Table of Content

05 July 2018, Volume 0 Issue 06

Previous Issue    Next Issue

ContextSemantic-basedNaiveBayesianAlgorithmforTextClassification

ZHENGKai-yu,ZHUCui

2018, 0(06):  1. 

Asbtract ( 94 )  

References | Related Articles | Metrics

TheNaiveBayesclassifierisbasedontheassumptionthatthesamples’attributesareindependentoneanother.Asasimplebag-of-wordsmodel,itignorestheinfluenceofsynonymsincontexttoclassification.Thispaperproposestheconceptofsimilarwordandusesclustersofsimilarwordsinsteadofkeyworddictionaryintraining.First,word2vecistrainedtogetwordembedding.Second,thekeyworddictionaryisrepresentedbywordembeddingwhichisthenclusteredhierarchically,theclustersofsimiliarwordsarebuiltandexpanded.Theexperimentalresultsshowthattheabovemethodcanimprovetheaccuracyoftextclassification,andavoidtheinstabilityofclassificationeffectduetothedifferencesintrainingcorpus.

TextClusteringRetrievalBasedonLDAModel

LIXiao-ye,LIChun-sheng,LILong,ZHANGKe-jia

2018, 0(06):  7.  doi:10.3969/j.issn.1006-2475.2018.06.002

Asbtract ( 204 )  

References | Related Articles | Metrics

Thetraditionalmethodofjudgingthesimilarityoftwodocumentsdoesnottakeintoaccountthesemanticrelationbehindthetexts,resultinginalargedifferencebetweentheresultsreturnedbytheretrievalsystemandtheusersqueryrequirements.ThispaperpresentsatextclusteringmethodbasedonLDAtopicmodel.Firstly,theapplicationprincipleofLDAtopicmodelisintroducedandthebasicmethodoftextminingisexpounded,andthentheLDAtopicmodelisconstructed.TheGibbssamplingmethodisusedtoderivetheprobabilitydistributionofthecharacteristicwords.Finally,thesetsoftestdataareclusteredwiththeK-means+〖KG-*3〗+methodchosenbytheoptimizationclustercenter.AndthedesignedLDA-GibbsmodeliscomparedwiththetraditionalTF-IDFmodel.Experimentalresultsshowthatthismodelcanimprovetheretrievaleffectofdataandhasgoodpromotionalvalue.

NeuralNetworksforModelingandForecastingVolatilityofEconomicMarket

XIERong-yan

2018, 0(06):  12.  doi:10.3969/j.issn.1006-2475.2018.06.003

Asbtract ( 156 )  

References | Related Articles | Metrics

ThispaperpresentsaMarkovswitchingartificialneuralnetwork(HMM),whichisappliedtothevolatilitymodelingandpredictionofthegoldmarketintheeconomicmarket.Theproposedmodelsdifferintermsofboththedynamicsoftheconditionalvolatilityprocessandtheforecastingcapabilitiescomparedtotraditionalneuralnetworkmodels.Inthispaper,thesemodelsareusedtotestvolatilityofgoldreturn.MAE,MSEandRMSEareevaluatedandtheimprovedDieboldMarianotestiscarriedoutunderthesameprecision.Anempiricalapplicationisprovidedforforecastingdailyreturnsingoldmarket.Theresultssuggestthattheproposedapproachperformswellinmodelingandforecastingvolatilityindailyreturnsofinternationalgoldmarket.

ApplicationofMulti-objectiveGeneticAlgorithminShipLockScheduling

MAOXing,XUXi-tao

2018, 0(06):  16.  doi:10.3969/j.issn.1006-2475.2018.06.004

Asbtract ( 128 )  

References | Related Articles | Metrics

Aimingattheinefficiencyoftraditionalwatertransportscheduling,ashiplockschedulingmethodbasedon〖JP2〗improvedmulti-objectivegeneticalgorithmisproposed.Basedonthebiologicalevolutionprocess,theresultsofshipgearingsaredefinedasindividualsofevolutionaryobjects,andchromosomecodingandpopulationinitializationareperformed.Theobjectivefunctionisconstructedaccordingtodifferentschedulingindexes,andindividualfitnessiscalculatedfortheinitialpopulation.Selectionoperations,crossoveroperationsandvarianceoperationsareusedtoevaluateandmakedecisionsfromaglobalperspectiveandtooutputtheoptimalgearschedulethatmeetstheschedulingrequirements.ExperimentsarecarriedoutusingtheactualdataofChangzhouShipLock,whichshowsthatthemethodnotonlyimprovestheutilizationrateoflockbutalsoshortenstheschedulingtime.

DoFFT:AFastFourierTransformMethodBasedonDistributedDatabase

JIPeng1,2,LIHui1,2,CHENMei1,2,DAIZhen-yu1,2

2018, 0(06):  19.  doi:10.3969/j.issn.1006-2475.2018.06.005

Asbtract ( 197 )  

References | Related Articles | Metrics

FastFouriertransformhasawiderangeofapplicationsinastronomy.Forexample,pulsarsignalsoftenrequirecoherentdeclerprocessingbasedonfastFouriertransforms.Asthesignaldataisusuallystoredinthedatabase,andexecutingfastFouriertransformalgorithmoutsideofdatabaseaftergettingdatafromthedatabasewillhavealotofI/Oandnetworkoverheadandthusseriouslyaffecttheoverallperformance.Tosolvethisproblem,thispaperdesignsaDoFFT(DatabaseoptimizedFFT)algorithmwhichcanexecuteandoptimizefastFouriertransformsinparallelintheformofuser-definedfunctions(UDF).Inaddition,differentloadofeachnodeinthedatabaseclusterandunevendistributionofdatamaysometimesleadtoinefficientimplementation,DoFFTmethodbasedontheCPU,I/O,networkandtransmissionrates,andothercosts,redistributesdatatofurtheroptimizetheparallelexecutionoffastFouriertransform.TheexperimentalresultsshowthattheperformanceofDoFFTalgorithmisimprovedeffectivelywiththeoptimizationbasedondataredistribution.

HybridParticleSwarmOptimizationAlgorithmBasedon#br# DynamicAdjustmentofInertiaWeight

GUMing-liang,LIMin

2018, 0(06):  25.  doi:10.3969/j.issn.1006-2475.2018.06.006

Asbtract ( 161 )  

References | Related Articles | Metrics

Whensolvinghighdimensionalnonlinearproblems,ParticleSwarmOptimizationalgorithmiseasytofallintolocaloptimalsolution.Inthiscase,anewnonlinearadaptiveweightadjustmentstrategybasedonSigmodfunctionisproposed.Inaddition,aLatinHypercubeSamplingmethodisusedtoproduceahomogeneousinitialpopulation,andanicheeliminationstrategyisusedtoenhancetheglobaloptimizationabilityofthealgorithm.Finally,sixstandardtestfunctionsareusedtotesttheperformanceoftheimprovedalgorithm.Theresultsshowthattheimprovedparticleswarmoptimizationalgorithmachievessatisfactoryresultsinconvergencespeed,convergenceaccuracyandtheacquisitionofglobaloptimalsolution.

CyberSecuritySituationEvaluationMethodBasedon#br# AssociationAnalysisandHiddenMarkovModel

WUJian-tai,LIUGuang-jie,LIUWei-wei,DAIYue-wei

2018, 0(06):  30.  doi:10.3969/j.issn.1006-2475.2018.06.007

Asbtract ( 218 )  

References | Related Articles | Metrics

MostofthecurrentnetworksecuritysituationassessmentmethodsbasedonHMMarefocusedonthestudyofHMMparameters,ignoringtheimpactofobservationvaluesonevaluationaccuracy.Thispaperisbasedontheaggregationofalarminformation,takesattackmodeasabasisforassociation,combinesthevulnerabilityinformationofnetworkassets，identifiestheattackphaseofthehostandconvertsittothethreatlevelofthehost,andfinally,usesHMMtoevaluatethesecuritysituationofthehostandnetwork.ExperimentbasedonDARPA2000datasetshows,comparedwiththegeneralHMMmethod,thismethodcanreflectthemulti-stepcharacteristicsoftheattack,anditcanmoreaccuratelyreflectthechangeofnetworksituation.

CloudDataIntegrityBasedonSBTTotalNodeStorage

ZHOUPeng1,2，LONGShi-gong1,2

2018, 0(06):  37.  doi:10.3969/j.issn.1006-2475.2018.06.008

Asbtract ( 92 )  

References | Related Articles | Metrics

Cloudstoragecanprovideuserswithhigh-quality,on-demanddatastorageservices,sothatuserscanenjoyalargeamountofstoragecapacityatlowprices.Butforusers,thecloudstorageserverisnotcompletelytrustworthy,sousersworryaboutthedatastoredinthecloudwillhavesecurityproblems.Whileinordertomeettheapplicationinthecloud,theintegrityvalidationmechanismisrequiredtosupportfulldynamicoperationsandthird-partypubliccertification.Therefore,aclouddataintegrityschemebasedonfullnodestorageisproposed.Abalancedbinarysearchtreestructure—nodesizebalancetree(SizeBalancedTree,SBT)isintroduced,thisstructuremakesallthenodesinthetreecanbeusedtostoretheactualdata,comparedtotheleavesnodestoragetree,nodoubtitreducestheserverspaceoverhead,whilereducingtheheightofthetree,thusreducingthetimecomplexityofbasicoperationssuchasdatainsertionanddeletion.Theschemehasbetterefficiencyinsupportofdynamicoperationandcanwellsupportdataintegrityverificationincloudstorageenvironment.

DetectionofForeignObjectsinSubwayOutdoorPlatform#br# BasedonK-meansAlgorithm

LEIHuan-yu,LIUWei-ming

2018, 0(06):  42.  doi:10.3969/j.issn.1006-2475.2018.06.009

Asbtract ( 172 )  

References | Related Articles | Metrics

Aimingatthegapbetweensubwayscreendoorandtraindoor,thereisahiddendangerofaccidentinsubwayoperationbecauseofthepinch-in,andadetectionmethodbasedonmetrostationsurfaceisproposed.ThismethodimprovestheefficiencyandaccuracyofthedetectionbyemployingamanualconstructionoftheopticalbackgroundandusingtheHSVcolorspace.Thealgorithmusesthemethodtoextractthetargetimageofthecartaillightwiththecameraofthevehiclehead,anddetermineswhetherthereisspatialforeignbodyinthegapbetweenthecarbodyandthescreendoorbycalculatingthecompletenessofthetarget.Experimentsonrealvideodatashowthattheproposedalgorithmhasgoodrobustnesstolightchangesandcandetectvariousforeignobjectsaccuratelyandcanassistthedriverinmakingdecisionsbeforedriving.

AnAugmentedRealityMethodBasedonSURFandGeographicGridModel

BIJin-qiang,XUJia-shuai,XINQuan-bo,SHANGDong-fang

2018, 0(06):  47.  doi:10.3969/j.issn.1006-2475.2018.06.010

Asbtract ( 128 )  

References | Related Articles | Metrics

Imagerecognitionandmatchingisthefoundationandkeyofresearchandapplicationonthefieldofaugmentedreality.Accordingtothewideareaandrandomnessofoutdoorscenes,similarityoftargettexturestructure,anaugmentedrealitymethodbasedonSURFandgeographicgridmodelisproposed.ThemethodaccordingtothecorrelationbetweenthetargetsceneandthegeographicallocationdetectstheimagefeaturepointstogeneratetheLocation-SURFimagefeaturedescription,constructsthespatialfourforktreeindexbasedonthegeographicalgrid,andbuildsthestaticfeaturesampledatabase.Featureimagesaregeneratedbyvideoframe,locationandangleinformation,anduploadedtotheservertoparseoperations,andtrainedtomatchwiththesampledatabase.Testsresearchwhichgathers270piecesofimagedatatoconstructasampledatabaseisdoneintheNingboglobalnavigationsquareabout0.376km2.Onlinefeaturepointscanbematchedonlinethroughthereal-timecollectionandcalculationofspotimage,andtheaccuracyofmatchingupcanbeimprovedbyadjustingtheproportionofdistancethreshold.Amobileaugmentedrealitysystemisdevelopedbasedonthismethod,whichusesfourlayersoftechnologyarchitecturetorealizetheparallelizationoftheterminalcollection,displayandserveranalysisandcalculation,andachievesthefusioneffectoftherealsceneandthevirtualinformation.Theapplicationresultsshowthat:Thismethodcansolvetheproblemoflowmatchingofimagerecognitionincomplexenvironment,canquicklycompletethedetectionandextractionoffeaturepoints,caneffectivelycompletesampletrainingandmatching.Aswellasthismethodmakesausefulattempttoprovideaneffectivewayintheoutdoormobileaugmentedreality.

ImageDenoisingAlgorithmBasedonReactionDiffusionandNonlocalSelf-similarity

MOPei-ji1,2，LEIHong1

2018, 0(06):  54.  doi:10.3969/j.issn.1006-2475.2018.06.011

Asbtract ( 150 )  

References | Related Articles | Metrics

Inordertomakebetteruseofimagepriorandtoprotecttheedges,textureoftheimage,animprovedalgorithmwhichcombinestrainednonlinearreactiondiffusion(TNRD)withpatchgrouppriorbaseddenoising(PGPD)isproposed.Firstofall,threeorthogonalsubbandsareobtainedbywaveletdecompositionofthePGPDdenoisedimage.Thetheoreticalanalysisshowsthattheimageisthesumofthesubbands.Thendiffusingthesubbandwithhighfrequencycoefficientsofwhichthewaveletcoefficientsaregreaterthanthethresholdbynonlinearreactiondiffusion,andtheresultsareusedtoreplacetheoriginalsubbandtogetthefinaldenoisingimage.Theexperimentalresultsshowthattheimprovedalgorithmhasgreaterperformanceimprovement,suchasthePeakSignaltoNoiseRatio(PSNR),thedetailsprotection.

Multi-taskFaceAttributeRecognitionBasedonUnbalancedClasses

ZHANGWen

2018, 0(06):  58.  doi:10.3969/j.issn.1006-2475.2018.06.012

Asbtract ( 160 )  

References | Related Articles | Metrics

Therecognitionofattributesplaysanimportantroleinobjectrecognition,suchasfaceverification,activityrecognitioninvideo.Theimprovementofattributerecognitionwillleadtobetterresultfortheapplicationwhichusestheseattributes.Inrecentyears,therearesomeworksfocusingontheattributelearning.However,attributeshavebeenconsideredtobeindependentinmostworks.Inpractice,weknowthatisnotrightandmanyattributesarestronglyrelated,suchasnobeardandfemale,baldandhaircolor.Inaddition,mostworksneglecttheunbalanceofdifferenceclasssamples,suchasimagesofbaldisaverysmallpartofsamples.Basedonthetwoobservations,weproposeamulti-taskunbalancedfacialattributerecognitionframeworkusingmodifiedDensenet.Toacertaindegrees,theframeworkrelievestheunbalancedproblem.Theproposedmethodoutperformsothermethods,haslessparametersandrunsfaster.Wedemonstratetheeffectivenessofourmethodontwochallengingpubliclyavailabledatasets.

MotionSensingDanceInteractionSystemBasedonMotionEvaluationAlgorithm

YUJing-hua,WANGQing,CHENHong

2018, 0(06):  64.  doi:10.3969/j.issn.1006-2475.2018.06.013

Asbtract ( 231 )  

References | Related Articles | Metrics

Squaredanceisawayofphysicalexercise,entertainmentandsocialinteractionwithhighparticipation.Inviewofthecharacteristicsofsquaredanceactivitiesandtheproblemsoftheactualimplementation,weanalyzedandimprovedtheactionevaluationalgorithm,andevaluatedthehumanskeletonsequencewhichtheKinectcapturedinrealtime.WedesignedandintegratedamotionsensingdanceinteractionsystembasedonKinecttoservethegrass-rootspublicculture.Wegavefullplaytotheeffectofmotionsensinginteractiveexperience.Userscanfullymobilizebody’ssubjectiveintheprocessofparticipation.Itprovidesanewactivitywayandconveniencesforgrass-rootsmassculturalactivities.

VISDMiner:AnInteractiveDataMiningProcessVisualizationSystem

WANGYong-sheng1,2，LIHui1,2，CHENMei1,2，DAIZhen-yu1,2，ZHUMing3

2018, 0(06):  72.  doi:10.3969/j.issn.1006-2475.2018.06.014

Asbtract ( 224 )  

References | Related Articles | Metrics

Inordertoaddresstheproblemthatthedataminingprocessoftentobenottransparentandlackofuserinteraction,wedesignandimplementtheVISDMinersystem.VISDMinercombinesthevisualizationtechnologyandthedataminingtechnologytoprovidethecapabilityofanalyzingandvisualizingpartialresultsofallstagesofminingprocess.Duringtheprocedures,userscantunetheparametersofdataminingalgorithmandvisualizationsaccordingtotheirdomainknowledgeandexperiencetoachievefurtherdataexploration.Inordertodealwithhigh-dimensionaldataset,VISDMinersystemusesanimprovedalgorithmMIC-PCAforprincipalcomponentanalysisbasedonthemaximuminformationcoefficient.ThealgorithmismainlyaimedatimprovingthedimensionalityreductionandclassificationaccuracyoftraditionalPCAalgorithms.TheexperimentalresultsshowthatVISDMinenotonlyrealizesthevisualizationofthedataminingprocess,butalsoimprovestheuser’sunderstandabilityofthedataminingresults,andtheMIC-PCAalgorithmalsoimprovesthedimensionalityreductionandclassificationaccuracyofPCAalgorithm.

AnNon-contactHigh-precisionMulti-liquidMeasuringandBlendingSystem

CHENMin-zhe,XIONGCheng,LIUShou-yin

2018, 0(06):  79.  doi:10.3969/j.issn.1006-2475.2018.06.015

Asbtract ( 97 )  

References | Related Articles | Metrics

Aimingattheproblemthatlackingofadevicetoblenddifferentkindofliquidcustomizedinanefficientway,asmartliquidblendingsystemisdesignedandimplemented.Thesystemcangettheuser’sinformationfrominteractingwithuserbyusingPCoranAndroidmobiledevice.Thenthesmartblendingdevicecanreceivetheinformationinordertoblendthemultipleliquidindemandwhichisloadedbefore.Thesystemisautomatic,complete,efficient,powerfultransplantablewithahigh-precisioninalowcost.Theexperimentresultindicatesthatthissystemcanmeetthemarketdemand.

DiagnosisofType2DiabetesBasedonCost-sensitiveActiveLearningAlgorithm

XUZhi-biao

2018, 0(06):  84.  doi:10.3969/j.issn.1006-2475.2018.06.016

Asbtract ( 153 )  

References | Related Articles | Metrics

Inthisstudy,adiagnosismodelfortype2diabeteswasbuiltandthelabelabsenceprobleminmedicaldatawassolvedbyactivelearning.Thediagnosisoftype2diabetescanbeseenasacost-sensitivebinaryclassificationtask.Takinglogisticregression,supportvectormachines(SVM)andartificialneuralnetwork(ANN)asthebasemodel,thisstudyadoptedthecost-sensitiveactivelearningalgorithmbasedontheexpectederrorreductionframework,whichcombinedtheactivelearningstrategywiththecost-sensitiveclassificationalgorithmandintroducedthecostinformationintotheinstancesamplingprocess.Forthediagnosisoftype2diabetes,thecost-sensitiveactivelearningalgorithmbasedontheexpectederrorreductionframeworkperformedbestinthesecomparedactivelearningstrategiesanditachievedtheminimummisclassificationcostsbylabelingfewerinstances.Activelearningalgorithmscanreducethenumberofinstancestobelabeled,savethelabelingcostsandguaranteethemodelperformanceatthesametime.

ResearchandApplicationofOpticalPowerStateAnalysisBasedonNormalDistribution

HANJun-long

2018, 0(06):  91.  doi:10.3969/j.issn.1006-2475.2018.06.017

Asbtract ( 132 )  

References | Related Articles | Metrics

Inordertoanalyzetheopticalpowerrunningstateinthewholenetwork,inthispaper,thebasicmethodinthetheoriesofprobabilityandstatisticswasused.First,wedistributetheopticalpowerwithfrequencybygraphical,andthenverifyitsnormalityintheory.Finally,webuildthedatamodeltoquantitativeanalysisofopticalpower.Thisresearchwasdeployedinarunningnetworkofrailway,theresultshowesthatitcanimprovetheefficiencyofopticalpowerdatavalueandintelligentmanagement,andcansatisfythepracticalapplication.

ProgressofPerformanceEvaluationMethodologyforTrackers

WANGQuan-ning1,2,ZHOUJin1,LEITao1，TANGZi-li3

2018, 0(06):  95.  doi:10.3969/j.issn.1006-2475.2018.06.018

Asbtract ( 197 )  

References | Related Articles | Metrics

Thenormativeevaluationmethodcanaccuratelyfeedbackalgorithmperformance,comparedifferentalgorithms,promotethedevelopmentoftrackingalgorithmandguideengineeringapplicationonthebasisofobjectivityandfairness.Thispapersummarizedtheresearchprogressoftheperformanceevaluationmethodsfromthreeaspects:evaluationmethods,commonlyuseddatasetsandexistingevaluationprograms.Thispaperbrieflyexplainedthetypeofevaluationmethodsandthedifferenceoftrackingevaluationbetweensingletargetandmulti-targets,gavedetailedanalysisofthecommonlyusedmeasurementindicatorsanditscharacteristics,introducedrepresentativedatasetsandassessmentprojects.Finally,thispaperexploredthedevelopmentofevaluationmethods.

DesignofEmploymentInformationManagementPlatform#br# BasedonBigDataTechnologyandFeatureRecommendation

LIJian，YANGXing，LIJun-cheng，HUANGHan-wen

2018, 0(06):  103.  doi:10.3969/j.issn.1006-2475.2018.06.019

Asbtract ( 153 )  

References | Related Articles | Metrics

Employmentisanimportantjobinvocationalcolleges.Employmentinformationmanagementplatformisanimportantmeansofcollegeemploymentguidance,managementandservice.Thekeytotheapplicationoftheemploymentinformationmanagementplatformisthenumberandqualityoftherecruitmentposition.Thecoreoftheemploymentinformationmanagementplatformistorealizetheeffectiverecommendationofthepositionaccordingtothestudents’employmentexpectation.Atthesametime,therapidcommunicationchannelbetweenthegovernment,theenterprise,theschoolandthestudentwillbeconstructedtoimprovetheemploymentguidanceandservicelevel,andprovidethefeedbackofemploymentsurveyandthefeedbackofemployment.Thefunctionofemploymentstatisticalanalysisprovidessupportfortheoptimizationofprofessionaltraining.Thispaperanalyzesthefunctionsoftheemploymentinformationmanagementplatform,designsandimplementstheplatformbyemployingthesoftwareengineeringideaandtheunifiedmodelingtool,andusingWebtechnology,crawlertechnology,databasetechnology,largedataprocessingtechnologyandrecommendationalgorithm.Thepracticehasshownthattheplatformcanmeettheneedsofpersonalizedemployment,improvethequalityofemploymentandservicelevel.

DesignandRealizationofDistributedTraceabilitySystemofAquaticProducts’Circulation

ZENGXiang-wei1,LIYin2,GUOChang2

2018, 0(06):  108.  doi:10.3969/j.issn.1006-2475.2018.06.020

Asbtract ( 113 )  

References | Related Articles | Metrics

Theconstructionofaquaticproductscirculationqualityandsafetytraceabilitysystemisoneoftheimportantmeasurestoensurethequalityandsafetyofaquaticproducts.Thispaperproposesadesignschemeofdistributedtraceabilitysystemofaquaticproductscirculationincludingnational,provincialandenterprisethreelevelsoftraceabilityplatform.Thesystemisbasedontheretrospectivecodeofaquaticproducts,theeventdataisindexed,anditprovidesthetraceabilityofupstreamtotheaquaticproductproducer,downstreamtraceabilitytotheseller,andcanacquirethecirculationofinformationatanytime.Bythesystem,theconsumptionrightsofChineseconsumersshouldbestronglyprotected,andthesustainabledevelopmentofaquacultureindustryinChinaescortshouldbegot.

Inthepresentsociety,foodsecurityincidentsemergeoneafteranother.Foodsecurityissuehasbecomeanimportantsocialissue.Foodtraceabilityhasproventobeaneffectivemethodforfoodsafety.Thispaperdesignsafoodelectronictraceabilityplatformbasedondistributionframework.Theplatformcanprovideproductionandmanagementserviceforfoodenterprise,forwardandbackwardtraceabilityofthewholecycleoffoodproductionandcirculationforsupervisiondepartments,andvariousmethodsoffoodtraceabilityforthepublic.Bybuildingaunifiedcommoditycirculationdatapoolthatcollectsallthedataamongproduction,circulationandsupervisingdepartments,notonlytheproductionandcirculationinformationofthefoodproductcanbetraced,butalsoitsinspectionandquarantineinformation.ThedatabaseanddatainterfaceoftheplatformisdevelopedbasedonthefoodelectronictraceabilitystandardsformulatedbytheNationalFoodandDrugAdministration.Itsinterfacestandardizationandcompatibilitywithotherfoodtraceabilityplatformscanthusbeguaranteed.TheplatformcurrentlyisrunningatGuangdongprovince.Keysupervisingproductsofinfantformulafoods(includingmilkpowder,riceflour,farina,etc),editableoilandliquoraretraceablebythisplatform.ThepubliccanusetheGuangdongfoodtraceabilityportal,mobileAPP,Wechatortheself-serviceterminalsinthesupermarketstotracefoodproductsbyscanningorinputtingitstraceabilitycodeoritsproductcode,andqueryinformationaboutfoodenterpriselicense,inspectionandquarantine,marketandcirculation,etc.Forproductwithtraceabilitycode,itsauthenticitycanbeverified.Itwillhelptoprovidehealthsafetytothepublicandpromoteconsumerconfidence.

LIYin,LUOHai-biao,LIUDong-cheng,OUYANGYun-xiong,CHENJian-bin,YUANFeng

2018, 0(06):  116.  doi:10.3969/j.issn.1006-2475.2018.06.021

Asbtract ( 48 )  

References | Related Articles | Metrics

Inthepresentsociety,foodsecurityincidentsemergeoneafteranother.Foodsecurityissuehasbecomeanimportantsocialissue.Foodtraceabilityhasproventobeaneffectivemethodforfoodsafety.Thispaperdesignsafoodelectronictraceabilityplatformbasedondistributionframework.Theplatformcanprovideproductionandmanagementserviceforfoodenterprise,forwardandbackwardtraceabilityofthewholecycleoffoodproductionandcirculationforsupervisiondepartments,andvariousmethodsoffoodtraceabilityforthepublic.Bybuildingaunifiedcommoditycirculationdatapoolthatcollectsallthedataamongproduction,circulationandsupervisingdepartments,notonlytheproductionandcirculationinformationofthefoodproductcanbetraced,butalsoitsinspectionandquarantineinformation.ThedatabaseanddatainterfaceoftheplatformisdevelopedbasedonthefoodelectronictraceabilitystandardsformulatedbytheNationalFoodandDrugAdministration.Itsinterfacestandardizationandcompatibilitywithotherfoodtraceabilityplatformscanthusbeguaranteed.TheplatformcurrentlyisrunningatGuangdongprovince.Keysupervisingproductsofinfantformulafoods(includingmilkpowder,riceflour,farina,etc),editableoilandliquoraretraceablebythisplatform.ThepubliccanusetheGuangdongfoodtraceabilityportal,mobileAPP,Wechatortheself-serviceterminalsinthesupermarketstotracefoodproductsbyscanningorinputtingitstraceabilitycodeoritsproductcode,andqueryinformationaboutfoodenterpriselicense,inspectionandquarantine,marketandcirculation,etc.Forproductwithtraceabilitycode,itsauthenticitycanbeverified.Itwillhelptoprovidehealthsafetytothepublicandpromoteconsumerconfidence.