Input Feature Selection by Mutual Information Based on Parzen Window

By Nojun Kwak, Chong-Ho Choi. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

650 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1d4c3311375d7a9e6b9672988a1bff3c90adbf05

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

Citations in the corpus

Efficient multivariate entropy estimation via $k$-nearest neighbour distances (2016, neutral): “…entropy that is of primary interest, for instance in goodness-of-fit tests of normality (Vasicek, 1976) or uniformity (Cressie, 1976), tests of independence (Goria et al., 2005), independent component analysis (Miller and Fisher, 2003) and feature selection in classification (Kwak and Choi, 2002).”
Edgeworth Approximation of Multivariate Differential Entropy (2005, background): “Another approach is to estimate mutual information from a Parzen window density estimator (Kwak & Choi, 2002).”
Pattern classification with missing data: a review (2010, methodology): “The mutual information has been computed using a Parzen window approach [83].”
MINE: Mutual Information Neural Estimation (2018, background): “…general problems, common approaches include binning (Fraser & Swinney, 1986; Darbellay & Vajda, 1999), kernel density estimation (Moon et al., 1995; Kwak & Choi, 2002), Edgeworth expansion based estimators Van Hulle (2005) and likelihood-ratio estimators based on support vector machines (SVMs,…”
Scalable Mutual Information Estimation Using Dependence Graphs (2018, methodology): “Non-parametric MI estimation methods have been studied that use estimation strategies including KSG [4], KDE [5] and Parzen window density estimation [6].”
Mutual Information Neural Estimation (2018, background): “…on support vector machines, non-parametric kernel-density estimators; see, Fraser & Swinney, 1986; Darbellay & Vajda, 1999; Suzuki et al., 2008; Kwak & Choi, 2002; Moon et al., 1995; Kraskov et al., 2004), or rely on approximate gaussianity of data distribution (e.g., Edgeworth expansion, Van…”
An Effective Feature Selection Method via Mutual Information Estimation (2012, methodology): “The better performance of MI-PW over mRMR and Kwak is expected since the latter two methods use the forward feature selection scheme.”
Simultaneous feature selection and clustering using mixture models (2004, background): “They can be divided roughly into two categories: hierarchical clustering, which creates a “tree” with branches merging at different levels, and partitional clustering, which divides the data into different “flat” clusters.”
Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy (2003, methodology): “For some applications where it is unclear how to properly discretize the continuous data, an alternative solution is to use density estimation method (e.g., Parzen windows) to approximate Iðx; yÞ, as suggested by earlier work in medical image registration [7] and feature selection [17].”
MILES: Multiple-Instance Learning via Embedded Instance Selection (2006, neutral): “tion [41], [29], [25], [30], [39], [12], [23], [28], [31], [50], [57].”
Universal Estimation of Information Measures for Analog Sources (2009, methodology): “In [145], a method is proposed for learning discriminative feature transforms using a criterion based on the mutual information between class labels and transformed features.”
A Survey on Malware Detection Using Data Mining Techniques (2017, background): “Feature selection is an important step in many classiﬁcation or prediction problems [Langley 1994; Jain et al. 2000; Kwak and Choi 2002; Murphy 2012].”