简介：Multilevelphotoncombinedwithbinarypulsepositionmodulation(BPPM)(Manchesterpulsedsignals),isintroducedinthisletter.Initially,errorprobabilityderivationandexplanationforfour-levelphotoncommunicationswiththatBPPMispresented.Next,the2-levelphotoncommunicationsmatchingwithBPPMisproposed.Forperformancecomparison,itisdonewiththattheconventionalschemebyfxingthebackgroundnoiseandalsoincreasingnumberofphotonperslot.Successfullywithapplyingconvolutionalcodingforsystemimproving,theproposedmultilevelphotononBPPMwiththiscodingschemeachieveshighergain.Finally,thisworkalsobeneftstoimprovingforfurtherperformancewhenconsideringwithmultilevelerrorcontrolcodingaswell.

简介：Deepconvolutionalneuralnetworks(DCNNs)haveshownoutstandingperformanceinthefieldsofcomputervision,naturallanguageprocessing,andcomplexsystemanalysis.Withtheimprovementofperformancewithdeeperlayers,DCNNsincurhighercomputationalcomplexityandlargerstoragerequirement,makingitextremelydifficulttodeployDCNNsonresource-limitedembeddedsystems(suchasmobiledevicesorInternetofThingsdevices).NetworkquantizationefficientlyreducesstoragespacerequiredbyDCNNs.However,theperformanceofDCNNsoftendropsrapidlyasthequantizationbitreduces.Inthisarticle,weproposeaspaceefficientquantizationschemewhichuseseightorlessbitstorepresenttheoriginal32-bitweights.Weadoptsingularvaluedecomposition(SVD)methodtodecreasetheparametersizeoffully-connectedlayersforfurthercompression.Additionally,weproposeaweightclippingmethodbasedondynamicboundarytoimprovetheperformancewhenusinglowerprecision.Experimentalresultsdemonstratethatourapproachcanachieveuptoapproximately14xcompressionwhilepreservingalmostthesameaccuracycomparedwiththefull-precisionmodels.TheproposedweightclippingmethodcanalsosignificantlyimprovetheperformanceofDCNNswhenlowerprecisionisrequired.

简介：视觉追踪是在计算机视觉的一个重要区域。怎么处理照明和吸藏问题是一个挑战性的问题。这份报纸论述一篇小说和有效追踪算法处理如此的问题。一方面，一起始的外观总是有的目标清除轮廓，它对照明变化光不变、柔韧。在另一方面，特征在追踪起一个重要作用，在哪个之中convolutional特征显示出有利性能。因此，我们采用卷的轮廓特征代表目标外观。一般来说，一阶的衍生物边坡度操作员在由卷检测轮廓是有效的他们与图象。特别，Prewitt操作员对水平、垂直的边更敏感，当Sobel操作员对斜边更敏感时。内在地，Prewitt和Sobel与对方一起是补足的。技术上说，这份报纸设计二组Prewitt和Sobel边察觉者提取一套完全的convolutional特征，它包括水平、垂直、斜的边特征。在第一个框架，轮廓特征从目标被提取构造起始的外观模型。在有这些轮廓特征的试验性的图象的分析以后，明亮的部分经常提供更有用的信息描述目标特征，这能被发现。因此，我们建议一个方法比较候选人样品和我们仅仅使用明亮的象素的训练模型的类似，它使我们的追踪者有能力处理部分吸藏问题。在得到新目标以后，变化以便改编外观，我们建议相应联机策略逐渐地更新我们的模型。convolutional特征由井综合的Prewitt和Sobel边察觉者提取了的实验表演能是足够有效的学习柔韧的外观模型。九个挑战性的序列上的众多的试验性的结果证明我们的建议途径与最先进的追踪者比较很有效、柔韧。

简介：Blindrecognitionofconvolutionalcodesisnotonlyessentialforcognitiveradio,butalsofornon-cooperativecontext.Thispaperisdedicatedtotheblindidentificationofratek/nconvolutionalencodersinanoisycontextbasedonWalsh-Hadamardtransformationandblockmatrix(WHT-BM).Theproposedalgorithmconstructsasystemofnoisylinearequationsandutilizesallitscoefficientstorecoverparitycheckmatrix.Itisabletomakeuseoffault-tolerantfeatureofWHT,thusprovidingmoreaccurateresultsandachievingbettererrorperformanceinhighrawbiterrorrate(BER)regions.Moreover,itismorecomputationallyefficientwiththeuseoftheblockmatrix(BM)method.

简介：在这份报纸，我们建议了能与深convolutional从食物图象识别盘子类型，食物成分，和煮的方法的一个多工系统神经网络。我们为每个班与至少500幅图象建立了不同食物的360个班的数据集。到数据的噪音，它是从因特网收集了的还原剂，孤立点图象通过与深convolutional特征训练的一个类的SVM被检测并且消除。我们同时训练了一个盘子标识符，一个煮的方法识别器，和一个多标签成分察觉者。他们在深网络体系结构分享一些低级的层。建议框架与手工制作的特征，和识别器和成分察觉者能被用于没在训练数据集被包括为用户提供引用信息的盘子的煮的方法比传统的方法显示出更高的精确性。

简介：无

简介：Thispaperconcernstheproblemofobjectsegmentationinreal-timeforpickingsystem.Aregionproposalmethodinspiredbyhumanglancebasedontheconvolutionalneuralnetworkisproposedtoselectpromisingregions,allowingmoreprocessingisreservedonlyfortheseregions.Thespeedofobjectsegmentationissignificantlyimprovedbytheregionproposalmethod.Bythecombinationoftheregionproposalmethodbasedontheconvolutionalneuralnetworkandsuperpixelmethod,thecategoryandlocationinformationcanbeusedtosegmentobjectsandimageredundancyissignificantlyreduced.Theprocessingtimeisreducedconsiderablybythistoachievetherealtime.Experimentsshowthattheproposedmethodcansegmenttheinterestedtargetobjectinrealtimeonanordinarylaptop.

简介：Synchronouschipsealisanadvancedroadconstructingtechnology,andthegravelcoveragerateisanimportantindicatoroftheconstructionquality.Inthispaper,anovelapproachforgravelcoverageratemeasurementisproposedbasedondeeplearning.Convolutionalneuralnetwork(CNN)isusedtosegmenttheimageofgroundcoveredwithgravels,andthegravelcoveragerateiscomputedbythepercentageofgravelpixelsinthesegmentedimage.Thegravelcoverageratedatasetformodeltrainingandtestingisbuilt.Theperformanceoffullyconvolutionalneuralnetwork(FCN)andU-Netmodelinthedatasetistested.AbettermodelnamedGravelNetisconstructedbasedonU-Net.Thescaledexponentiallinearunit(SELU)isemployedintheGravelNettoreplacethepopularcombinationofrectifiedlinearunit(ReLU)andbatchnormalization(BN).Dataaugmentationandalphadropoutareperformedtoreduceoverfitting.Theexperimentalresultsdemonstratetheeffectivenessandaccuracyofourproposedmethod.OurtrainedGravelNetachievesthemeangravelcoveragerateerrorof0.35%ontestdataset.

简介：在这份报纸，我们比较了联合网络隧道编码的表演(JNCC)为多点传送当独占时，用低密度同等值支票(LDPC)的继电器网络作为隧道代码编码，Convolutional编码或(XOR)编码的网络在中间的继电器节点使用了。多点传送继电器传播是二个固定继电器节点在第二在作出贡献的传播计划的一种类型在基础收发器车站(BTS)和一双活动车站之间的端对端的传播跳跃。我们认为一个方法和二个方法多点传送评估位错误率(BER)和产量性能的情形。是否使用XOR网络在中间的继电器节点编码，被看了那，一样的传播因此在更少的时间槽变得可能产量性能能被改进。而且我们也在建议系统模型，差异和multiplexing获得在被考虑了讨论了二种可能的情形。它值得通知那BER和产量为LDPC代码完成了比对讨论的所有计划的Convolutional代码好。

简介：Oneofthetechnicalbottlenecksoftraditionallaser-inducedbreakdownspectroscopy(LIBS)isthedifficultyinquantitativedetectioncausedbythematrixeffect.Totroubleshootthisproblem,thispaperinvestigatedacombinationoftime-resolvedLIBSandconvolutionalneuralnetworks(CNNs)toimproveKdeterminationinsoil.Thetime-resolvedLIBScontainedtheinformationofbothwavelengthandtimedimension.Thespectraofwavelengthdimensionshowedthecharacteristicemissionlinesofelements,andthoseoftimedimensionpresentedtheplasmadecaytrend.Theone-dimensionaldataofLIBSintensityfromtheemissionlineat766.49nmwereextractedandcorrelatedwiththeKconcentration,showingapoorcorrelationofR^2c=0.0967,whichiscausedbythematrixeffectofheterogeneoussoil.Forthewavelengthdimension,thetwo-dimensionaldataoftraditionalintegratedLIBSwereextractedandanalyzedbyanartificialneuralnetwork(ANN),showingR^2v=0.6318andtherootmeansquareerrorofvalidation(RMSEV)=0.6234.Forthetimedimension,thetwo-dimensionaldataoftime-decayLIBSwereextractedandanalyzedbyANN,showingR^2v=0.7366andRMSEV=0.7855.Thesehigherdeterminationcoefficientsrevealthatboththenon-KemissionlinesofwavelengthdimensionandthespectraldecayoftimedimensioncouldassistinquantitativedetectionofK.However,duetolimitedcalibrationsamples,thetwo-dimensionalmodelspresentedover-fitting.Thethree-dimensionaldataoftime-resolvedLIBSwereanalyzedbyCNNs,whichextractedandintegratedtheinformationofboththewavelengthandtimedimension,showingtheR^2v=0.9968andRMSEV=0.0785.CNNanalysisoftime-resolvedLIBSiscapableofimprovingthedeterminationofKinsoil.