Advertisement

Applied Intelligence

, Volume 43, Issue 4, pp 802–824 | Cite as

An explication of uncertain evidence in Bayesian networks: likelihood evidence and probabilistic evidence

Uncertain evidence in Bayesian networks
  • Ali Ben Mrad
  • Véronique Delcroix
  • Sylvain Piechowiak
  • Philip Leicester
  • Mohamed Abid
Article

Abstract

This paper proposes a systematized presentation and a terminology for observations in a Bayesian network. It focuses on the three main concepts of uncertain evidence, namely likelihood evidence and fixed and not-fixed probabilistic evidence, using a review of previous literature. A probabilistic finding on a variable is specified by a local probability distribution and replaces any former belief in that variable. It is said to be fixed or not fixed regarding whether it has to be kept unchanged or not after the arrival of observation on other variables. Fixed probabilistic evidence is defined by Valtorta et al. (J Approx Reason 29(1):71–106 2002) under the name soft evidence, whereas the concept of not-fixed probabilistic evidence has been discussed by Chan and Darwiche (Artif Intell 163(1):67–90 2005). Both concepts have to be clearly distinguished from likelihood evidence defined by Pearl (1988), also called virtual evidence, for which evidence is specified as a likelihood ratio, that often represents the unreliability of the evidence. Since these three concepts of uncertain evidence are not widely understood, and the terms used to describe these concepts are not well established, most Bayesian networks engines do not offer well defined propagation functions to handle them. Firstly, we present a review of uncertain evidence and the proposed terminology, definitions and concepts related to the use of uncertain evidence in Bayesian networks. Then we describe updating algorithms for the propagation of uncertain evidence. Finally, we propose several results where the use of fixed or not-fixed probabilistic evidence is required.

Keywords

Bayesian network Uncertain evidence Probabilistic evidence Likelihood finding Soft evidence Virtual evidence 

References

  1. 1.
    Ahuactzin JM, Bessière P, Mazer E, Mekhnacha K (2014) ProBT, Computer software. ProBayes, Grenoble. http://www.probayes.com/ Google Scholar
  2. 2.
    Badsberg JH, Malvestuto FM (2001) An implementation of the iterative proportional fitting procedure by propagation trees. Comput Stat Data Anal 37:297–322zbMATHMathSciNetCrossRefGoogle Scholar
  3. 3.
    Baldwin JF, Tomaso ED (2003) Inference and learning in fuzzy bayesian networks. In: The 12th IEEE International conference on fuzzy Systems, FUZZ-IEEE 2003, St. Louis, pp 630–635Google Scholar
  4. 4.
    Ben Mrad A, Delcroix V, Maalej MA, Piechowiak S, Abid M (2012) Uncertain evidence in Bayesian networks : Presentation and comparison on a simple example. In: 2012 Proceedings of the 14th conference on information processing and management of uncertainty in knowledge-based systems, IPMU, Catania, pp 39–48Google Scholar
  5. 5.
    Ben Mrad A, Delcroix V, Piechowiak S, Maalej MA, Abid M (2013) Understanding soft evidence as probabilistic evidence: Illustration with several use cases. In: 2013 5th international conference on modeling, simulation and applied optimization (ICMSAO), pp 1–6Google Scholar
  6. 6.
    Ben Mrad A, Maalej MA, Delcroix V, Piechowiak S., Abid M (2011) Fuzzy evidence in Bayesian networks. In: Proceedings of computing, soft, recognition, pattern, DalianGoogle Scholar
  7. 7.
    Benferhat S, Tabia K (2012) Inference in possibilistic network classifiers under uncertain observations. Ann Math Artif Intell 64(2–3):269–309zbMATHMathSciNetCrossRefGoogle Scholar
  8. 8.
    Bessière P, Mazer E, Ahuactzin JM, Mekhnacha K (2013) Bayesian Programming. CRC PressGoogle Scholar
  9. 9.
    Bilmes J (2004) On soft evidence in Bayesian networks. Tech. Rep. UWEETR-2004-00016. Department of Electrical Engineering, University of Washington, SeattleGoogle Scholar
  10. 10.
    Birtles N, Fenton N, Neil M, Tranham E (2014) AgenaRisk manual (Version 6.1) Computer software. http://www.agenarisk.com/
  11. 11.
    Bloemeke M (1998) Agent encapsulated Bayesian networks. Ph.D. thesis, Department of Computer Science, University of South CarolinaGoogle Scholar
  12. 12.
    Butz CJ, Fang F (2005) Incorporating evidence in Bayesian networks with the select operator. In: Proceedings of the 18th Canadian conference on artificial intelligence. Springer-Verlag, pp 297–301Google Scholar
  13. 13.
    Chan H (2005) Sensitivity analysis of probabilistic graphical models. Ph.D. thesis. University of California, Los AngelesGoogle Scholar
  14. 14.
    Chan H, Darwiche A (2004) Sensitivity analysis in Bayesian networks: From single to multiple parameters. In: UAI, pp 67– 75Google Scholar
  15. 15.
    Chan H, Darwiche A (2005) On the revision of probabilistic beliefs using uncertain evidence. Artif Intell 163(1):67–90zbMATHMathSciNetCrossRefGoogle Scholar
  16. 16.
    Cooper GF (1990) The computational complexity of probabilistic inference using Bayesian belief networks. Artif Intell 42:393–405zbMATHCrossRefGoogle Scholar
  17. 17.
    Dagum P, Luby M (1993) Approximating probabilistic inference in Bayesian belief networks is NP-hard. Artif Intell 60:141– 153zbMATHMathSciNetCrossRefGoogle Scholar
  18. 18.
    D’Ambrosio B, Takikawa MDU (2000) Representation for dynamic situation modeling. Technical report, Information Extraction and Transport, Inc.Google Scholar
  19. 19.
    D’Angelo MFSV, Palhares RM, Cosme LB, Aguiar LA, Fonseca FS, Caminhas WM (2014) Fault detection in dynamic systems by a fuzzy/bayesian network formulation. Appl Soft Comput 21:647–653CrossRefGoogle Scholar
  20. 20.
    Darwiche A (2009) Modeling and reasoning with Bayesian networks. Cambridge University Press, CambridgezbMATHCrossRefGoogle Scholar
  21. 21.
    Darwiche A (2014) Samlam Computer software. University of California, Los Angeles. http://reasoning.cs.ucla.edu/samiam Google Scholar
  22. 22.
    Delcroix V, Sedki K, Lepoutre FX (2013) A Bayesian network for recurrent multi-criteria and multi-attribute decision problems, Choosing a manual wheelchair. Expert Syst Appl 40(7):2541–2551CrossRefGoogle Scholar
  23. 23.
    Deming WE, Stephan FF (1940) On a least square adjustment of a sampled frequency table when the expected marginal totals are known. Ann Math Stat 11:427–444MathSciNetCrossRefGoogle Scholar
  24. 24.
    Druzdzel MJ (2014) Genie smile, Version 20. Computer software. Decision systems laboratory. University of Pittsburgh, Pennsylvania. http://genie.sis.pitt.edu Google Scholar
  25. 25.
    Dubois D, Moral S, Prade H (1998) Belief change rules in ordinal and numerical uncertainty theories. In: Gabbay D, Smets P, Dubois D, Prade H (eds) Belief change vol. 3 of the handbook of defeasible reasoning and uncertainty systems, management. Kluwer Academic Publishers, Dordrecht, pp 311–392Google Scholar
  26. 26.
    Elvira (2014) Elvira project, http://leo.ugr.es/elvira/
  27. 27.
    Fattah MA (2014) A hybrid machine learning model for multi-document summarization. Appl Intell 40 (4):592–600CrossRefGoogle Scholar
  28. 28.
    Ferreira L, Borenstein D (2012) A fuzzy-bayesian model for supplier selection. Expert Syst Appl 39 (9):7834–7844CrossRefGoogle Scholar
  29. 29.
    Flores MJ, Gámez JA, Martínez AM, Puerta JM (2011) Handling numeric attributes when comparing Bayesian network classifiers: Does the discretization method matter?. Appl Intell 34(3):372– 385CrossRefGoogle Scholar
  30. 30.
    Gacquer D, Delcroix V, Delmotte F, Piechowiak S (2011) Comparative study of supervised classification algorithms for the detection of atmospheric pollution. Eng Appl Artif Intell 24(6):1070–1083CrossRefGoogle Scholar
  31. 31.
    Giordano R, D’Agostino D, Apollonio C, Lamaddalena N, Vurro M (2013) Bayesian belief network to support conflict analysis for groundwater protection: The case of the Apulia region. J Environ Manag 115C:136–146CrossRefGoogle Scholar
  32. 32.
    Henrion M (2014) Analytica, version computer software. Lumina decision systems, Los Gatos. http://www.lumina.com/
  33. 33.
    Højsgaard S (2014) gRain, (Version 1.2-3) Computer software. Aalborg University, Denmark. http://people.math.aau.dk/sorenh/software/gR/ Google Scholar
  34. 34.
    Jeffrey RC (1990) The logic of decision, 2nd edn. University of Chicago Press, Chicago, p 246Google Scholar
  35. 35.
    Jensen FV, Nielsen TD (2007) Bayesian networks and decision graphs, 2nd. Springer Publishing Company IncorporatedGoogle Scholar
  36. 36.
    Jiroušek R (1991) Solution of the marginal problem and decomposable distributions. Kybernetika 27:403–412zbMATHMathSciNetGoogle Scholar
  37. 37.
    Jiroušek R, Přeučil S (1995) On the effective implementation of the iterative proportional fitting procedure. Comput Stat Data Anal 19(2):177–189zbMATHCrossRefGoogle Scholar
  38. 38.
    Jouffe L, Munteanu P (2014) BayesiaLab, Laval. http://www.bayesia.com
  39. 39.
    Keppens J, Shen Q, Price C (2011) Compositional bayesian modelling for computation of evidence collection strategies. Appl Intell 35(1):134–161CrossRefGoogle Scholar
  40. 40.
    Kim YG, Valtorta M, Vomlel J (2004) A prototypical system for soft evidential update. Appl Intell 21 (1):81–97zbMATHCrossRefGoogle Scholar
  41. 41.
    Kjaerulff U, Madsen A (2013) Bayesian networks and influence diagrams: A guide to construction and analysis, vol 22, 2nd edn. SpringerGoogle Scholar
  42. 42.
    Korb K, Nicholson A (2010) Bayesian artificial intelligence, 2nd. Chapman and Hall, londonGoogle Scholar
  43. 43.
    Koski T, Noble J (2009) Bayesian networks: An introduction. Wiley series in probability and statistics. Wiley, ChichesterCrossRefGoogle Scholar
  44. 44.
    Krieg ML (2001) A tutorial on Bayesian belief networks. Technical Report DSTO-TN-0403, surveillance systems division electronics and surveillance research laboratory. Defense science and technology organisation, EdinburghGoogle Scholar
  45. 45.
    Kruithof R (1937) Telefoonverkeersrekening. De Ingenieur 52:15–25Google Scholar
  46. 46.
    Landuyt D, Broekx S, D’hondt R, Engelen G, Aertsens J, Goethals P (2013) A review of Bayesian belief networks in ecosystem service modelling. Environ Model Softw 46:1–11CrossRefGoogle Scholar
  47. 47.
    Langevin S (2011) Knowledge representation, communication, and update in probability-based multiagent systems. Ph.D. thesis. University of South Carolina, Columbia. AAI3454755Google Scholar
  48. 48.
    Langevin S, Valtorta M (2008) Performance evaluation of algorithms for soft evidential update in Bayesian networks: First results. In: SUM. 284–297Google Scholar
  49. 49.
    Langevin S, Valtorta M, Bloemeke M (2010) Agent-encapsulated Bayesian networks and the rumor problem. In: AAMAS ’10 Proceedings of the 9th international conference on autonomous agents and multiagent systems, vol 1, pp 1553–1554Google Scholar
  50. 50.
    Laskey KB, Wright EJ, da Costa PCG (2010) Envisioning uncertainty in geospatial information. Int J Approx Reason 51(2):209–223CrossRefGoogle Scholar
  51. 51.
    Lauritzen SL (2014) Hugin, Version 8.0 Computer software, Aalborg. http://www.hugin.com
  52. 52.
    Lauritzen SL, Spiegelhalter DJ (1988) Local computations with probabilities on graphical structures and their application to expert systems. J R Stat Soc Ser B 50:157–224. doi: 10.2307/2345762 zbMATHMathSciNetGoogle Scholar
  53. 53.
    Leicester PA, Goodier CI, Rowley P (2012) Community energy delivers megawatts, pounds, carbon reductions, etcetera. In: Midlands energy graduate school (MEGS)Google Scholar
  54. 54.
    Leicester PA, Goodier CI, Ro wley P (2013) Using a Bayesian network to evaluate the social, economic and environmental impacts of community renewable energy. In: Clean technology for smart cities and buildings (CISB AT)Google Scholar
  55. 55.
    Madsen AL, Jensen FV (1999) Lazy propagation: A junction tree inference algorithm based on lazy evaluation. Artif Intell 113(1–2):203–245zbMATHMathSciNetCrossRefGoogle Scholar
  56. 56.
    Minka T, Winn J (2014) Infer.NET, (Version 205) Computer software. Microsoft Research, Cambridge. http://research.microsoft.com/en-us/um/cambridge/projects/infernet/default.aspx Google Scholar
  57. 57.
    Murphy K (2014) Bayesian Network Toolbox (BNT), (Version 1.0.7) Computer software. MIT AI lab, Cambridge. http://www.cs.ubc.ca/murphyk/Software/BNT/bnt.html Google Scholar
  58. 58.
    Norsys (2014) Netica application, (Version 5.12) Computer software. Norsys Software Corp, Vancouver. http://www.norsys.com Google Scholar
  59. 59.
    Pan H, Liu L (2000) Fuzzy bayesian networks - A general formalism for representation, inference and learning with hybrid bayesian networks, vol 14, pp 941–962Google Scholar
  60. 60.
    Pan R, Peng Y, Ding Z (2006) Belief update in Bayesian networks using uncertain evidence. In: ICTAI, pp 441–444Google Scholar
  61. 61.
    Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers, San MateoGoogle Scholar
  62. 62.
    Peng Y, Ding Z (2005) Modifying bayesian networks by probability constraints. In: Proceedings of the 21st Conference in uncertainty in artificial intelligence, Edinburg July 26-29 UAI ’05, pp 459–466Google Scholar
  63. 63.
    Peng Y, Ding Z, Zhang S, Pan R (2012) Bayesian network revision with probabilistic constraints. Int J Uncertainty Fuzziness Knowledge Based Syst 20(3):317–337zbMATHMathSciNetCrossRefGoogle Scholar
  64. 64.
    Peng Y, Zhang S, Pan R (2010) Bayesian network reasoning with uncertain evidences. Int J Uncertainty Fuzziness Knowledge Based Syst 18(5):539–564zbMATHMathSciNetCrossRefGoogle Scholar
  65. 65.
    Pourret O, Naïm P, Marcot B (2008) Bayesian networks: A practical guide to applications, statistics in practice, WileyGoogle Scholar
  66. 66.
    Sandiford J (2014) Bayes Server, (Version 5.5) Computer software, East Preston. http://www.bayesserver.com/
  67. 67.
    Tang H, Liu S (2007) Basic theory of fuzzy bayesian networks and its application in machinery fault diagnosis. IEEE Computer Society, WashingtonGoogle Scholar
  68. 68.
    Tomaso ED, Baldwin JF (2008) An approach to hybrid probabilistic models. Int J Approximate Reasoning 47(2):202– 218zbMATHCrossRefGoogle Scholar
  69. 69.
    Valtorta M, Kim YG, Vomlel J (2002) Soft evidential update for probabilistic multiagent systems. Int J Approx Reason 29(1):71–106zbMATHMathSciNetCrossRefGoogle Scholar
  70. 70.
    Vomlel J (2004) Integrating inconsistent data in a probabilistic model. J Appl Non-Classical Log 14(3):367–386zbMATHMathSciNetCrossRefGoogle Scholar
  71. 71.
    Vomlel J, Probabilistic reasoning with uncertain evidence. Neural network world (2004) Int J Neural Mass-Parallel Comput Inf Syst 14(5):453–465Google Scholar
  72. 72.
    Wang Y, Zhang NL, Chen T (2008) Latent tree models and approximate inference in Bayesian networks. J Artif Intell Res 32:879–900zbMATHMathSciNetGoogle Scholar
  73. 73.
    Yuan C, Lim H, Lu TC (2011) Most relevant explanation in Bayesian networks. J Artif Intell Res 42 (1):309–352zbMATHMathSciNetGoogle Scholar
  74. 74.
    Zhang S, Peng Y, Wang X (2008) An Efficient Method for Probabilistic Knowledge Integration. In: Proceedings of The 20th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2008), November 3–5, 2008, vol 2. Dayton, pp 179– 182Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.LAMIH, UMR CNRS 8201 (Laboratory of Industrial and Human Automation control, Mechanical engineering and Computer Science)University of Valenciennes and Hainaut-CambresisValenciennesFrance
  2. 2.Computer & Embedded Systems (CES Lab.), National Engineering School of Sfax (ENIS)University of SfaxSfaxTunisia
  3. 3.Centre for Renewable Energy Systems Technology (CREST)Loughborough University Science and Enterprise ParksLeicestershireUK

Personalised recommendations