Holographic neuro-predictor for fractional Brownian motion

Alexander V. Pavlov; Ravil Z. Zakirov; Vlad S. Bilyk; Vladimir V. Vedeneev

doi:10.1117/12.498462

8 July 2003 Holographic neuro-predictor for fractional Brownian motion

Alexander V. Pavlov, Ravil Z. Zakirov, Vlad S. Bilyk, Vladimir V. Vedeneev

Proceedings Volume 5036, Photonics, Devices, and Systems II; (2003) https://doi.org/10.1117/12.498462
Event: Photonics, Devices, and Systems II, 2002, Prague, Czech Republic

Abstract

In this paper we discuss our approach to based on holographic techniques implementation of neuro-fuzzy predictor for processes, described by Fractal Brownian Motion (FBM) model. We use the model of the predictor as a Riemann - Stieltjes integral over the observed traffic of specific weight function. We discuss two-layered bi-directional optical neural network to find our solution. To find the weight function we use non-linearity in the correlation layer of the neural network. In our experiments we used air-photograph of forest as this kind of images demonstrates self-similarity property and can be described by the FBM model. As a first step we used approximate solution for the weight function, achieved by using binary filtering function in the correlation layer. We demonstrate experimental results and discuss directions of our future investigations.

Citation Download Citation

Alexander V. Pavlov, Ravil Z. Zakirov, Vlad S. Bilyk, and Vladimir V. Vedeneev "Holographic neuro-predictor for fractional Brownian motion", Proc. SPIE 5036, Photonics, Devices, and Systems II, (8 July 2003); https://doi.org/10.1117/12.498462

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available