Lowing ambiguity level in object state estimation in a case-based control system

This work continues the publication series that is devoted to the investigation of methods of controlling complex objects basing on cases. In situation when it is hard or even impossible to use the exact mathematical model of object behavior the case-based reasoning control method becomes adequate. Instead of using the model we may use the accessible information about object under control state, controlling actions and their results. This means that we are using “cases”. In the theory of deduction this idea corresponds to three constituents of the case-based reasoning: description of a problem, solution or action applied, and outcome that is the result of applying the solution. This approach is based on separating of object states into classes, in each of which all the states are equivalent to each other. After that the object under control state is comparing with cases in the case base which was collected in advance. In order to choose the controlling action for the current case some metrics of similarity is used to find a case with similar initial and final states in the case base. The controlling action is extracted from this case then. The way of estimating of similarity of the current case and its precedent is critical for a system that uses the case-based reasoning technique. In previous publications the method was presented that used to separate cases from the case base into classes of equivalence. To estimate not fully described case the projection of classes onto the features space was used. Incompleteness in object description brings to the ambiguity in object estimation especially while one has the lack of time and resources. Classes in the intersection of which the object appears, are forming so called differential set of the object. If there is no feature that may separate the classes the choice of controlling action is hardly being made. The method offered by authors helps to low the ambiguity level on the basis of object prehistory investigation (previous states found and actions used). As a result of taking the prehistory into account the number of possible choices of actions is decreasing. The way of lowing the ambiguity level is described in the article. The notion of “prognostic” differential set of object states is presented. The final state estimation is produced on the basis of comparison of the current and prognostic sets.

control system, case-based reasoning, case base, complex object, incompleteness of description, ambiguity of estimation, object behavior, prehistory, differential set

1. V. N. Yudin. Sistema informatsionnoj podderzhki vrachebnykh reshenij, osnovannaya na modifitsirovannom metode dinamicheskogo klasternogo analiza [The system of information support of physician’s decisions based on modified method of dynamic cluster analysis], Trudy ISP RАN [The Proceedings of ISP RAS], vol. 3, 2002, pp. 103-118, ISBN/ISSN: 2079-8156 (in Russian).

2. V.N. Yudin, A.T. Bespaev. Application of Cluster Analysis for Searching for Analogies in Diagnostics and Choice of Treatment in the "Doctor’s Partner" System, Pattern Recognition and Image Analysis, vol. 13, No 2, 2003, pp. 387-390.

3. V. N. Yudin. Mera blizosti v sisteme vyvoda na osnove pretsedentov. [The measure of closeness in the case-based reasoning system], Doklady 12-j Vserossijskoj konferentsii Matematicheskie Metody Raspoznavaniya Obrazov [Proc. of 12-th All-Russian conference Math. methods of pattern recognition], MAKS Press, 2005, pp. 241-244 (in Russian).

4. L. E. Karpov, V. N. Yudin. Аdaptivnoe upravlenie po pretsedentam, osnovannoe na klassifikatsii sostoyanij upravlyaemykh ob"ektov [Case-Based Reasoning adaptive control with classification of states of objects under control], Trudy ISP RАN [The Proceedings of ISP RAS], vol. 13, no. 2, 2007, pp. 37-57, ISBN 5-89823-026-2. ISSN 2220-6426 (Online), ISSN 2079-8156 (Print), http://www.ispras.ru/ru/proceedings/docs/2007/13/2/isp_2007_13_2_37.pdf, http://www.citforum.ru/consulting/BI/karpov/ (in Russian).

5. L. E. Karpov, V. N. Yudin. Integratsiya metodov dobychi dannykh i vyvoda po pretsedentam v meditsinskoj diagnostike i vybore lecheniya [Integration of data Mining and Case-Based Reasoning methods in medical diagnostics and treatment choosing], Sbornik dokladov 13-j Vserossijskoj konferentsii Matematicheskie metody raspoznavaniya obrazov [Proc. of 13-th All-Russian conference Math. methods of pattern recognition], October 2007, MAKS Press, 2007, pp. 589-591, ISBN 978-5-317-02060-6, http://www.mmro.ru/files/mmro13.pdf (in Russian).

6. V. N. Yudin, L. E. Karpov, A. V. Vatazin. Protsess lecheniya kak adaptivnoe upravlenie chelovecheskim organizmom v programmnoj sisteme "Sputnik vracha" [Process of patient treatment as an adaptive control of human being organism in software system "Doctor's Partner"], Аl'manakh klinicheskoj meditsiny [Almanac of Clinical Medicine], vol. 17, no. 1, МОНИКИ [Moscow Regional Scientific Research Clinical Institute], 2008, pp. 262-265, ISSN 2072-0505, ISBN 978-5-98511-032-6, ISBN 5-9900012-1-5, http://www.isan.troitsk.ru/win/block1.pdf (in Russian).

7. V. N. Yudin, L. E. Karpov, A. V. Vatazin. Metody intellektual'nogo analiza dannykh i vyvoda po pretsedentam v programmnoj sisteme podderzhki vrachebnykh reshenij [Application of Data Mining and Case-Based Reasoning in software system for physician's decision support], Аl'manakh klinicheskoj meditsiny [Almanac of Clinical Medicine], vol. 17, no. 1, MONIKI [Moscow Regional Scientific Research Clinical Institute], 2008, pp. 266-269, ISSN 2072-0505, ISBN 978-5-98511-032-6, ISBN 5-9900012-1-5, http://www.isan.troitsk.ru/win/block1.pdf (in Russian).

8. L. E. Karpov, A. N. Tomilin, V. N. Yudin. Replikatsiya i validatsiya v raspredelennoj sisteme podderzhki vrachebnykh reshenij [Data replication and validation in distributed software system for physician's decision support], Trudy Vserossijskoj nauchnoj konferentsii "Nauchnyj servis v seti Internet: reshenie bol'shikh zadach" [Proc. All-Russian scientific conference “Scientific Service in Internet: solving of huge problems”], MGU [Moscow State University, 2008, pp. 387-392, ISBN 978-5-211-05616-9, http://agora.guru.ru/abrau2008/pdf/043.pdf (in Russian).

9. L. E. Karpov, A. V. Vatazin, V. N. Yudin. Virtual'naya integratsiya i konsolidatsiya znanij v raspredelennoj sisteme podderzhki vrachebnykh reshenij [Virtual knowledge integration and consolidation in software system for physician's decision support], Trudy Nauchno-prakticheskaya konferentsiya TSFO RF «Аktual'nye voprosy gemafereza, khirurgicheskoj detoksikatsii i dializa [Proc. of research and practical conference ‘Actual problems of hemapheresis, surgery detoxication and dialysis’], MONIKI [Moscow Regional Scientific Research Clinical Institute], 2009, pp. 36. ISBN 978-5-98511-054-8 (in Russian).

10. A. V. Vatazin, L. E. Karpov, V. N. Yudin. Virtual'naya integratsiya i konsolidatsiya znanij v raspredelennoj sisteme podderzhki vrachebnykh reshenij [Virtual knowledge integration and consolidation in software system for physician's decision support], Аl'manakh klinicheskoj meditsiny [Almanac of Clinical Medicine], vol. 20, 2009, pp. 83-86. ISSN 2072-0505 (in Russian).

11. A. V. Vatazin, L. E. Karpov, V. N. Yudin. Mnogoparametricheskoe upravlenie slozhnym ob"ektom v programmnoj sisteme podderzhki vrachebnykh reshenij [Multiparametric object control in software system for physician's decision support], III Evrazijskij kongress po meditsinskoj fizike i inzhenerii "Meditsinskaya fizika – 2010" [Third Euro-Asia congress for medical physics], 21-25 of June 2010, vol. 4, MONIKI [Moscow Regional Scientific Research Clinical Institute], 2010, pp. 415-417 (in Russian).

12. A. V. Vatazin, L. E. Karpov, V. N. Yudin. Mnogoparametricheskoe upravlenie slozhnym ob"ektom v programmnoj sisteme podderzhki vrachebnykh reshenij [Multiparametric object control in software system for physician's decision support], Ezhegodnaya nauchno-prakticheskaya konferentsiya TSentral'nogo Federal'nogo okruga RF "Аktual'nye voprosy zamestitel'noj pochechnoj terapii, gemafereza i transplantatsionnoj koordinatsii" [Proc. of Annual research and practical conference 'Actual problems of replacement therapy, hemapheresis, and transplantation coordination'], MONIKI [Moscow Regional Scientific Research Clinical Institute], 2010, стр. 8. ISBN 978-5-98511-091-3. (in Russian).

13. Leonid Karpov, Valery Yudin. The Case-Based Software System for Physician's Decision Support. Sami Khari, Lenka Lhotska, Nadia Pisanti (eds.), "Information Technology in Bio- and Medical Informatics, ITBAM 2010", Proceedings of the First International Conference, Bilbao, Spain. Lecture Notes in Computer Science Sublibrary: SL 3, Springer Verlag, Berlin, Heidelberg, 2010, pp. 78-85. ISSN 0302-9743.

14. L. E. Karpov, V. N. Yudin, A. V. Vatazin. Multi-Parametric Control of Complex Object in the Program System for Physician's Decision Support, Proceedings of the 12-th International Workshop on Computer Science and Information Technologies (CSIT'2010), Russia, Moscow – St. Petersburg, September 13-19, v. 1, Ufa State Aviation Technical University, 2010, pp. 28-30.

15. L. E. Karpov, V. N. Yudin. Obmen dannymi v raspredelyonnoj sisteme podderzhki reshenij [Data exchange in distributed software system for decision support], Trudy ISP RАN [The Proceedings of ISP RAS], vol. 19, 2010, pp. 71-80, ISBN 978-0-543-57630-9, ISBN 978-5-4221-0085-9, ISSN 2220-6426 (Online), ISSN 2079-8156 (Print), http://www.ispras.ru/ru/proceedings/docs/2010/19/isp_19_2010_71.pdf (in Russian).

16. L. E. Karpov, V. N. Yudin. Case-based multi-parametric object control, Trudy ISP RАN [The Proceedings of ISP RAS], vol. 19, 2010, pp. 81-93, ISBN 978-0-543-57630-9, ISBN 978-5-4221-0085-9, ISSN 2220-6426 (Online), ISSN 2079-8156 (Print), http://www.ispras.ru/ru/proceedings/docs/2010/19/isp_19_2010_81.pdf (in Russian).

17. A. V. Vatazin, L. E. Karpov, Y. G. Smetanin, V. N. Yudin. Programmnaya sistema podderzhki vrachebnykh reshenij s gibridnoj arkhitekturoj na osnove pravil i pretsedentov [Software system for physician's decision support with architecture based on rules and cases], V Troitskaya konferentsiya "Meditsinskaya fizika i innovatsii v meditsine (TKMF-5)", Sbornik materialov [Proc. of Fifth conference 'Medical physics and innovations in medicine'], vol. 2, pp. 425-427. 2012, RAS, Troitsk Scienfic Centre, ISBN 978-5-89513-272-2 (in Russian).

18. L. E. Karpov, V. N. Yudin. Rol' predystorii pri otsenke slozhnogo ob"ekta v upravlenii po pretsedentam [State prehistory for complex object estimation in a control system based on cases], Trudy ISP RАN [The Proceedings of ISP RAS], vol. 24, 2013, pp. 437-445, ISSN 2220-6426 (Online), ISSN 2079-8156 (Print), http://www.ispras.ru/ru/proceedings/docs/2013/24/isp_24_2013_437.pdf (in Russian).

19. V. N. Yudin, L. E. Karpov. Gibridnyj podkhod k postroeniyu sistem podderzhki reshenij [Hybrid approach to building decision support system], Trudy ISP RАN [The Proceedings of ISP RAS], vol. 24, 2013, pp. 447-456, ISSN 2220-6426 (Online), ISSN 2079-8156 (Print), http://www.ispras.ru/ru/proceedings/docs/2013/24/isp_24_2013_447.pdf (in Russian).