学科分类
/ 1
4 个结果
  • 简介:

  • 标签:
  • 简介:Regardforthefuzzinessandtherandomnessinsomeacousticfields,amethodforthenumericalanalysisofthe2DacousticfieldwithFuzzy-Randomparameterswasproposedbasedontheequivalentconversionofinformationentropy.Intheproposedmethod,afuzzyrandomacousticfieldwastreatedasapurefuzzyacousticfieldorapurerandomacousticfieldbytransformingallthevariablesintofuzzyvariablesorrandomvariables.Perturbationfiniteelementmethodsforanalyzingthetwo-dimensionalacousticfuzzyandrandomfieldarededuced.Thesoundpressureresponseofa2Dacoustictubeandthe2Dacousticcavityofacarwithfuzzy-randomparameterswereanalyzedbytheproposedmethodandtheMonteCarlomethod,theresultsshowthattheproposedmethodcanbewellappliedtothenumericalanalysisofthe2Dacousticfieldwithfuzzy-randomparameters,andhasgoodprospectofengineeringapplication.

  • 标签: 数值分析方法 随机参数 模糊性 声场 二维 蒙特卡罗方法
  • 简介:Numericalanalysisofthree-dimensionalsoundpropagationinsoft-softorsoft-hardcircularductswithcircumferentialandaxialmodesofsoundsourcesattheinlethasbeencarriedout.Inthispaper,thenumericalmethodandthesamplesareofferedandtheeffectsofcircumferentialandaxialmodesonnumericalresultsarediscussedindetail.

  • 标签: INLET lined AXIAL circular CONVERGENT DISCONTINUITY
  • 简介:Foraccuracyandrapidityofaudioeventdetectioninthemass-dataaudioprocessingtasks,agenericmethodofrapidlyrecognizingaudioeventbasedon2D-HaaracousticsuperfeaturevectorandAdaBoostisproposed.Firstly,itcombinescertainnumberofcontinuousaudioframestobean'acousticfeatureimage',secondly,usesAdaBoost.MHorfastRandomAdaBoostfeatureselectionalgorithmtoselecthighrepresentative2D-Haarpatterncombinationstoconstructsuperfeaturevectors;thirdly,analyzesthecommonalityanddifferencesbetweensubcategories,thenextractscommonfeaturesandreducesdifferentfeaturestoobtainagenericaudioeventtemplate,whichcansupporttheaccurateidentificationofmultiplesub-classesanddetectandlocatethespecificaudioeventfromtheaudiostreamaccurately.Experimentalresultsshowthattheuseof2D-Haaracousticfeaturesupervectorcanmakerecognitionaccuracy5%higherthanonesthatMFCC,PLP,LPCCandothertraditionalacousticfeaturesyielded,andcanmakethetrainingprocessing7-20timesfasterandtherecognitionprocessing5-10timesfaster,itcanevenachieveanaverageprecisionof93.38%,anaveragerecallof95.03%undertheoptimalparameterconfigurationfoundbygridmethod.Aboveall,itcanprovideanaccurateandfastmass-dataprocessingmethodforaudioeventdetection.

  • 标签: 事件检测 特征向量 音频帧 ADABOOST 声学特征 平均精度