Abstract
A novel convex set based neuro-fuzzy algorithm for classification of difficult-to-diagnose instances of breast cancer is described in this paper. The new approach offers rational advantages over the leading neural algorithm - backpropagation. The comparative results obtained using receiver operating characteristic (ROC) analysis show that the ability of the convex set based method to infer knowledge is better than that of backpropagation, making it more suitable for use in real diagnostic systems.
| Original language | English (US) |
|---|---|
| Title of host publication | Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings |
| Publisher | IEEE |
| Number of pages | 1 |
| Volume | 2 |
| ISBN (Print) | 0780356756 |
| State | Published - Dec 1 1999 |
| Externally published | Yes |
| Event | Proceedings of the 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Fall Meeting of the Biomedical Engineering Society (1st Joint BMES / EMBS) - Atlanta, GA, USA Duration: Oct 13 1999 → Oct 16 1999 |
Other
| Other | Proceedings of the 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Fall Meeting of the Biomedical Engineering Society (1st Joint BMES / EMBS) |
|---|---|
| City | Atlanta, GA, USA |
| Period | 10/13/99 → 10/16/99 |
All Science Journal Classification (ASJC) codes
- Bioengineering