Neural network technologies in experimental computer science (measurement, monitoring, diagnostics, and tests)

Vladyslav D. Tsydelko; Sergiy O. Bragynets

doi:10.1117/12.429716

12 June 2001 Neural network technologies in experimental computer science (measurement, monitoring, diagnostics, and tests)

Vladyslav D. Tsydelko, Sergiy O. Bragynets

Author Affiliations +

Proceedings Volume 4425, Selected Papers from the International Conference on Optoelectronic Information Technologies; (2001) https://doi.org/10.1117/12.429716
Event: International Conference on Optoelectronic Information Technologies, 2000, Vinnytsia, Ukraine

Abstract

Distinguished tendency of modern experimental informatics (EI) and metrology technical means development is their intellectualization. Examples of neural network technologies (NNT) application in modern EI for measurement, monitoring, diagnostics and tests are indicated. Features of NNT from the point of view of their application in means of EI are considered, field of solved by them problems is determined. Parallel 'measurement - classification' is conducted, i.e. problem of measurement -- determination of numerical value of physical quantity -- is considered as problem of classification. Possibility of NNT application in EI for interpolation of interferometer quadrature measuring signals with the purpose of resolving possibility increase in range of nanometer is considered. For solution of interpolation problem some structures of artificial neural networks such as perceptron and probabilistic networks are analyzed. Comparative analysis of exactitude for all considered structures is indicated. Increasing of the interferometer resolution by means of NNT application is possible theoretically up to 0.001 nm.

Citation Download Citation

Vladyslav D. Tsydelko and Sergiy O. Bragynets "Neural network technologies in experimental computer science (measurement, monitoring, diagnostics, and tests)", Proc. SPIE 4425, Selected Papers from the International Conference on Optoelectronic Information Technologies, (12 June 2001); https://doi.org/10.1117/12.429716

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