Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.
About 10,000 papers for “Feature selection”
Verleysen, Michel, Soft Computing and Statistics, COST Action IC0702 summer course 2009 · Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) · 2009
Cited by 0
Suhang Wang, Jiliang Tang, Huan Liu · Encyclopedia of Machine Learning and Data Mining · 2017
Cited by 16
Amin Zollanvari · 2023
Cited by 5
Robert Nisbet, Gary Miner, Ken Yale · Elsevier eBooks · 2018
Cited by 3
S THEODORIDIS, Aggelos Pikrakis, Konstantinos Koutroumbas et al. · Elsevier eBooks · 2010
Cited by 3
Курт Вармуза · Lecture notes in chemistry · 1980
Cited by 1
Jianqing Fan · 2016
Cited by 0
Kristin Larsson (3812860), Simon Baker (3812857), Ilona Silins (142059) et al. · Figshare · 2017
<p>The number of features for each node in the taxonomy after the feature selection step.</p>
Cited by 0Open access
Stuart Sutherland · Nature · 1998
Cited by 10Open access
Matthias Reif A, Faisal Shafait B · 2013
Classification Forward selection a b s t r a c t Most of the widely used pattern classification algorithms, such as Support Vector Machines (SVM), are sensitive to the presence of irrelevant or redundant features in the training data. Automatic feature selection algorithms aim at selecting a subset of features present in a given dataset so that the achieved accuracy of the following classifier can be maximized. Feature selection algorithms are generally categorized into two broad categories: algorithms that do not take the following classifier into account (the filter approaches), and algorithms that evaluate the following classifier for each considered feature subset (the wrapper approaches). Filter approaches are typically faster, but wrapper approaches deliver a higher performance. In this paper, we present the algorithm – Predictive Forward Selection – based on the widely used wrapper approach forward selection. Using ideas from meta-learning, the number of required evaluations of the target classifier is reduced by using experience knowledge gained during past feature selection runs on other datasets. We have evaluated our approach on 59 real-world datasets with a focus on SVM as the target classifier. We present comparisons with state-of-the-art wrapper and filter approaches as well as one embedded method for SVM according to accuracy and run-time. The results show that the presented method reaches the accuracy of traditional wrapper approaches requiring significantly less evaluations of the target algorithm. Moreover, our method achieves statistically significant better results than the filter approaches as well as the embedded method. &amp; 2013 Elsevier Ltd. All rights reserved. 1.
Cited by 0
Ruye Wang · Cambridge University Press eBooks · 2025
Emphasizing how and why machine learning algorithms work, this introductory textbook bridges the gap between the theoretical foundations of machine learning and its practical algorithmic and code-level implementation. Over 85 thorough worked examples, in both Matlab and Python, demonstrate how algorithms are implemented and applied whilst illustrating the end result. Over 75 end-of-chapter problems empower students to develop their own code to implement these algorithms, equipping them with hands-on experience. Matlab coding examples demonstrate how a mathematical idea is converted from equations to code, and provide a jumping off point for students, supported by in-depth coverage of essential mathematics including multivariable calculus, linear algebra, probability and statistics, numerical methods, and optimization. Accompanied online by instructor lecture slides, downloadable Python code and additional appendices, this is an excellent introduction to machine learning for senior undergraduate and graduate students in Engineering and Computer Science.
Cited by 1
Menaa Nawaz (14304920), Jameel Ahmed (9946639) · Figshare · 2022
Cited by 0Open access
Leyuan Shi, Sigurdur Ólafsson · RePEc: Research Papers in Economics
Feature Selection, Average Accuracy, Information Gain, Feature Subset, Promising Region
Cited by 0
Stefan Selle · 2024
Cited by 0
A. Ardeshir Goshtasby · 2004
This chapter contains sections titled: Points Lines Regions Templates Summary Bibliographical Remarks
Cited by 0
Damien François · IGI Global eBooks · 2011
In many applications, like function approximation, pattern recognition, time series prediction, and data mining, one has to build a model relating some features describing the data to some response value. Often, the features that are relevant for building the model are not known in advance. Feature selection methods allow removing irrelevant and/or redundant features to only keep the feature subset that are most useful to build a prediction model. The model is simpler and easier to interpret, reducing the risks of overfitting, non-convergence, etc. By contrast with other dimensionality reduction techniques such as principal component analysis or more recent nonlinear projection techniques (Lee & Verleysen 2007), which build a new, smaller set of features, the features that are selected by feature selection methods preserve their initial meaning, potentially bringing extra information about the process being modeled (Guyon 2006). Recently, the advent of high-dimensional data has raised new challenges for feature selection methods, both from the algorithmic point of view and the conceptual point of view (Liu & Motoda 2007). The problem of feature selection is exponential in nature, and many approximate algorithms are cubic with respect to the initial number of features, which may be intractable when the dimensionality of the data is large. Furthermore, high-dimensional data are often highly redundant, and two distinct subsets of features may have very similar predictive power, which can make it difficult to identify the best subset. Request access from your librarian to read this chapter's full text.
Cited by 0
2015
Cited by 1
Seema R. Chaudhary, Sangeeta Kakarwal, Chitra Gaikwad · 2021
From the last few years research in Musical Information Retrieval (MIR) is increased. Enormous availability of audio content on the internet demands audio information retrieval in less time. Many have explored music genre, singer identification, audio scene analysis, and instrument classification. It is technically challenging to search similar music pieces, singers, or instruments from available audio files as unstructured data. The classifier's performance depends on the features used to train and test the classifier. Hence, it is important not only to feature extraction from audio signal but also to select relevant features from a large set of extracted features, increasing classification accuracy. This empirical study focuses on the filter approach of feature selection using the Correlation Pearson coefficient, InfoGain, Gain Ration and ReliefF methods to classify Indian musical instruments. It checks the effectiveness of selection methods on classification. The performance of selected features is evaluated using a Random Forest classifier. From result, highest classification accuracy 93% has been achieved by the Information Gain method for top selected features i.e. Flatness, Mean, MFCC 4th Coefficient, Spectral Rolloff(85%) and Zero Crossing Rate.
Cited by 1
Leyuan Shi, Sigurður Ólafsson · International series in management science/operations research/International series in operations research & management science · 2008
Cited by 0
Suhang Wang, Jiliang Tang, Huan Liu · Encyclopedia of Machine Learning and Data Mining · 2016
Cited by 21