Quick search
Go!

PREDICTION OF THE LIQUID CRYSTALLINE BEHAVIOR FOR SOME BIS PHENIL AROMATIC DERIVATIVES WITH ARTIFICIAL NEURAL NETWORKS


CATALIN LISA*, VICTOR BULACOVSCHI
TECHNICAL UNIVERSITY „GH. ASACHI” IAŞI, FACULTY OF CHEMICAL ENGINEERING AND ENVIRONMENTAL PROTECTION, BLVD. D. MANGERON 71, 700050 - IAŞI, ROMANIA *CORRESPONDING AUTHOR: CLISA@CH.TUIAŞI.RO

Issue:

SCSCC6, Volume VIII, No. 2

Section:

Volume VIII, No. 2 (2007)

Abstract:

Artificial neural networks (ANN) are robust and efficient mathematical tools inspired by the biological nervous system, and can be used to simulate a wide variety of complex scientific and engineering problems. A powerful ANN function is determined largely by the interconnections between artificial neurons, similar to those occurring in their natural counterparts of biological systems. Neural network based method proved to be able to appreciate the liquid crystalline behavior with small errors, so it represents an effective tool for structure – properties prediction. The most common type ANN with multiple layers has been used in this work.

Keywords:

liquid crystal properties, prediction, feed forward neural networks.

Code [ID]:

CSCC6200708V02S01A0001 [0001952]

Full paper:

Download pdf


Copyright (c) 1995-2007 University of Bacu