The Design Of Plant Disease Diagnosis Expert System Based On Neural Network

The main wo出 ofthls thesis Is to design and realize a Plant DiseaseD叫叨osls Emert Sxstem based on Neural Nemork(PDDES NNNN)andmodem－dialing connection恤ughthe research ofexpert systems basedmflclal neural network and that of remote senal communreatlonbetween PDA and PC．The details ofour Work are: 1．1讪1＊ ＊S,a＊e娜rBPmuralmM0rh0dell＊Sed,andforthe consideration oflts slow conve侣ent speed,one of＊theeration two mainl删s of＊the basic BP algonthmhm,a new BP algonthln namedselfad叩tlve step factor BP algont咖(SSFBP)has been put forward．The main idea of＊the algon咖 Is:Change the value ofstep factor,l．e．theV砌e OflCSYfllllg仰e SCCOfdlllgtothC SignS ＆fldTC18tlVC SIZC OfthCMo latestwdlents as leamingprogresses,and叮 to keep the currentSt印,l．C．thC SIZC OfWClght lflCTCffiCflt,SS id侣e SS pOSSlblC Wltholltovershooting so thatselFad地tatlon ofleaming rate can be reallied andMtcoM鸽t speedcanbe achieved．The algonth Is high e征ctlve．and easy to realize wlthoutneedingto choose any cntlcal parameters．ptthe same time,forthe consideration of＊theeration probability oflocalCOllV吗mC＊ th OthCT Ofth tWO i81＊ 0删S Of＊C的SIC BP ＆lgOTI山i,slmulatedannealingtheoryls In眈ducedto Integratethe sensltlvltyofthe micro s饲cture of＊the＊＝ new BP algorithm with the macrod此地onality ofslmlated annealing algonth．So a combination of＊theationtWO ＆lgo伽S,fi8ITICd SASSFBP slgofl讪,h肪 bCCflpfCSCfltCd lfl thisthesis．The main principle of＊theple algonth Is:on one hand,t帅ugh thescWdwtlve step factorBP algontM,ltaccelerates thelteratlvepacesto cause fast convefgence In the negative gTadlent direction With thenumber ofuseless searches being greatly re山ced,and on the other hand,咖ugh simulated annealing algon山m,It can．escaPe from local minimaso as to conve侣e to global minimum as much as possible．By the仰etltlve alternation ofthetwo algon咖s,the global minimum can beachieved inally． The results of our eXpenmentatlon,reflect that the two main lawsof＊the basic BP algorith can be overcome to a large degree by theSASSFBP algont帅basedon combination of＊theation above刚o algorithms． 2．AcomunlcatlonprotocolbasedonRS－232 async址onous senalcomunlcatlongortandcormectlon establlshedbymodemdlaling,whichls su中山leford咖rismlsslonbetweenPDAandPC,has beendesl即ed m this thesis．nd acco巾lug to this protocol,a remote senalcommunication systembetween PDAandPCbasedon Interrupt－recelving mode,has been reallzednot only to solve the problem of＊themremoted咖trailsmlsslonbetween PDAandPC,butalso to conseectthebase forP以's urure"use ofaccessing Information加m expert systemsonPC servers and other Information from the Internet． 3·Basedonthe neural netwo巾's learning algonth广一SASSFBPalgonthlnandthe r皿ote senalco删unlcatlon system,the yooESNNNNisdeslgnedandlmplememedlnthls thesis．The system overcomes thel删s of咖dltlonal耶ertsystems such as邵atdlfficulty In knowledgeac叭lsltlon and low speedofreasoning to some extent,and has goodprospects Inthefieldofpl咖protection from diseases．...