id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_663xupkdkzhanoy2e2fbo7p2jm	Jia Wu	Self-adaptive attribute weighting for Naive Bayes classification	2015	17	.pdf	application/pdf	14252	2934	72	In this paper, we propose a new Artificial Immune System (AIS) based self-adaptive attribute weighting method for Naive Bayes classification. As a result, AISWNB can obtain good attribute weight values during the learning process. Keywords: Naive Bayes, Self-Adaptive, Attribute Weighting, Artificial Immune Systems, Evolutionary Computing Because weight values enforce attributes to play different roles in classification, the corresponding Weighted Naive Bayes (WNB) will help relax the conditional independence assumption and make NB efficient for data then propose a new method to automatically calculate optimal attribute weight values for WNB, by directly working on six image classification data sets (Li & Wang, 2008), demonstrate that the proposed artificial immune systems based weighting scheme for Naive Bayes classification (AISWNB) can successfully find optimal weight combinations for different learning tasks, and its performance consistently outperforms other to search optimal weight values for weighted naive Bayes classification, our method is related to attribute weighting in machine learning and AIS based evolutionary computation.	./cache/work_663xupkdkzhanoy2e2fbo7p2jm.pdf	./txt/work_663xupkdkzhanoy2e2fbo7p2jm.txt