Abstract
Like standard discrete artificial neural networks (ANNs), continual neurodynamical systems can be used for classification and diagnosis of breast cancer. In this paper a two-feature generalized bidirectional associative memory classifier is formulated in tensorial invariant form. It is implemented in `Mathematica 3.0' and tested on two sample features (radius and perimeter of cell nuclei in free needle aspiration slides) from Wisconsin breast-cancer database. The classification accuracy obtained (86%) together with invariance of the classification result upon the variation of dimension and output-form of neural activation fields, shows the potential classification ability of theoretical classifiers directly-implemented into computer algebra systems.
Original language | English |
---|---|
Title of host publication | 1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems |
Editors | L. C. Jain |
Place of Publication | Piscataway, NJ, USA |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 296-299 |
Number of pages | 4 |
ISBN (Print) | 0-7803-5578-4 |
DOIs | |
Publication status | Published - 1999 |
Event | Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99) - Adelaide, Aust Duration: 31 Aug 1999 → 1 Sept 1999 |
Conference
Conference | Proceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99) |
---|---|
City | Adelaide, Aust |
Period | 31/08/99 → 1/09/99 |