Selection of attributes for a classifier of telecommunication failures in the copper mine

• Authors: Karaban Bartłomiej , Korczak Jerzy
• Languages of publication: EN

Abstracts

EN

Ensuring safety and continuity of production is the major task of telecommunication systems in deep mining. These systems, despite their use of modern and innovative infrastructure of monitoring solutions, are not free from imperfections. One of the practical problems are false alarms signaling the occurrences of damaged infrastructures. In the paper, the data sources of the telecommunication system are identified and described, as well as the methods of their preprocessing. To build a classifier, a method of attribute selection is proposed to detect false alarms generated by the telecommunication system of the mine. Experiments were carried out on real data extracted from the telecommunication system operating in the copper mine of the KGHM Polska Miedź SA.

Keywords

EN

Data mining; telecommunication system; data preprocessing; classification me¬thods; inductive decision trees; detection of false alarms; decision rules

• Publisher: Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
• Journal: Informatyka Ekonomiczna
• Year: 2014
• Issue: 3(33)
• Pages: 77-87

Contributors

author

Karaban Bartłomiej

author

Korczak Jerzy

References

• Bramer M., 2013, Undergraduate Topics in Computer Science. Principles of Data Mining, Springer, London.
• Ding S., 2013, Model-Based Fault Diagnosis Techniques. Design Schemes, Algorithms and Tools, Springer, London.
• Gorunescu F., 2011, Data Mining. Concepts, Models and Techniques, Springer, Berlin.
• Karaban B., 2013, Indukcyjne drzewa decyzyjne w analizie alarmów systemu telekomunikacyjnego, Uniwersytet Ekonomiczny we Wrocławiu, Wrocław [master thesis].
• Karaban B., Korczak J., 2014, An approach to discover false alarms in monitoring system in the copper mine, [in:] Ganzha M., Maciaszek L., Paprzycki M. (eds), Proceedings of the 2014 Federated Conference on Computer Science and Information Systems. Annals of Computer Science and Information Systems, vol. 2, Polskie Towarzystwo Informatyczne, Warsaw, Institute of Electrical and Electronics Engineers, New York City, pp. 307–312.
• Kohavi R., John G.H., 1997, Wrappers for feature subset selection, Artificial Intelligence, vol. 97, pp. 273–324.
• Korbicz J, Kościelny J., Kowalczuk Z., Cholewa W., 2002, Diagnostyka procesów. Modele. Metody sztucznej inteligencji. Zastosowania, WNT, Warszawa.
• Korczak J., Karaban B., 2014, Metoda wykrywania fałszywych alarmów w systemie monitorującym sieć telekomunikacyjną kopalni, Przegląd Górniczy, nr 70, pp. 108–112.
• Madolando S., Weber R., Famili F., 2014, Feature selection for high-dimensional class-imbalanced data sets using Support Vector Machines, Information Sciences, vol. 286, pp. 228–246.
• Morzy T., 2013, Eksploracja danych. Metody i algorytmy, Wydawnictwo Naukowe PWN, Warszawa, pp. 326–327.
• Piatetsky-Shapiro G., Frawley W., 1991, Knowledge Discovery in Databases, The AAAI Press, Menlo Park.
• Rivas T., Paz M., Martín J.E., Matías J.M., García, J.F., Taboada J., 2011, Explaining and predicting workplace accidents using data-mining techniques, Reliability Engineering & System Safety, vol. 96, pp. 739–747.
• Sang Y., Qi H., Li K., Jin Y., Yan D., Gao S., 2014, An effective discretization method for disposing high-dimensional data, Information Sciences, vol. 270, pp. 73–91.
• Zhang K., Li Y., Scarf P., Ball A., 2011, Feature selection for high-dimensional machinery fault diagnosis data using multiple models and Radial Basis Function networks, Neurocomputing, vol. 74, pp. 2941–2952.