A new two-feature GBAM-neurodynamical classifier for breast cancer diagnosis

Tijana Ivancevic, Lakhmi Jain, Murk Bottema

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

8 Citations (Scopus)

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 languageEnglish
Title of host publication1999 Third International Conference on Knowledge-Based Intelligent Information Engineering Systems
EditorsL. C. Jain
Place of PublicationPiscataway, NJ, USA
PublisherInstitute of Electrical and Electronics Engineers
Pages296-299
Number of pages4
ISBN (Print)0-7803-5578-4
DOIs
Publication statusPublished - 1999
EventProceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99) - Adelaide, Aust
Duration: 31 Aug 19991 Sept 1999

Conference

ConferenceProceedings of the 1999 3rd International Conference on Knowledge-Based Intelligent Information Engineering Systems (KES '99)
CityAdelaide, Aust
Period31/08/991/09/99

Fingerprint

Dive into the research topics of 'A new two-feature GBAM-neurodynamical classifier for breast cancer diagnosis'. Together they form a unique fingerprint.

Cite this