Fully probabilistic knowledge expression and incorporation

An exploitation of prior knowledge in parameter estimation becomes vital whenever measured data is not informative enough. Elicitation of quantified prior knowledge is a well-elaborated art in societal and medical applications but not in the engineering ones. Frequently required involvement of a facilitator is mostly unrealistic due to either facilitator’s high costs or complexity of modelled relationships that cannot be grasped by humans. This paper provides a facilitator-free approach based on an advanced knowledgesharing methodology. It presents the approach on commonly available types of knowledge and applies the methodology to a normal controlled autoregressive model.

[1]  M. Kárný.  Adaptive Systems: Local Approximators? , 1998 .

[2]  Miroslav Kárný.  Parametrization of multi-output autoregressive-regressive models for self-tuning control , 1992, Kybernetika.

[3]  Tatiana V. Guy,et al.  How to exploit external model of data for parameter estimation? , 2006 .

[4]  Petr Nedoma,et al.  Quantification of prior information revised , 2001 .

[5]  M. Birattari,et al.  Lazy learning for local modelling and control design , 1999 .

[6]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[7]  Ferenc Szeifert,et al.  Incorporating prior knowledge in fuzzy model identification , 2000, Int. J. Syst. Sci..

[8]  J. F. C. Kingman,et al.  Information and Exponential Families in Statistical Theory , 1980 .

[9]  John Ladbrook,et al.  Using a simulation model for knowledge elicitation and knowledge management , 2004, Simul. Model. Pract. Theory.

[10]  Tatiana V. Guy,et al.  Fully probabilistic control design , 2006, Syst. Control. Lett..

[11]  E. Mosca.  Optimal, Predictive and Adaptive Control , 1994 .

[12]  David Ríos Insua,et al.  Robust Bayesian analysis , 2000 .

[13]  G. Bierman.  Factorization methods for discrete sequential estimation , 1977 .

[14]  V. G. D. Fonseca,et al.  Distortion in statistical inference: the distinction between data contamination and model deviation , 2006 .

[15]  Miroslav Kárný,et al.  Optimized bayesian dynamic advising : theory and algorithms , 2006 .

[16]  David Clarke.  Pretuning and adaptation of PI controllers , 2003 .

[17]  A. O'Hagan,et al.  Statistical Methods for Eliciting Probability Distributions , 2005 .

[18]  Alessandra Guglielmi,et al.  Methods for global prior robustness under generalized moment conditions , 2000 .

[19]  Kotagiri Ramamohanarao,et al.  DeEPs: A New Instance-Based Lazy Discovery and Classification System , 2004, Machine Learning.

[20]  O. Barndorff-Nielsen.  Information and Exponential Families in Statistical Theory , 1980 .

[21]  Bradley P. Carlin,et al.  BAYES AND EMPIRICAL BAYES METHODS FOR DATA ANALYSIS , 1996, Stat. Comput..

[22]  Robert L. Kosut,et al.  Iterative Adaptive Control: Windsurfing with Confidence , 2001 .

[23]  Ivan Nagy,et al.  When has estimation reached a steady state? The Bayesian sequential test , 2005 .

[24]  Miroslav Kárný,et al.  Merging of data knowledge in bayesian estimation , 2005, ICINCO.

[25]  Rodney W. Johnson,et al.  Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy , 1980, IEEE Trans. Inf. Theory.

[26]  João M. Lemos,et al.  Survey of industrial optimized adaptive control , 2012 .

[27]  Huaiyu Zhu.  On Information and Sufficiency , 1997 .

[28]  D. Kerridge.  Inaccuracy and Inference , 1961 .

[29]  Kweku-Muata Osei-Bryson,et al.  Supporting knowledge elicitation and consensus building for dempster‐shafer decision models , 2003, Int. J. Intell. Syst..

[30]  J. Bernardo.  Expected Information as Expected Utility , 1979 .

[31]  Petr Nedoma,et al.  Prior information in structure estimation , 2003 .

[32]  Václav Peterka,et al.  Bayesian system identification , 1979, Autom..

[33]  Orhan Arikan,et al.  Maximum likelihood estimation of Gaussian mixture models using stochastic search , 2012, Pattern Recognit..

[34]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[35]  Karl Johan Åström,et al.  Relay Feedback Auto-tuning of Process Controllers – A Tutorial Review , 2002 .

[36]  Miroslav Kárný.  Quantification of prior knowledge about global characteristics of linear normal model , 1984, Kybernetika.