On new methods of dynamic ensemble selection based on randomized reference classifier

• Autorzy: Krysmann M. , Kurzyński M.
• Języki publikacji: EN

Abstrakty

EN

In the paper two dynamic ensemble selection (DES) systems are proposed. Both systems are based on a probabilistic model and utilize the concept of Randomized Reference Classifier (RRC) to determine the competence function of base classifiers. In the first system in the selection procedure of base classifiers the dynamic threshold of competence is applied. In the second DES system, selected classifiers are combined using weighted majority voting rule with continuous-valued outputs, where the weights are equal to the class-dependent competences. The performance of proposed MCSs were tested and compared against DES system with better-than-random selection rule using eleven databases taken from the UCI Machine Learning Repository. The experimental results clearly show the effectiveness of the proposed methods.

Słowa kluczowe

EN

machine learning; classifier competence; multiple classifier systems; dynamic competence threshold

PL

uczenie maszynowe; kompetencja klasyfikatora; systemy wielo-klasyfikatorów

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2012
• Tom: Vol. 20
• Strony: 101--107
• Opis fizyczny: Bibliogr. 15 poz., rys., tab.

Twórcy

autor

Krysmann M.

• Department of Systems and Computer Networks, Wroclaw University of Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

autor

Kurzyński M.

Bibliografia

• [1] DEMSAR J., Statistical comparison of classifiers over multiple data sets, Journal of Machine Learning Research 7, 2006, pp. 1-30.
• [2] DIDACI L., GIACINTO G., ROLI F., MARCIALIS G., A study of the performances of dynamic classifier selection based on local accuracy estimation, Pattern Recognition 38, 2005, pp. 2188-2191.
• [3] EULANDA M., SANTOS D, SABOURIN R., A dynamic overproduce and choose strategy for the selection of classifier ensembles, Pattern Recognition 41, 2008, pp. 2993-3009.
• [4] GIACINTO G., ROLI F., Dynamic classifier selection based on multiple classifier behavior, Pattern Recognition 34, 2001, pp. 1879-1881.
• [5] HUENUPAN F., YOMA N., Confidence based multiple classifier fusion in speaker verification, Pattern Recognition Letters 29, 2008, pp. 957-966.
• [6] KO A., SABOURIN R., BRITTO A., From dynamic classifier selection to dynamic ensemble selection, Pattern Recognition 41, 2008, pp. 1718-1733.
• [7] KUNCHEVA L.I., Combining Pattern Classifiers: Methods and Algorithms, John Wiley & Sons, (2004).
• [8] PRTools, http://www.prtools.org/.
• [9] UCI Machine Learning repository, http://archive.ics.uci.edu/ml/.
• [10] WOLOSZYNSKI T., KURZYNSKI M., A measure of competence based on randomized reference classifier for dynamic ensemble selection, In: 20th Int. Conf. on Pattern Recognition, 2010, pp. 4194-4197.
• [11] WOLOSZYNSKI T., KURZYNSKI M., A probabilistic model of classifier for dynamic ensemble selection, Pattern Recognition 44, 2011, pp. 2656-2668.
• [12] WOLOSZYNSKI T., KURZYNSKI M., A measure of competence based on random classification for dynamic ensemble selection, Information Fusion 13, 2012, pp. 207-213.
• [13] WOLOSZYNSKI T, KURZYNSKI M., et al., Prediction of progression of radiographic knee osteoarthritis using tibial trabecular bone texture, Arthritis and Rheumatism 64, 2012, pp. 688-695.
• [14] WOLOSZYNSKI T, KURZYNSKI M., et al., A signature dissimilarity measure for trabecular bone texture in knee radiographics, Medical Physics 37, 2011, pp. 2030-2042.
• [15] KURZYŃSKI M., , WOLCZOWSKI A., Dynamic selection of classifiers ensemble applied to the recognition of EMG signal for the control of bioprosthetic hand, Proc.11th Int. Conf. on Control, Automation and Systems, Seoul 26-29 Oct. 2011, pp. 382-386.