Identification and dealing with uncertainties in the form of incomplete data by data mining methods

Authors

DOI:

https://doi.org/10.20535/SRIT.2308-8893.2016.2.10

Keywords:

risks analysis, data mining, Bayesian networks, informational technologies, system analysis

Abstract

In this paper, the methods for processing missing data are reviewed. The classification of methods depending on input data, data types and formats, and causes of data incompleteness associated with influence of uncertainties of the outside world and modeling object is proposed. The commonalities and differences between existing methods are investigated. The application peculiarities of these methods for filling missing data depending on properties of uncertainties are determined. It is shown that the traditional approach for filling the missing data by average values does not allow obtaining correct forecasts in many cases due to changes in sample’s properties. The usage of data mining methods technologies for dealing with missing data is proposed. An example of using regression methods is shown for filling missing data, in particular, using the forecast evaluation.

Author Biography

Nataliia V. Kuznietsova, ESC "Institute for Applied System Analysis" NTUU "KPI", Kyiv

Nataliia Vladymyrivna Kuznietsova,

PhD, assistant professor of Education-scientific complex "Institute for Applied System Analysis" NTUU "KPI", Kyiv, Ukraine

Scientific interests: risks analysis, data mining, Bayesian networks, informational technologies, system analysis.

References

Bolotin V.V. Resurs mashin i konstruktsij / V.V. Bolotin. — M.: Mashinostroenie, 1990. — 448 s.

Veksler A.B. Nadezhnost', sotsial'naja i ekologicheskaja bezopasnost' gidrotehnicheskih ob'ektov: otsenka riska i prinjatie reshenij / A.B. Veksler, D.A. Ivashintsov, D.V. Stefanishin. — SPb.: VNIIG im. B.E. Vedeneeva, 2002. — 591 s.

The use of risk analysis to support dam safety decisions and management. Trans. of the 20-th Int. Congress on Large Dams. Vol. 1. Q. 76. Beijing-China, 2000. — 896 p.

Hartford D.N.D. Risk and Uncertainty in Dam Safety / D.N.D. Hartford, G.B. Baecher // Published by Thomas Telford, 2004. — 401 p.

Vajnberg A.I. Nadezhnost' i bezopasnost' gidrotehnicheskih sooruzhenij. Izbrannye problemy / A.Y. Vajnberh. — Kh.: Tjazhpromavtomatyka, 2008. — 304 s.

Stefanyshyn D.V. Prohnozuvannja avarij na hrebljakh v zadachakh otsinky j zabezpechennja yikh nadijnosti ta bezpeky / D.V. Stefanyshyn // Hidroenerhetyka Ukrayiny. —2011. — № 3–4 – S. 52–60.

Zgurovskij M.Z. Informatsionnyj podhod k analizu i upravleniju proektnymi riskami / M.Z. Zgurovskij, I.I. Kovalenko, K. Kondrak, E. Kondrak // Problemy upravlenija i informatiki. — 2000. — № 4. — S. 148–156.

Mirtshulava Ts.E. Opasnosti i riski na nekotoryh vodnyh i drugih sistemah. Vidy, analiz, otsenka / Ts.E. Myrtskhulava. — Tbylysy: Metsnyereba ("Nauka"), 2003. — 538 s.

Pankratova N.D. Otsinjuvannja bahatofaktornykh ryzykiv v umovakh kontseptual'noyi nevyznachenosti / N.D. Pankratova, N.I. Nedashkivs'ka // Kibernetika i sistemnyj analiz. — 2009. — № 2. — S. 72–82.

Perel'muter A.V. Izbrannye problemy nadezhnosti i bezopasnosti stroitel'nyh konstruktsij / A.V. Perel'muter. — M.: Izd-vo Assotsiatsii stroit. vuzov, 2007. — 255 s.

Polovko A.M. Osnovy teorii nadezhnosti / A.M. Polovko, S.V. Gurov. — 2-e izd. pererab. i dop. — SPb: BHV-Peterburg, 2006. — 704 s.

Rjabinin I.A. Nadezhnost' i bezopasnost' strukturno-slozhnyh sistem / I.A. Rjabinin. — SPb.: Izd-vo S-Peterburg. un-ta, 2007. — 276 s.

Trofimchuk A.N. Nadezhnost' sistem sooruzhenie – gruntovoe osnovanie v slozhnyh inzhenerno-geologicheskih uslovijah / A.N. Trofimchuk, V.G. Chernyj, G.I. Chernyj. — K.: PolgrafKonsalting, 2006. — 248 s.

Kumamoto H. Probabilistic Risk Assessment and Management for Engineers and Scientists / H. Kumamoto, E.J. Henley. — New York: IEEE Press, 1996. — 597 p.

Begun V.V. Metod reshenija problemy rascheta tehnogennyh riskov / V.V. Begun, S. A. Vahnin // Upravljajuschie sistemy i mashiny. — 2014. — № 3. — S. 3–9.

Kachyns'kyj A.B. Bezpeka, zahrozy i ryzyk: naukovi kontseptsiyi ta matematychni metody: monohr. / A.B. Kachyns'kyj; In-t problem nats. bezpeky. Nats. akad. sluzhby bezpeky Ukrayiny. — K.: [b. n.], 2004. — 470 s.

Lysychenko H.V. Pryrodnyj, tekhnohennyj ta ekolohichnyj ryzyky: analiz, otsinka, upravlinnja / H.V. Lysychenko, O.L. Zabulonov, H.A. Khmil'. — K.: Nauk. dumka, 2008. — 544 s.

Romanchuk K.H. Imovirnisne modeljuvannja stsenariyiv dvokh netypovykh avarij na hidroenerhetychnykh ob’yektakh / K.H. Romanchuk, D.V. Stefanyshyn // Hidroenerhetyka Ukrayiny. —2014. — № 2–3. — S. 20–25.

Stefanyshyn D.V. Lohiko-imovirnisna otsinka ryzyku zbytkiv vid avarijnoho vylyvu vody z basejnu dobovoho rehuljuvannja Zaramahs'koyi HES-1 / D.V. Stefanyshyn, K.H. Romanchuk // Systemni doslidzhennja ta informatsijn tekhnolohiyi. — 2013. — № 3. — S. 130–141.

Stefanyshyn D.V. Use of the Bayes’ approach for assessment of damage risks of system failures / D.V. Stefanyshyn, K.G. Romanchuk // Proc. of Int. Scientific School "Modelling and Analysis of Safety and Risk in Complex Systems". — July 7–11, 2009. — Saint-Petersburg, Russia. — P. 165–169.

Zahirs'ka I.O. Metodyka pobudovy stsenarnoho analizu iz vykorystannjam bajyesivs'kykh metodiv / I.O. Zahirs'ka, P.I. Bidjuk // Elektrotekhnichni ta komp’juterni systemy. Informatsijni systemy ta tekhnolohiyi. — 2012. — № 8 (84). — S. 137–142.

Pankratova N.D. Modeljuvannja al'ternatyv stsenariyiv protsesu tekhnolohichnoho peredbachennja / N.D. Pankratova, V.V. Savast'janov // Systemni doslidzhennja ta informatsijni tekhnolohiyi. — 2009. — № 1. — S. 22–35.

Stefanishin D.V. Stsenarnyj podhod k otsenke verojatnostej avarij na plotinah / D.V. Stefanishin // Monitoring. Nauka i bezopasnost'. Ustojchivost' zdanij i sooruzhenij. — 2013. — № 1 (9). — S. 26–33.

Poja D. Matematika i pravdopodobnye rassuzhdenija / D. Poja [Per. s anhl. Y.A. Vajnshtejna]. — M.: Nauka, 1975. — 462 s.

Rajfa G. Prikladnaja teorija statisticheskih reshenij / G. Rajfa, R. Shlejfer [Per. s angl. A.K. Zvonkina, Z.G. Majmina i B.L. Rozovskogo; pod red. i s pred. Ju.N. Blagoveschenskogo]. — M.: Statistika, 1977. — 360 s.

Published

2016-06-21

Issue

Section

Methods of system analysis and control in conditions of risk and uncertainty