Adaptive step size kernel least mean square algorithm for Lorenz time series prediction

Author

Shoaib, Bilal ; Qureshi, Ijaz Mansoor ; Butt, Sharjeel Abid ; Khan, Shafqat Ullah ; Khan, Wasim

Author_Institution

Dept. of Electron. Eng., Int. Islamic Univ., Islamabad, Pakistan

fYear

2015

fDate

13-17 Jan. 2015

Firstpage

218

Lastpage

221

Abstract

An adaptive stepsize kernel least mean square(AKLMS) algorithm is presented in this paper. A mechanism is introduced here to adjust the stepsize parameter in the output of the KLMS algorithm using gradient descent method. The proposed method improves the results by reducing the training time of the algorithm that also helps in converging to global minima instead of local minima. We named the algorithm, the adaptive stepsize KLMS algorithm. Simulation results for the prediction of chaotic Lorenz series is presented in the terms of mean square error as the figure of merit. To validate the algorithm, comparison is made with KLMS.

Keywords

chaos; convergence; gradient methods; least mean squares methods; time series; AKLMS algorithm; Lorenz time series prediction; adaptive step size kernel least mean square algorithm; adaptive stepsize KLMS algorithm; algorithm training time; chaotic Lorenz series prediction; convergence; global minima; gradient descent method; local minima; mean square error; step size parameter adjustment; Adaptive filters; Kernel; Kernel LMS; LMS; Lorenz Chaotic Time Series;

fLanguage

English

Publisher

ieee

Conference_Titel

Applied Sciences and Technology (IBCAST), 2015 12th International Bhurban Conference on

Conference_Location

Islamabad

Type

conf

DOI

10.1109/IBCAST.2015.7058507

Filename

7058507