ALGEBRAIC BAYESIAN NETWORKS:SEQUESTERED FUSION OF KNOWLEDGE PATTERNS UNDER INFORMATION DEFICIENCY CONDITIONS

Kharitonov N.A., Tulupyev A.L. Algebraic Bayesian networks: sequestered fusion of knowledge patterns under information deficiency conditions. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2019, vol. 19, no. 4, pp. 641–649 (in Russian). doi: 10.17586/2226-1494-2019-19-4-641-649

Subject of Research. The paper deals with situations when two or more models trained on different but crossing datasets are associated with one object in machine learning of probabilistic graphical models. The subject of this study is the fusion of such models, represented by knowledge patterns of algebraic Bayesian network. The study is aimed at description and formalization of the ways for fusion of algebraic Bayesian networks, presented in the form of two knowledge patterns. Method. We created such fusion models that their semantics is clearly explicated by assumptions about the ratio of probabilistic semantics of the considered knowledge patterns. Main Results. We have defined and systematized the ways to fuse knowledge patterns with no generation of new network elements. The statement about the number of atoms in the resulting network and the theorem on the difficulty of maintaining its internal consistency is given and proved. An example of the two networks fusion on a sample with noise is demonstrated. At this, the theoretical distribution of the sample is specified for carrying out comparative analysis, and the sample itself is generated by the Monte Carlo method. Practical Relevance. The methods proposed in the study for algebraic Bayesian networks fusion can be used when applying two or more trained networks describing various properties of a single object. The application of these methods gives the possibility to build a complex network aggregating all accessible data about the object under study and carry out probabilistic-logic operations in it.

1. Ackland G.J., Chattoe-Brown E., Hamill H., Hampshire K.R., Mariwah S., Mshana G. The role of trust in a self-organising pharmaceutical supply chain model with variable drug quality and imperfect information. Journal of Artificial Societies and Social Simulation, 2019, vol. 22, no. 2. doi: 10.18564/jasss.3984
2. Asher N., Paul S. Strategic conversations under imperfect information: epistemic message exchange games. Journal of Logic, Language and Information, 2018, vol. 27, no. 4, pp. 343–385. doi: 10.1007/s10849-018-9271-9
3. Zolotin A.A., Tulupyev A.L. Sensitivity statistical estimates for local a posteriori inference matrix-vector equations in algebraic Bayesian networks over quantum propositions. Vestnik St. Petersburg University-Mathematics, 2018, vol. 51, no. 1, pp. 42–48. doi: 10.3103/S1063454118010168
4. Kharitonov N.A., Tulupyev A.L., Zolotin A.A. Software implementation of reconciliation algorithms in algebraic Bayesian networks. Proc. 20^th Int. Conf. on Soft Computing and Measurements, SCM 2017. St. Petersburg, Russia, 2017, pp. 8–10.
5. Kou F.F., Du J.P., Yang C.X., Shi Y.S., Liang M.Y., Xue Z., Li H.S. A multi-feature probabilistic graphical model for social network semantic search. Neurocomputing, 2019, vol. 336, pp. 67–78. doi: 10.1016/j.neucom.2018.03.086
6. Ramazzotti D., Nobile M.S., Antoniotti M., Graudenzi A. Efficient computational strategies to learn the structure of probabilistic graphical models of cumulative phenomena. Journal of Computational Science, 2019, vol. 30, pp. 1-10. doi: 10.1016/j.jocs.2018.10.009
7. Tai W.P., Teng Q.Y., Zhou Y.M., Zhou J.P., Wang Z. Chaos synchronization of stochastic reaction-diffusion time-delay neural networks via non-fragile output-feedback control. Applied Mathematics and Computation, 2019, vol. 354, pp. 115–127. doi: 10.1016/j.amc.2019.02.028
8. Dey M., Rana S.P., Siarry P. A robust FLIR target detection employing an auto-convergent pulse coupled neural network. Remote Sensing Letters, 2019, vol. 10, no. 7, pp. 639–648. doi: 10.1080/2150704X.2019.1597296
9. Li J.J., Song G.B., Semakula H.M., Zhang S.S. Climatic burden of eating at home against away-from-home: A novel Bayesian Belief Network model for the mechanism of eating-out in urban China. Science of the Total Environment, 2019, vol. 650, pp. 224–232. doi: 10.1016/j.scitotenv.2018.09.015
10. Li X.D., Tang W.Y. Structural risk analysis model of damaged membrane LNG carriers after grounding based on Bayesian belief networks. Ocean Engineering, 2019, vol. 171, pp. 332–344. doi: 10.1016/j.oceaneng.2018.10.047
11. Prishchepov A.V., Ponkina E., Sun Z.L., Muller D. Revealing the determinants of wheat yields in the Siberian breadbasket of Russia with Bayesian networks. Land Use Policy, vol. 80, pp. 21–31. doi: 10.1016/j.landusepol.2018.09.038
12. Don M.G., Khan F. Dynamic process fault detection and diagnosis based on a combined approach of hidden Markov and Bayesian network model. Chemical Engineering Science, 2019, vol. 201, pp. 82–96. doi: 10.1016/j.ces.2019.01.060
13. Baggenstoss P.M. On the duality between belief networks and feed-forward neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2019, vol. 30, no. 1, pp. 190–200. doi: 10.1109/TNNLS.2018.2836662
14. Marcot B.G., Penman T.D. Advances in Bayesian network modelling: Integration of modelling technologies. Environmental Modelling and Software, 2019, vol. 111, pp. 386–393. doi: 10.1016/j.envsoft.2018.09.016
15. Tulup'ev A.L., Nikolenko S.I., Sirotkin A.V. Bayesian Networks: Logical-Probabilistic Approach. St. Petersburg, Nauka Publ., 2006, 607 p. (in Russian)
16. Tulup'evA.L., SirotkinA.V., NikolenkoS.I. Bayesian Belie fNetworks: Logical-Probabilistic Inference in the Acyclic Directed Graph. St. Petersburg, SPbSUPubl., 2009, 400 p. (inRussian)
17. Tulupyev A.L., Nikolenko S.I., Sirotkin A.V. Fundamentals of the Theory of Bayesian Networks: A Textbook. St. Petersburg, SPbSU Publ., 2019, 399 p. (in Russian)
18. Kharitonov N.A. Maintaining of internal consistency of algebraic bayesian networks with linear and stellate structure. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2018, vol. 18, no. 6, pp. 1108–1117. doi: 10.17586/2226-1494-2018-18-6-1108-1117
19. Tulup'evA.L. Algebraicheskie Baiesovskie Seti: Logiko-Veroyatnostnaya Graficheskaya Model' Baz Fragmentov Znanii s Neopredelennost'yu. Dis. dr. fiz.-mat. nauk [Algebraic Bayesian networks: a logical-probabilistic graphical model of knowledge bases with uncertainty.Diss. Dr. in Phys.-Math. Sci.]. St. Petersburg, SPbGU, 2009, 670 p.
20. Tulupyev A., Kharitonov N., Zolotin A. Algebraic Bayesian networks: Consistent fusion of partially intersected knowledge systems. CEUR Workshop Proceedings, 2018, vol. 2258, pp. 109–115.
21. Levenets D.G., Zotov M.A., Romanov A.V., Tulupyev A.L., Zolotin A.A., Filchenkov A.A. Decremental and incremental reshaping of algebraic Bayesian networks global structures. Proc. 1^st Int. Scientific Conference on Intelligent Information Technologies for Industry, IITI’16. Sochi, Russia, 2016, pp. 57–67. doi: 10.1007/978-3-319-33816-3_6
22. Malinowski G. Kleene logic and inference. Bulletin of the Section of Logic, 2014, vol. 43, no. 1/2, pp. 43–52.
23. Abramov M.V. Automating the analysis of social networks for assessing security from socio-engineering attacks. Automation of Management Processes, 2018, no. 1, pp. 34–40.(in Russian)
24. Bagretsov G.I., Shindarev N.A., Abramov M.V., Tulupyeva T.V. Approaches to automate the collection, structuring and analysis of information about company employees based on social network data. Proc. 7^th All-Russian Scientific and Practical Conference on Fuzzy Systems, Soft Computing and Intellectual Technologies, NSMVIT. St. Petersburg, 2017, vol. 1, pp. 9–16. (in Russian)

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License