Title :
Diffusion estimation of state-space models: Bayesian formulation
Author_Institution :
Inst. of Inf. Theor. & Autom., Prague, Czech Republic
Abstract :
The paper studies the problem of decentralized distributed estimation of the state-space models from the Bayesian viewpoint. The adopted diffusion strategy, consisting of collective adaptation to new data and combination of posterior estimates, is derived in general model-independent form. Its particular application to the celebrated Kalman filter demonstrates the ease of use, especially when the measurement model is rewritten into the exponential family form and a conjugate prior describes the estimated state.
Keywords :
Bayes methods; Kalman filters; estimation theory; state-space methods; Bayesian formulation; Bayesian viewpoint; adopted diffusion strategy; celebrated Kalman filter; collective adaptation; decentralized distributed estimation; diffusion estimation; estimated state; posterior estimate; state-space model; Abstracts; Artificial neural networks; Bayes methods; Trajectory; Yttrium; Bayesian estimation; Distributed estimation; diffusion networks; state-space models;
Conference_Titel :
Machine Learning for Signal Processing (MLSP), 2014 IEEE International Workshop on
Conference_Location :
Reims
DOI :
10.1109/MLSP.2014.6958920