简介：

简介：

简介：Itisveryimportantinthefieldofbioinformaticstoapplycomputertoperformthefunctionannotationfornewsequencedbio-sequences.BasedonGOdatabaseandBLASTprogram,anovelmethodforthefunctionannotationofnewbiologicalsequencesispresentedbyusingthevariable-precisionroughsettheory.TheproposedmethodisappliedtotherealdatainGOdatabasetoexamineitseffectiveness.Numericalresultsshowthattheproposedmethodhasbetterprecision,recall-rateandharmonicmeanvaluecomparedwithexistingmethods.

简介：Whendevelopingahumanoidmyo-controlhand,notonlythemechanicalstructureshouldbeconsideredtoaffordahighdexterity,butalsothemyoelectric(electromyography,EMG)controlcapabilityshouldbetakenintoaccounttofullyaccomplishtheactuationtasks.Thispaperpresentsanovelhumanoidroboticmyocontrolhand(ARhandⅢ)whichadoptedanunderac-tuatedmechanismandaforearmmyocontrolEMGmethod.TheARhandⅢhasfivefingersand15joints,andactuatedbythreeembeddedmotors.Underactuationcanbefoundwithineachfingerandbetweentherestthreefingers(themiddlefinger,theringfingerandthelittlefinger)whenthehandisgraspingobjects.FortheEMGcontrol,twospecificmethodsareproposed:thethree-fingeredhandgestureconfigurationoftheARhandⅢandapatternclassificationmethodofEMGsignalsbasedonastatisticallearningalgorithm-SupportVectorMachine(SVM).Eighteenactivehandgesturesofatesteearerecognizedef-fectively,whichcanbedirectlymappedintothemotionsofARhandⅢ.Anon-lineEMGcontrolschemeisestablishedbasedontwodifferentdecisionfunctions:oneisforthediscriminationbetweentheidleandactivemodes,theotherisfortherecog-nitionoftheactivemodes.Asaresult,theARhandⅢcanswiftlyfollowthegestureinstructionsofthetesteewithatimedelaylessthan100ms.

简介：Detectingtheboundariesofproteindomainsisanimportantandchallengingtaskinbothexperimentalandcomputationalstructuralbiology.Inthispaper,apromisingmethodfordetectingthedomainstructureofaproteinfromsequenceinformationaloneispresented.Themethodisbasedonanalyzingmultiplesequencealignmentsderivedfromadatabasesearch.Multiplemeasuresaredefinedtoquantifythedomaininformationcontentofeachpositionalongthesequence.Thentheyarecombinedintoasinglepredictorusingsupportvectormachine.Whatismoreimportant,thedomaindetectionisfirsttakenasanimbalanceddatalearningproblem.Anovelundersamplingmethodisproposedondistance-basedmaximalentropyinthefeaturespaceofSupportVectorMachine(SVM).Theoverallprecisionisabout80%.Simulationresultsdemonstratethatthemethodcanhelpnotonlyinpredictingthecomplete3Dstructureofaproteinbutalsointhemachinelearningsystemongeneralimbalanceddatasets.

简介：Anactivestereovisionsystembasedonamodelofneuralpathwaysofhumanbinocularmotorsystemisproposed.Withthismodel,itisguaranteedthatthetwocamerasoftheactivestereovisionsystemcankeeptheirlinesofsightfixedonthesametargetobjectduringsmoothpursuit.Thisfeatureisveryimportantforactivestereovisionsystems,sincenotonly3Drecon-structionneedsthetwocamerashaveanoverlappingfieldofvision,butalsoitcanfacilitatethe3Dreconstructionalgorithm.Toevaluatetheeffectivenessoftheproposedmethod,somesoftwaresimulationsaredonetodemonstratethesametargettrackingcharacteristicinavirtualenvironmentapttomistrackingeasily.Here,mistrackingmeanstwoeyestracktwodifferentobjectsseparately.Thentheproposedmethodisimplementedinouractivestereovisionsystemtoperformrealtrackingtaskinalaboratoryscenewhereseveralpersonswalkself-determining.Beforetheproposedmodelisimplementedinthesystem,mis-trackingoccurredfrequently.Afteritisenabled,mistrackingneveroccurred.Theresultshowsthatthevisionsystembasedonneuralpathwaysofhumanbinocularmotorsystemcanreliablyavoidmistracking.

简介：Wepresentarapidsystemforpredictingbeeftendernessbymimickingthehumantactilesense.ThedetectionsystemincludesaFSpressuresensor,apowersupplyconversioncircuit,asignalamplifierandaboxinwhichthesampleismounted.AsampleofrawLongissimusdorsi(LD)muscleisplacedinthemeasuringbox;thenarodconnectedtothepressuresensorispressedintothebeefsampletoagivendepth;thereactionforceofthebeefsampleismeasuredandusedtopredictthetenderness.SensoryevaluationandWarner-BratzlerShearForce(WBSF)evaluationofsamplesfromthesameLDmuscleareusedforcomparison.Thenewdetectionsystemagreeswithestablishedprocedure95%ofthetime,andthetimetotestasampleislessthan5minutes.

简介：Anovelbionicswarmintelligencealgorithm,calledantcolonyalgorithmbasedonablackboardmechanism,isproposedtosolvetheautonomyanddynamicdeploymentofmobilessensornetworkseffectively.Ablackboardmechanismisintroducedintothesystemformakingpheromoneandcompletingthealgorithm.Everynode,whichcanbelookedasanant,makesoneinformationzoneinitsmemoryforcommunicatingwithothernodesandleavespheromone,whichiscreatedbyantitselfinnature.ThenantcolonytheoryisusedtofindtheoptimizationschemeforpathplanninganddeploymentofmobileWirelessSensorNetwork(WSN).Wetestthealgorithminadynamicandunconfigurableenvironment.Theresultsindicatethatthealgorithmcanreducethepowerconsumptionby13%averagely,enhancetheefficiencyofpathplanninganddeploymentofmobileWSNby15%averagely.

简介：Thispaperproposesanewadaptivelineardomainsystemidentificationmethodforsmallunmannedaerialrotorcraft.Byusingtheflashmemoryintegratedintothemicroguidenavigationcontrolmodule,systemrecordsthedatasequencesofflighttestsasinputs(controlsignalsforservos)andoutputs(aircraft’sattitudeandvelocityinformation).Afterdatapreprocessing,thesystemconstructsthehorizontalandverticaldynamicmodelforthesmallunmannedaerialrotorcraftusingadaptivegeneticalgorithm.Theidentifiedmodelisverifiedbyaseriesofsimulationsandtests.Comparisonbetweenflightdataandtheone-steppredictiondataobtainedfromtheidentificationmodelshowsthatthedynamicmodelhasagoodestimationforrealunmannedaerialrotorcraftsystem.Basedontheproposeddynamicmodel,thesmallunmannedaerialrotorcraftcanperformhovering,turning,andstraightflighttasksinrealflighttests.

简介：

简介：Inthepost-genomicbiologyera,thereconstructionofgeneregulatorynetworksfrommicroarraygeneexpressiondataisveryimportanttounderstandtheunderlyingbiologicalsystem,andithasbeenachallengingtaskinbioinformatics.TheBayesiannetworkmodelhasbeenusedinreconstructingthegeneregulatorynetworkforitsadvantages,buthowtodeterminethenetworkstructureandparametersisstillimportanttobeexplored.Thispaperproposesatwo-stagestructurelearningalgorithmwhichintegratesimmuneevolutionalgorithmtobuildaBayesiannetwork.Thenewalgorithmisevaluatedwiththeuseofbothsimulatedandyeastcellcycledata.Theexperimentalresultsindicatethattheproposedalgorithmcanfindmanyoftheknownrealregulatoryrelationshipsfromliteratureandpredicttheothersunknownwithhighvalidityandaccuracy.

简介：