Systems and Means of Informatics
2019, Volume 29, Issue 2, pp 122-134
METHOD FOR SEARCHING OUTLIER OBJECTS USING PARAMETERS OF LEARNING INSTABILITY
- I. S. Ozhereliev
- O. V. Senko
- N. N. Kiseleva
Abstract
The paper describes a new method of outliers detection in pattern recognition tasks. The authors define an outlier as an object which deviates significantly from the other objects of the same class. The method is based on simultaneous use of evaluated object estimates for classes and integral distortion of recognition algorithm that is caused by evaluated object. Usefulness of the developed technique was shown for the task of predicting if an inorganic compound of composition A+3B+3C+2O4 is formed under ordinary conditions.
The method may be used for erroneous observations detection that is aimed to improve training information in different recognition tasks.
[+] References (11)
- Aggarwal, C. C. 2013. Outlier analysis. New York, NY: Springer-Verlag. 446 p.
- Kiseleva, N.N. 2005. Komp'yuternoe konstruirovanie neorganicheskikh soedineniy [Computer design of nonorganic compounds]. Moscow: Nauka. 289 p.
- Kiseleva, N. N., A. V. Stolyarenko, V. V. Ryazanov, O. V. Sen'ko, and A. A. Dokukin.
2017. Prediction of new A3+B3+C2+O4 compounds. Russ. J. Inorg. Chem. 62:1058- 1066.
- Grubbs, F. E. 1969. Procedures for detecting outlying observations in samples. Technometrics 11(1): 1-21.
- Rousseeuw, P. J., and K. Van Driessen. 2006. Computing LTS regression for large data sets. Data Min. Knowl. Discovery 12:29-45.
- Rousseeuw, P. J. 1984. Least median of squares regression. J. Acoust. Soc. Am. 79:871-880.
- Cook, R.D. 1979. Influential observations in linear regression. J. Acoust. Soc. Am. 74:169-174.
- Cao, D. S., Y. Z. Liang, Q. S. Xu, H. D. Li, and X. Chen. 2010. A new strategy of outlier detection for QSAr/QSpR. J. Comput. Chem. 31:592-602.
- Zhuravlev, Yu. I., V.V. Ryazanov, and O.V. Sen'ko. 2006. "Raspoznavanie." Ma- tematicheskie metody. Programmnaya sistema. Prakticheskie primeneniya ["Recognition." Mathematical methods. Program system. Applications]. Moscow: Fazis. 159 p.
- Hastie, T., R. Tibshirani, and J.H. Friedman. 2009. The elements of statistical learning: Data mining, interference, and prediction. 2nd ed. New York, NY: Springer. 767 p.
- Zweig, M.H. 1993. Receiver-operating Characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine. Clin. Chem. 39:561-577.
[+] About this article
Title
METHOD FOR SEARCHING OUTLIER OBJECTS USING PARAMETERS OF LEARNING INSTABILITY
Journal
Systems and Means of Informatics
Volume 29, Issue 2, pp 122-134
Cover Date
2019-05-30
DOI
10.14357/08696527190211
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
outliers; databases; recognition; instability of training; nonorganic compounds
Authors
I. S. Ozhereliev  , O. V. Senko  , and N. N. Kiseleva 
Author Affiliations
Faculty of Computational Mathematics and Cybernetics, M.V. Lomonosov Moscow State University, 1-52 Leninskiye Gory, GSP-1, Moscow 119991, Russian Federation
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
A. A. Baikov Institute of Metallurgy and Materials Science of the Russian Academy of Sciences, 49 Leninskiy Prosp., Moscow 119991, Russian Federation
|