APA 6th Edition Vojnović, B. i Michieli, I. (2003). Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation. Journal of computing and information technology, 11 (1), 55-66. https://doi.org/10.2498/cit.2003.01.04
MLA 8th Edition Vojnović, Božidar i Ivan Michieli. "Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation." Journal of computing and information technology, vol. 11, br. 1, 2003, str. 55-66. https://doi.org/10.2498/cit.2003.01.04. Citirano 26.02.2021.
Chicago 17th Edition Vojnović, Božidar i Ivan Michieli. "Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation." Journal of computing and information technology 11, br. 1 (2003): 55-66. https://doi.org/10.2498/cit.2003.01.04
Harvard Vojnović, B., i Michieli, I. (2003). 'Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation', Journal of computing and information technology, 11(1), str. 55-66. https://doi.org/10.2498/cit.2003.01.04
Vancouver Vojnović B, Michieli I. Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation. Journal of computing and information technology [Internet]. 2003 [pristupljeno 26.02.2021.];11(1):55-66. https://doi.org/10.2498/cit.2003.01.04
IEEE B. Vojnović i I. Michieli, "Detecting Noise in Chaotic Signals through Principal Component Matrix Transformation", Journal of computing and information technology, vol.11, br. 1, str. 55-66, 2003. [Online]. https://doi.org/10.2498/cit.2003.01.04
Sažetak We study the reconstruction of continuous chaotic attractors from noisy time-series. A method of delays and principal component eigenbasis (defined by singular vectors) is used for state vectors reconstruction. We introduce a simple measure of trajectory vectors directional distribution for chosen principal component subspace, based on nonlinear transformation of principal component matrix. The value of such defined measure is dependent on the amount of noise in the data. For isotropically distributed noise (or close to isotropic), that allows us to set up window width boundaries for acceptable attractor reconstruction as a function of noise content in the data.