Аннотації
30.05.2014
Розглядаються питання інтелектуального аналізу даних, представлених часовими рядами (ЧР), на підставі моделей гранулярного компютингу, що вміщують матрицизацію вікна ЧР з наступним сингулярним розвиненням. Показано можливість представлення чіткого гранульованого ЧР нечітким та нечіткого гранульованого ЧР – чітким.
Рассматриваются вопросы интеллектуального анализа данных, представленных временными рядами (ВР), на основе моделей гранулярного компьютинга, включающих матрицизацию окна ВР с последующим сингулярным разложением. Показана возможность представления четкого гранулированного ВР нечетким и нечеткого гранулированного ВР – четким.
The questions of intellectual data analysis, presented by time series, on the base of granular computing models, include matricing time series windows with following singular decomposition are observed. The possibility of presentations crisp granular time series by fuzzy granular TS and fuzzy granular time series by crisp granular TS is shown. Intelligent analysis of time series is made by structuring time series windows of tensors of rank 2 matrices with dimension m´m or m´n, (which play the role of information granules (tensor-granules). Structuring the input data is represented as a square matrix that can significantly reduce the size of the task, open up opportunities for solving tasks in forecasting matrix structuring the time series in the use of the nearest neighbour method, which serve not the individual elements of a sequence, but tensors. Is shown the existence of dualism between crisp and fuzzy time series regardless of conditions the granular clear time series may be represented in the form of fuzzy time series, which has an element of FS-granule, and vice versa, any fuzzy time series can be presented clearly. Observe that the duality affects only granulated time series.
1. Финн В.К. Об интеллектуальном анализе данных.// Новости Искусственного интеллекта, № 3, 2004.
– С.58-66.
2. Zadeh, L. (1996). Fuzzy logic = computing with words. IEEE Transactions on Fuzzy Systems, 94(2),103–111.
3. Zadeh, L. (1999). From computing with numbers to computing with words -from ma-nipulation of measurements to manipulation of perceptions. IEEE Transactions on Circuits and Systems Part I: Fundamental Theory and Applications,
– 45 (1), 105–119.
4. Zadeh, L., & Kacprzyk, J. (Eds.). (1999a). Computing with words in information/ intelligent systems 1 (foundations). Studies in fuzziness and soft computing (Vol. 33). New York: Springer-Verlag. – Pp. 383–406.
5. Zadeh, L., & Kacprzyk, J. (Eds.). (1999b). Computing with words in information /in-telligent systems 2 (applications). Studies in fuzziness and soft computing (Vol. 34). New York: Springer-Verlag. – Рр.988-1006.
6. Ярушкина, Н. Г. Интеллектуальный анализ временных рядов: учебное пособие // Н. Г. Ярушкина,
Т. В. Афанасьева, И. Г. Перфильева. – Ульяновск: УлГТУ, 2010. – 320 с.
7. Song Q., Chissom B. Fuzzy time series and its models // Fuzzy Sets and Systems. – №54 (1993). – Р. 269-277.
8. Herrera F., Alonso S., Chiclana F.,Herrera-Viedma E. Computing with words in decision making: foundations, trends and prospects. Fuzzy Optim Decis Making (2009) 8. – Р. 337–364.
9. Cichocki A. Tensor Decompositions: A New Concept in Brain Data Analysis? arXiv: 1305.0395v1 [cs.NA] 2 May 2013. – 19 pp.
10. Минаев Ю.Н., Филимонова О.Ю., Минаева Ю.И. Тензорные модели НМ-гранул и их применение для решения задач нечеткой арифметики. «Искусственный интеллект». – №2, 2013. – С. 18-31.
11. Van Loan Ch.F. Block Matrix Computations and the Singular Value Decomposition A Tale of Two Ideas. – Інтернет-ресурс.
12. Van Loan Ch.F. The ubiquitous Kronecker product. Journal of Computational and applied mathematics. 2000,
123 (1-2): 85-100.
1. Finn V.K. (2004). An intellectual analysis of data -Lease. // News of artificial intelli -ta, № 3, 2004. – P.58- 66
2. Zadeh, L. (1996). Fuzzy logic = compu-ting with words. IEEE Transactions on Fuzzy Systems, 94 (2),103-111.
3. Zadeh, L. (1999). From computing with numbers to computing with words-from ma-nipulation of measurements to manipulation of perceptions. IEEE Transactions on Circuits and Systems Part I: Fundamental Theory and Applications, 45 (1), 105-119.
4. Zadeh, L., & Kacprzyk, J. (Eds.). (1999a). Computing with words in information / intelligent systems 1 (foundations). Studies in fuzziness and soft computing (Vol. 33). New York: Springer-Verlag. – Pp. 383-406.
5. Zadeh, L., & Kacprzyk, J. (Eds.). (1999b). Computing with words in information / in-telligent systems 2 (applications). Studies in fuzziness and soft computing (Vol. 34). New York: Springer-Verlag. – Rr.988 -1006.
6. Yarushkina N.G., Afanasiev T. V., Perfil'eva I.G. (2010) Intellectuals -tion time-series analysis: a tutorial // Ulyanovsk: UlSTU 2010. – 320 р.
7. Song Q., Chissom B. (1993). Fuzzy time se-ries and its models // Fuzzy Sets and Systems. - № 54 (1993) – Р. 269-277.
8. Herrera F., Alonso S., Chiclana F., Herrera-Viedma E. (2009). Computing with words in deci-sion making: foundations, trends and prospects. Fuzzy Optim Decis Making (2009) 8: 337-364.
9. Cichocki A.(2013) Tensor Decompositions: A New Concept in Brain Data Analysis? arXiv: 1305.0395v1 [cs.NA] 2 May 2013. – 19 pp.
10. Minaev Y.N., Filimonov O.Y., Minaeva J. I. (2013). Tensor model HM - granules and their application to solving fuzzy arithmetic - tics. "Artificial Intelligence". – № 2, 2013. – P.18-31.
11. Van Loan Ch.F. Block Matrix Computa-tions and the Singular Value Decomposition A Tale of Two Ideas. - Services Internet resource.
12. Van Loan Ch.F. (2000) The ubiquitous Kronecker product. Journal of Computational and ap-plied mathematics. 2000, 123 (1-2): 85-100.