Mini-model method based on k-means clustering

• Autorzy: Pietrzykowski M. , Pluciński M.

Identyfikatory

DOI

10.15199/48.2017.01.18

Warianty tytułu

PL

Metoda mini-modeli bazuja˛ca na algorytmie k-średnich

• Języki publikacji: EN

Abstrakty

EN

Mini-model method (MM-method) is an instance-based learning algorithm similarly as the k-nearest neighbor method, GRNN network or RBF network but its idea is different. MM operates only on data from the local neighborhood of a query. The paper presents new version of the MM-method which is based on k-means clustering algorithm. The domain of the model is calculated using k-means algorithm. Clustering method makes the learning procedure simpler.

PL

Metoda mini-modeli (metoda MM) jest algorytmem bazującym na próbkach podobnie jak metoda k-najbliższych sąsiadów, sieć RBF czy sieć GRNN ale jej zasada działania jest inna. MM operuje tylko na danych z najbliższego otoczenia punktu zapytania. Artykuł prezentuje nową wersję metody MM, która bazuje na algorytmie k-średnich. Domena MM jest obliczana przy pomocy algorytmu k-średnich. Użycie algorytmu klasteryzacji uprościło procedurę uczenia.

Słowa kluczowe

EN

mini-model; local self-learning; function approximation; instance-based learning; k-means

PL

mini-model; lokalne samouczenie; aproksymacja funkcji; algorytm; algorytm k-średnich

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2017
• Tom: R. 93, nr 1
• Strony: 73--76
• Opis fizyczny: Bibliogr.16 poz.,rys., tab.

Twórcy

autor

Pietrzykowski M.

• Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Z˙ołnierska 49, 71-210 Szczecin, Poland

autor

Pluciński M.

• Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Z˙ołnierska 49, 71-210 Szczecin, Poland

Bibliografia

• [1] Piegat, A., Wasikowska, B., Korzeń, M.: Differences between the method of mini-models and the k-nearest neighbors an example of modeling unemployment rate in Poland. Information Systems in management IX-Business Intelligence and Knowledge Management. WULS Press, Warsaw, 34–43, (2011)
• [2] Pietrzykowski, M.: Comparison between mini-models based on multidimensional polytopes and k-nearest neighbor method: case study of 4D and 5D problems. Series: Advances in Intelligent Systems and Computing, vol. 342, pp. 107–118, Springer Verlag, (2015)
• [3] Pietrzykowski, M., Piegat, A.: Geometric Approach in Local Modeling: Learning of Mini-Models Based on n-Dimensional Simplex Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science Volume 9120, pp. 460-470 (2015)
• [4] Pluciński, M.: Mini-models - Local Regression Models for the Function Approximation Learning. In Rutkowski L. et. al. Proceedings of ICAISC 2012, Part II, LNCS 7268, Springer-Verlag Berlin Heidelberg, pp. 160–167, (2012)
• [5] Pluciński, M.: Evaluation of the mini-models robustness to data uncertainty with the application of the information-gap theory. Artificial intelligence and soft computing : 12th International Conference, ICAISC 2013, Springer, 2013 pp. 230–241, (2013)
• [6] Pluciński, M.: Application of Mini-Models to the Interval Information Granules Processing. Series: Advances in Intelligent Systems and Computing, vol. 342, pp. 37–48, Springer Verlag, (2015)
• [7] Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, second edition, Prentice Hall. ISBN 0-13-080302-2, (2003)
• [8] Samworth, R.J.: Optimal Weighted Nearest Neighbour Classifiers, Annals of Statistics, vol. 40(5), pp. 2733–2763, (2012)
• [9] Nose, K., Lotufo, A.D.P., Minussi, C.R.: Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network. IEEE Transactions on Power Delivery, vol. 26 (4), pp. 2862–2869, (2011)
• [10] Lin, C.L., Wang, J.F., Chen, C.Y., Chen, C.W., Yen, C.W.: Improving the generalization performance of RBF neural networks using a linear regression technique. Expert Systems with Applications, vol. 36 (10), pp. 12049–12053, (2009)
• [11] Jain, A. K. Data clustering: 50 years beyond K-means. IEEE Pattern Recognition Letters, vol. 31 (8), pp. 651-666, (2010)
• [12] Celebi, M. E., Kingravi, H. A., Vela, P. A.: A comparative study of efficient initialization methods for the k-means clustering algorithm. Expert systems with applications, vol. 40 (1), pp. 200– 201, (2013)
• [13] David, A., Vassilvitskii, S.: K-means++: The Advantages of Careful Seeding. SODA ‘07: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1027–1035, (2007)
• [14] Kutner, M. H., Nachtsheim, C. J., Neter, J., et al.: Applied Linear Statistical Models. McGraw-Hill/Irwin, ISBN 9780073108742, (2005)
• [15] Ruppert D., Wand M.P.: Multivariate locally weighted leastsquares regression. Annals of Statistics, vol. 22 (3), pp. 1346– 1370, (1994)
• [16] UCI MACHINE LEARNING REPOSITORY, http://archive.ics.uci.edu/ml/

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).