Abo Bibliothek: Guest
Journal of Automation and Information Sciences

Erscheint 12 Ausgaben pro Jahr

ISSN Druckformat: 1064-2315

ISSN Online: 2163-9337

SJR: 0.173 SNIP: 0.588 CiteScore™:: 2

Indexed in

Plausible but Groundless Premises when Constructing Diagnostic Models

Volumen 52, Ausgabe 5, 2020, pp. 38-50
DOI: 10.1615/JAutomatInfScien.v52.i5.40
Get accessGet access

ABSTRAKT

When solving a number of applied problems of medical and technical diagnostics, the designing of diagnostic models is carried out under the conditions of insufficient knowledge of physical regularities occurring in the studied objects. It is necessary to create models only based on "common case" and intuition, relying on the available experimental material (precedents). However, here erroneous solutions are possible that lead to the inefficiency of the diagnostic system. We consider examples of some considerations, which turn to be scientifically insolvent. It is shown that the linear classifier, to which the method of decision-making on the distance to standards is reduced according to the method of reference images, can lead to absurd results. Such an effect occurs if the independence condition for the preferences of individual characteristics is not fulfilled, which foresees the "worsening" of the value of one attribute can be compensated by the "improvement" of another, and vice versa, which is not always true. It is shown that the unjustified expansion of the space of diagnostic attributes impairs the effectiveness of the diagnostic rule. Therefore, it is important to get rid of unnecessary signs even before the training stage. We analyzed the inconsistency of the argumentation that when constructing diagnostic models it is expedient to use only statistically independent attributes. For showing the fallibility of such an argumentation it is proved that under a statistical dependence between attributes, a combination of individually non-informative attributes can be not only useful but also capable of providing unmistakable recognition of classes. Therefore, it is important in every definite case to investigate the question of conditional statistical dependence between attributes before making decision on their exclusion from a description. By the example of constructing a model of indirect estimation of the carbon content in a liquid metal by the temperature of crystallization onset, it is shown that it is impossible to restore the true diagnostic model using only self-organization methods without using additional algorithms.

REFERENZEN
  1. Belkin A.R., Levin M.Sh., Decision making: combinatorial methods of approximation of information [in Russian], Nauka, Moscow, 1990.

  2. Tou J., Gonzalez R., Pattern recognition principles, Addison-Wesley Publishing Co., London, 1974.

  3. MensinkT., VerbeekJ., PerronninF., CsurkaG., Distance-based image classification: generalizing to new classes at near-zero cost, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2013, 35, No. 11, 2624-2637, DOI: 10.1109/TPAMI.2013.83.

  4. Weinberger K., Saul L., Distance metric learning for large margin nearest neighbor classification, Journal of Machine Learning Research, 2009, 10, 207-244.

  5. Bilenko M., Basu S., Mooney R., Integrating constraints and metric learning in semisupervised clustering, Proceedings of the 21th Int. Conf. on Machine Learning (ICML-04, Canada, Banf), 2004, 839-846, DOI: 10.1145/1015330.1015360.

  6. BraunR., EssweinW., Classification of reference models, Advances in data analysis. Studies in classification, Data Analysis, and Knowledge Organization, Springer, Berlin, 2007, 401-408, DOI: 10.1007/978-3-540-70981-7_45.

  7. HaghighatM., Abdel-Mottaleb M., Alhalabi W., Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition, IEEE Transactions on Information Forensics and Security, 2016, 11, No. 9, 1984-1996, DOI: 10.1109/TIFS.2016.2569061.

  8. McLachlan G., Discriminant analysis and statistical pattern recognition, Wiley-Interscience, New York, 2004.

  9. KeeneyR.L., RaiffaH., Decisions with multiple objectives: preferences and value trade-offs, Cambridge University Press, Cambridge, 1993, DOI: 10.1002/bs.3830390206.

  10. Golovkin B.A., Machine recognition and linear programming [in Russian], Sov. Radio, Moscow, 1973.

  11. Zagoruiko N.V., Recognition methods and their application [in Russian], Sov. Radio, Moscow, 1972.

  12. Fainzilberg L.S., Mathematical methods of estimation of the utility of diagnostic attributes [inRussian], Osvita Ukrainy, Kiev, 2010.

  13. Ivakhnenko A.G., Induction method of self-organization of models of complex systems [inRussian], Naukova dumka, Kiev, 1981.

  14. TiszaM., Physical metallurgy for engineers, ASM Int. and Fraund Publishing House Ltd, Ohio, 2002.

  15. Fainzilberg L.S., Information technologies of complicated shape signal processing. Theory and practice, Naukova dumka, Kiev, 2008.

Digitales Portal Digitale Bibliothek eBooks Zeitschriften Referenzen und Berichte Forschungssammlungen Preise und Aborichtlinien Begell House Kontakt Language English 中文 Русский Português German French Spain