id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_xf2a6wdpgbbs5gx2ibpnpn67i4	Mohamed Bennasar	Feature selection using Joint Mutual Information Maximisation	2015	13	.pdf	application/pdf	10704	1924	57	Feature selection based on information theory is a popular approach due its computational efficiency, scalability in terms of the dataset dimensionality, and independence from the classifier. To address this problem, this article introduces two new nonlinear feature selection methods, namely Feature selection is used in many application areas relevant to exert and intelligent systems, such as data mining and machine learnng, image processing, anomaly detection, bioinformatics and natural election by proposing two new nonlinear feature selection methds based on information theory. This paper also reviews existing feature selection methods highighting their common limitations and compares the performance of ection 4 discusses the limitations of current feature selection criteia, Section 5 introduces the proposed methods. To tackle this problem new methods have been proposed for selecting relevant features, which are non-redundant with Features selected by the JMIM and JMI methods have a method with this dataset with almost any number of selected features, followed by NJMIM.	./cache/work_xf2a6wdpgbbs5gx2ibpnpn67i4.pdf	./txt/work_xf2a6wdpgbbs5gx2ibpnpn67i4.txt