Publica
Hier finden Sie wissenschaftliche Publikationen aus den FraunhoferInstituten. Bayesian processing of big data using log homotopy based particle flow filters
 Institute of Electrical and Electronics Engineers IEEE; IEEE Aerospace and Electronic Systems Society AESS; International Society of Information Fusion ISIF: Symposium on Sensor Data Fusion: Trends, Solutions, Applications, SDF 2017 : Bonn, Germany, October 1012, 2017 Piscataway, NJ: IEEE, 2017 ISBN: 9781538631034 ISBN: 9781538631027 ISBN: 9781538631041 pp.1318 
 Symposium on Sensor Data Fusion  Trends, Solutions, Applications (SDF) <11, 2017, Bonn> 

 English 
 Conference Paper 
 Fraunhofer FKIE () 
Abstract
Bayesian recursive estimation using large volumes of data is a challenging research topic. The problem becomes particularly complex for high dimensional nonlinear state spaces. Markov chain Monte Carlo (MCMC) based methods have been successfully used to solve such problems. The main issue when employing MCMC is the evaluation of the likelihood function at every iteration, which can become prohibitively expensive to compute. Alternative methods are therefore sought after to overcome this difficulty. One such method is the adaptive sequential MCMC (ASMCMC), where the use of the confidence sampling is proposed as a method to reduce the computational cost. The main idea is to make use of the concentration inequalities to subsample the measurements for which the likelihood terms are evaluated. However, ASMCMC methods require appropriate proposal distributions. In this work, we propose a novel ASMCMC framework in which the loghomotopy based particle flow filter form an adaptive proposal. We show the performance can be significantly enhanced by our proposed algorithm, while still maintaining a comparatively low processing overhead.