作者: Loris Nanni , Alessandra Lumini
DOI: 10.1007/S00521-007-0170-2
关键词:
摘要: In this paper, we study the performance improvement that it is possible to obtain combining classifiers based on different notions (each trained using a physicochemical property of amino-acids). This multi-classifier has been tested in three problems: HIV-protease; recognition T-cell epitopes; predictive vaccinology. We propose combines classifier approaches problem as two-class pattern and method one-class classifier. Several combined with “sum rule” enables us an over best results previously published literature.