"

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.

Neural Network applied to multifunctional materials

TERİN ADALI1,* , ALİ HAYDAR2

Affiliation

  1. Social Science and Science Institute, Girne American University, Karaoglanoglu Girne, P. O. Box: 5 TRNC-via Mersin 10 Turkey
  2. Department of Computer Engineering, Girne American University, Karaoglanoglu Girne, P. O. Box: 5 TRNC-via Mersin 10 Turkey

Abstract

Progress in optoelectronic and electronic sensor technology has enabled new capabilities in the field of sensor construction, particularly miniaturized pH sensors (ion-sensitive field-effect transistors, ISFETS). The possibility of covalent anchoring of polyHEMA on the surface of silicon nitride, using photolithographic techniques for crosslinking of 2-hydroyethyl methacrylate (HEMA) has already demonstrated in the literature. 2-Hydroxyethyl methacrylate, HEMA, and 2-hydroxyethyl methacrylate / diethylene glycol dimethacrylate, HEMA / DEGDMA, systems were chosen as model systems due to their importance as possibly of chemical binding of the ion-selective membrane to the silicon nitride surface. In the manufacturing of durable ion-selective sensors, the mechanical stability of sensors is very important. This property is affected by the light intensity and crosslinking ratio of the polyHEMA and polyHEMA / EGDMA layers produced. The aim of the present work was to develop a nonlinear empirical model and in this way to overcome the difficulty of using the complex polymerization kinetic model. This paper focuses on using the back-propagation multi-layer perceptron (BPMLP) algorithm to predict the monomer conversion. The neural network proposed in this study is very suitable to achieve improved control over the photopolymerization process, in the manufacturing processes of durable ion-selective sensors with photolithographic techniques..

Keywords

Biosensors, HEMA, DEGDMA, Neural Networks, ISFETS.

Submitted at: Nov. 14, 2006
Accepted at: June 15, 2007

Citation

TERİN ADALI, ALİ HAYDAR, Neural Network applied to multifunctional materials, Journal of Optoelectronics and Advanced Materials Vol. 9, Iss. 6, pp. 1618-1622 (2007)