"

Cookies ussage consent

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

I agree, do not show this message again.

Prediction of the liquid crystalline property for polyazomethines using modular neural networks

S. CURTEANU1,* , C. RACLES2, V. COZAN2

Affiliation

  1. “Gh. Asachi” Technical University, Department of Chemical Engineering, Bd. D. Mangeron No. 71A, 700050, Iasi, Romania
  2. “Petru Poni” Institute of Macromolecular Chemistry, Aleea Gr.Ghica Voda 41A, Iasi, 700487, Romania

Abstract

The liquid crystalline properties of the poly(siloxane - azomethine)s were studied by experiment and simulation. A special class of neural networks was used in this paper – modular neural networks – to predict the liquid crystalline behavior as function of some molecular parameters which count for geometrical features (fully extended length and diameter of the structural unit) or polarizability features (dipole moment). The importance of an adequate choice of the input parameters for the neural models was emphasized. Satisfactory results are obtained with this neural network based method, especially in the validation phase of the models..

Keywords

Liquid crystal, Polyazomethines, Modular neural networks.

Submitted at: Oct. 31, 2007
Accepted at: Dec. 10, 2008

Citation

S. CURTEANU, C. RACLES, V. COZAN, Prediction of the liquid crystalline property for polyazomethines using modular neural networks, Journal of Optoelectronics and Advanced Materials Vol. 10, Iss. 12, pp. 3382-3391 (2008)