An application of expectation-maximization for model verification

• Autorzy: Łukawska B. , Łukawski G. , Sapiecha K.
• Języki publikacji: EN

Abstrakty

EN

A description which summarizes entire and usually big set of data is called its model. The problem investigated in the paper consists in verification of models of data coming from a simulation experiment of selecting candidates for operators of mobile robot (more strictly building reliable predictive model of the data). The models are validated using train-and-test method and verified with the help of the EM (expectation-maximization) algorithm which was originally designed for solving clustering problems with missing data. Actually, the selecting is a clustering problem because the candidates are assigned to ‘chosen’, ‘accepted’ or ‘rejected’ subgroups. For such a case the missing data is the category (the subgroup) for which a candidate should be assigned on the basis of his activity measured during the simulation experiment. The paper explains the procedure of model verification. It also shows experimental results and draws conclusions.

Słowa kluczowe

EN

EM algorithm; data clustering; model verification

• Wydawca: Wydawnictwo UMCS
• Czasopismo: Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica
• Rocznik: 2010
• Tom: Vol. 10, no. 1
• Strony: 15--27
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Łukawska B.

• Department of Computer Science, Kielce University of Technology, Al. Tysiaclecia Panstwa Polskiego 7, 25-314 Kielce, Poland

autor

Łukawski G.

• Department of Computer Science, Kielce University of Technology, Al. Tysiaclecia Panstwa Polskiego 7, 25-314 Kielce, Poland

autor

Sapiecha K.

• Department of Computer Science, Kielce University of Technology, Al. Tysiaclecia Panstwa Polskiego 7, 25-314 Kielce, Poland

Bibliografia

• [1] Hand D., Mannila H., Smyth P., Eksploracja danych (WNT, Warszawa, 2005): 207–252.
• [2] StatSoft Electronic Textbook, http://www.statsoft.com/textbook/stathome.html (accessed 2009-02-17).
• [3] Sapiecha K., Łukawska B., Paduch P., Experimental Data Driven Robot for Pattern Classification, Annales UMCS Informatica AI 3 (2005): 263–271.
• [4] Łukawska B., Paduch P., Sapiecha K., An application of virtual reality for training and ranking operators of mobile robot, Annales UMCS Informatica AI 5 (2006): 393–399.
• [5] Sapiecha K., Bedla M., Łukawska B., Paduch P., Computer-based system for training and selecting mobile robot operators – evolving software tools, Annales UMCS Informatica AI 7 (2007): 107–115.
• [6] Bedla M., Łukawska B., Sapiecha K., Software architecture for a system of remote training mobot operator, Advanced Computer Systems and Networks: Design and Application. Proc. of the third International Conference ACSN-2007 (ACSN, Lwów, 2007): 104–106.
• [7] Sapiecha K., Łukawska B., Bedla M., Computer-based system for training and ranking mobot operators – selection procedure, Annales UMCS Informatica AI 8 (2008): 107–118.
• [8] Polski Wortal Robotyki, http://www.asimo.pl (accessed 2009-02-17).
• [9] The University of Waikato, WEKA, http://www.cs.waikato.ac.nz/ml/weka (accessed 2009-02-17).
• [10] John G. H., Langley J., Langley P., Estimating Continuous Distributions in Bayesian Classifiers, Proc. of the Eleventh Conference on Uncertainty in Artificial Intelligence (Morgan Kaufmann, San Mateo, 1995): 338–345.
• [11] Quinlan R., C4.5: Programs for Machine Learning (Morgan Kaufmann Publishers, San Mateo, 1993): 1–26.
• [12] Kohavi R., The Power of Decision Tables, Proc. European Conference on Machine Learning (1995): 174–189.