Comparative survey on non linear filtering methods : the quantization and the particle filtering approaches Afef SELLAMIOverviewNon linear filter estimatorsSlide 4Bayes FilterSlide 6Slide 7Quantization based filtersZero order schemeSlide 10Recalling Taylor SeriesFirst order schemesOne step recursive schemeSlide 14Two step recursive schemeSlide 16Comparisons of convergence rateSlide 18Particle filteringImportance samplingSequential importance sampling (SIS) filterSIS Filter AlgorithmSampling-Importance Resampling(SIR)Slide 24Slide 25Elements for a comparisonComplexity comparisonNumerical performancesKalman filter (KF)Canonical stochastic volatility model (SVM)Explicit non linear filterNumerical performance ResultsNumerical performance Results : Convergence rate improvementSlide 34Slide 35ConclusionsComparative survey on non linear filtering methods : thequantization and the particle filtering approachesAfef SELLAMIChang Young KimOverviewIntroductionBayes filtersQuantization based filtersZero order schemeFirst order schemesParticle filtersSequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterComparison of two approachesSummaryNon linear filter estimatorsQuantization based filtersZero order schemeFirst order schemesParticle filtering algorithms:Sequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterOverviewIntroductionBayes filtersQuantization based filtersZero order schemeFirst order schemesParticle filtersSequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterComparison of two approachesSummaryBayesian approach: We attempt to construct the πnf of the state given all measurements.PredictionCorrectionBayes FilterOne step transition bayes filter equationBy introducint the operaters , sequential definition of the unnormalized filter πnForward ExpressionBayes FilterOverviewIntroductionBayes filtersQuantization based filtersZero order schemeFirst order schemesParticle filtersSequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterComparison of two approachesSummaryQuantization based filtersZero order schemeFirst order schemesOne step recursive first order schemeTwo step recursive first order schemeZero order schemeQuantizationSequential definition of the unnormalized filter πnForward ExpressionZero order schemeRecalling Taylor Series Let's call our point x0 and let's define a new variable that simply measures how far we are from x0 ; call the variable h = x –x0.Taylor Series formulaFirst Order Approximation:Introduce first order schemes to improve the convergence rate of the zero order schemes.Rewriting the sequential definition by mimicking some first order Taylor expansion:Two schemes based on the different approximation by One step recursive scheme based on a recursive definition of the differential term estimator. Two step recursive scheme based on an integration by part transformation of conditional expectation derivative.First order schemesOne step recursive schemeThe recursive definition of the differential term estimatorForward ExpressionTwo step recursive schemeAn integration by part formulawherewhereComparisons of convergence rateZero order schemeFirst order schemesOne step recursive first order schemeTwo step recursive first order schemeOverviewIntroductionBayes filtersQuantization based filtersZero order schemeFirst order schemesParticle filtersSequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterComparison of two approachesSummaryParticle filteringConsists of two basic elements:Monte Carlo integrationImportance samplinglimL ! 1LX`=1w`f(x`) =Zf(x )p(x)dxp(x) ¼LX`=1w`±x`Importance samplingProposal distribution: easy to sample from Original distribution: hard to sample from, easy to evaluate Ex[ f (x)] =Zp(x)f (x)dx=Zp(x)q(x)f(x)q(x)dx¼1LLX`=1p(x`)q(x`)f(x`)Importanceweights x`» q(¢)wl=p(x`)q(x`)we want samples fromand make the following importance sampling identificationsSequential importance sampling (SIS) filterProposal distribution Distribution from which we want to sample1 1 1( ) ( | ) ( | ) ( )t t t t t t tBel x p y x p x x Bel x dxh- - -=�1 1( ) ( | ) ( )t t tq x p x x Bel x- -=( ) ( )tp x Bel x=draw xit1 from Bel(xt1)draw xit from p(xt | xit1)Importance factor for xit:1 11 1( )( )( | ) ( | ) ( )( | ) ( )( | )itt t t t tt t tt tp xwq xp y x p x x Bel xp x x Bel xp y xh- -- -==�1 1 1( ) ( | ) ( | ) ( )t t t t t t tBel x p y x p x x Bel x dxh- - -=�SIS Filter AlgorithmSampling-Importance Resampling(SIR)Problems of SIS:Weight DegenerationSolution RESAMPLINGResampling eliminates samples with low importance weights and multiply samples with high importance weightsReplicate particles when the effective number of particles is below a threshold 211( )effnikiNw==�Sampling-Importance Resampling(SIR)( )111,nikixn-=� �� ��x{ }( ) ( )1,ni ik kix w=( )111,nikixn+=� �� ��{ }( ) ( )1 11,ni ik kix w+ +=( )211,nikixn+=� �� ��Sensor modelUpdateResamplingPredictionOverviewIntroductionBayes filtersQuantization based filtersZero order schemeFirst order schemesParticle filtersSequential importance sampling (SIS) filterSampling-Importance Resampling(SIR) filterComparison of two approachesSummaryElements for a comparisonComplexityNumerical performances in three state models:Kalman filter (KF)Canonical stochastic volatility model (SVM)Explicit non linear filterComplexity comparisonZero order schemeC0N2One step recursive first order schemeC1N2d3Two step recursive first order schemeC2N2dSIS particle filterC3NSIR particle filterC4NNumerical performances Three models chosen to make up the benchmark.Kalman filter (KF)Canonical stochastic volatility model (SVM)Explicit non linear filterKalman filter (KF)Both signal and observation equations are linear with Gaussian independent noises.Gaussian process which parameters (the two first moments) can be computed sequentially by a deterministic algorithm (KF)Canonical stochastic volatility model (SVM)The time discretization of a continuous diffusion model.State ModelExplicit non
or
We will never post anything without your permission.
Don't have an account? Sign up