Preserving convexity through rational cubic spline fractal interpolation function
被引:22
作者:
Viswanathan, P.
论文数: 0引用数: 0
h-index: 0
机构:
Indian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, IndiaIndian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, India
Viswanathan, P.
[1
]
Chand, A. K. B.
论文数: 0引用数: 0
h-index: 0
机构:
Indian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, IndiaIndian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, India
Chand, A. K. B.
[1
]
Agarwal, R. P.
论文数: 0引用数: 0
h-index: 0
机构:
Texas A&M Univ, Dept Math, Kingsville, TX 78363 USA
King Abdulaziz Univ, Fac Sci, Dept Math, Jeddah 21589, Saudi ArabiaIndian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, India
Agarwal, R. P.
[2
,3
]
机构:
[1] Indian Inst Technol, Dept Math, Madras 600036, Tamil Nadu, India
[2] Texas A&M Univ, Dept Math, Kingsville, TX 78363 USA
[3] King Abdulaziz Univ, Fac Sci, Dept Math, Jeddah 21589, Saudi Arabia
We propose a new type of zeta(1)-rational cubic spline Fractal Interpolation Function (F1F) for convexity preserving univariate interpolation. The associated Iterated Function System (IFS) involves rational functions of the form n, where P-n(x)/Q(n)(x) are cubic polynomials determined through the Hermite interpolation conditions of the FIF and Q(n)(x) are preassigned quadratic polynomials with two shape parameters. The rational cubic spline FIF converges to the original function Phi as rapidly as the rth power of the mesh norm approaches to zero, provided Phi(r) is continuous for r = 1 or 2 and certain mild conditions on the scaling factors are imposed. Furthermore, suitable values for the rational IFS parameters are identified so that the property of convexity carries from the data set to the rational cubic FIFs. In contrast to the classical non-recursive convexity preserving interpolation schemes, the present fractal scheme is well suited for the approximation of a convex function Phi whose derivative is continuous but has varying irregularity. (C) 2013 Elsevier BM. All rights reserved.