Results 21 to 30 of about 96,228 (258)
Feature ranking for semi-supervised learning
Machine Learning, 2022 AbstractThe data used for analysis are becoming increasingly complex along several directions: high dimensionality, number of examples and availability of labels for the examples. This poses a variety of challenges for the existing machine learning methods, related to analyzing datasets with a large number of examples that are described in a high ...
Matej Petkovic +2 more
openaire +2 more sources
Alternative Relative Discrimination Criterion Feature Ranking Technique for Text Classification
IEEE Access, 2023 The use of text data with high dimensionality affects classifier performance. Therefore, efficient feature selection (FS) is necessary to reduce dimensionality.
Sarah Abdulkarem Alshalif +6 more
doaj +1 more source
Decision Support System for Predicting Mortality in Cardiac Patients Based on Machine Learning
Applied Sciences, 2023 Researchers have proposed several automated diagnostic systems based on machine learning and data mining techniques to predict heart failure. However, researchers have not paid close attention to predicting cardiac patient mortality.
Ashir Javeed +5 more
doaj +1 more source
Wrapper for Ranking Feature Selection [PDF]
, 2004 We propose a new feature selection criterion not based on calculated measures between attributes, or complex and costly distance calculations. Applying a wrapper to the output of a new attribute ranking method, we obtain a minimum subset with the same error rate as the original data.
Roberto Ruiz +2 more
openaire +2 more sources
The Feature Importance Ranking Measure [PDF]
, 2009 15 pages, 3 figures. to appear in the Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD ...
Alexander Zien +3 more
openaire +3 more sources
Number of Instances for Reliable Feature Ranking in a Given Problem
Business Systems Research, 2018 Background: In practical use of machine learning models, users may add new features to an existing classification model, reflecting their (changed) empirical understanding of a field. New features potentially increase classification accuracy of the model
Bohanec Marko +2 more
doaj +1 more source
Online Learning to Rank with Features
CoRR, 2018 We introduce a new model for online ranking in which the click probability factors into an examination and attractiveness function and the attractiveness function is a linear function of a feature vector and an unknown parameter. Only relatively mild assumptions are made on the examination function. A novel algorithm for this setup is analysed, showing
Shuai Li 0010 +2 more
openaire +3 more sources
Fast Feature Ranking Algorithm [PDF]
, 2003 The attribute selection techniques for supervised learning, used in the preprocessing phase to emphasize the most relevant attributes, allow making models of classification simpler and easy to understand. The algorithm has some interesting characteristics: lower computational cost (O(m n log n) m attributes and n examples in the data set) with respect ...
Roberto Ruiz +2 more
openaire +2 more sources
Analysis of Feature Rankings for Classification [PDF]
, 2005 Different ways of contrast generated rankings by feature selection algorithms are presented in this paper, showing several possible interpretations, depending on the given approach to each study. We begin from the premise of no existence of only one ideal subset for all cases.
Roberto Ruiz +3 more
openaire +3 more sources
Classification with correlated features: unreliability of feature ranking and solutions [PDF]
Bioinformatics, 2011 AbstractMotivation: Classification and feature selection of genomics or transcriptomics data is often hampered by the large number of features as compared with the small number of samples available. Moreover, features represented by probes that either have similar molecular functions (gene expression analysis) or genomic locations (DNA copy number ...
Tolosi, L., Lengauer, T.
openaire +3 more sources