C4.5: programs for machine learning
C4.5: programs for machine learning
An Algorithm for Subgraph Isomorphism
Journal of the ACM (JACM)
A system for induction of oblique decision trees
Journal of Artificial Intelligence Research
An assessment of submissions made to the predictive toxicology evaluation challenge
IJCAI'99 Proceedings of the 16th international joint conference on Artifical intelligence - Volume 1
Combining Classifiers of Pesticides Toxicity through a Neuro-fuzzy Approach
MCS '02 Proceedings of the Third International Workshop on Multiple Classifier Systems
Hi-index | 0.00 |
One approach to deal with real complex systems is to use two or more techniques in order to combine their different strengths and overcome each other's weakness to generate hybrid solutions. In this project we pointed out the needs of an improved system in toxicology prediction. An architecture able to satisfy these needs has been developed. The main tools we integrated are rules and ANN. We defined chemical structures of fragments responsible for carcinogenicity according to human experts. After them we developed specialized rules to recognize these fragments into a given chemical and to assess their toxicity. In practice the rule-based expert associates a category to each fragment found, then a category to the molecule. Furthermore, we developed an ANN-based expert that uses molecular descriptors in input and predicts carcinogenicity as a numerical value. Finally we added a classifier program to combine the results obtained from the two previous experts into a single predictive class of carcinogenicity to man.