA—n烈)(3)TllepaperfinisheseValuatingtheuniVerSity’sScientificiIllloVationabilitybyusingthePCABPmodelaIldthePCAFNNmodelrcspectiVelyIntheprincipleofminimumdatainfbnnationloss，thepaperfirstusesPrincipleComponentAnalysis(PCA

9、)teducethedimensionalityef’fectiVelya11dfilteroutthemainfactorsabout90％，whichaimedateliminatingChedata’scorrelationandoVerlapThenthepaperconstmctedtheevaluationmodelsbasedonPCA—BPandPCA—FNNrespectiVely，andsimulated，check

10、ed，testandcompletedtheevaluationoftheuniVersity’sinnoVation如ilitywithMatlabAtlastthebetterexperilnentalresultsofPCA—FNNwasnotrankeddirectly，butgroupedbycluSterThereSultwasremarkableUsingt11isclustermethod，wecaneliminatet