Macromolecular Research, Vol.10, No.1, 13-17, February, 2002
Influences of the Input on ANN and QSPR of Homopolymers
E-mail:
An artificial neural network (ANN) was used to study the relationship between the glass transition temperature (Tg) and the structure of homopolymers. The input is very important for the ANN. In this paper, six kinds of input vectors were designed for the ANN. Of the six approaches, the best one gave the Tg of 251 polymers with a standard deviation of 8 K and a maximum error of 29 K. The trained ANN also predicted the Tg of 20 polymers which are not included in the 251 polymers with a standard deviation of 7 K and a maximum error of 21 K.
- van Krevelen DW, Properties of Polymers, Third edition, Amsterdam, Elsevier (1990)
- Bicerano J, Prediction of Polymer Properties, Marcel Dekker, New York (1993)
- Ulmer CW, Smith DA, Sumpter BG, Comput. Theor. Polym. Sci., 8(3-4), 311 (1998)
- Sumpter BG, Noid DW, Macromol. Thoer. Simul., 3, 363 (1994)
- Ebube NK, Ababio GO, Adeyeye CM, Int. J. Pharm., 196, 27 (2000)
- Haykin S, Neural Networks - a Comprehensive Foundation, Macmillan College Publishing Company, New York (1994)
- Brandrup J, Polymer Handbook, Third edition, New York (1989)
- Bhat BR, Modern Probability Theory - an Introductory Textbook, Second edition, New York (1985)