Current Derivative Estimation of Non-stationary Processes Based on Metrical Information

被引：5

作者：

Kochegurova, Elena ^{[1
]}

Gorokhova, Ekaterina ^{[1
]}

机构：

[1] Tomsk Polytech Univ, Tomsk 634050, Russia

来源：

COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2015), PT II | 2015年 / 9330卷

关键词：

Recurrent algorithm; Derivatives estimation; Variation smoothing spline;

D O I：

10.1007/978-3-319-24306-1_50

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Demand for estimation of derivatives has arisen in a range of some applied problems. One of the possible approaches to estimating derivatives is to approximate measurement data. The problem of real-time estimation of derivatives is investigated. A variation method of obtaining recurrent smoothing splines is proposed for estimation of derivatives. A distinguishing feature of the described method is recurrence of spline coefficients with respect to its segments and locality about measured values inside the segment. Influence of smoothing spline parameters on efficiency of such estimations is studied. Comparative analysis of experimental results is performed.

引用

页码：512 / 519

页数：8

共 11 条

[1] Ageev U. M., 1990, NOTIFY HIGH SCH INST, V3, P3
[2] Estimating curves and derivatives with parametric penalized spline smoothing
Cao, Jiguo
Cai, Jing
Wang, Liangliang
[J]. STATISTICS AND COMPUTING, 2012, 22 (05) : 1059 - 1067
[3] De Brabanter K, 2013, J MACH LEARN RES, V14, P281
[4] Dmitriev V. I., 2010, COMP MATH MATH PHYS, V21, P206, DOI DOI 10.1007/S10598-010-9065-7
[5] Golubinsky A. N., 2007, HEARLD VORONEZH I MI, V2, P138
[6] Kochegurova E. A., 2006, NOTIFY TOMSK POLYTEC, V7, P36
[7] ERROR-BOUNDS FOR DERIVATIVE ESTIMATES BASED ON SPLINE SMOOTHING OF EXACT OR NOISY DATA
RAGOZIN, DL
[J]. JOURNAL OF APPROXIMATION THEORY, 1983, 37 (04) : 335 - 355
[8] Rozhenko A. I., 2007, THESIS, P231
[9] Vershinin V. V., 1988, EXTREME PROPERTIES S, P102
[10] Voskoboynikov Y. E., 2003, J AVTOMETRIYA, V39, P3

← 1 2 →