An unsupervised approach to feature discretization and selection

Ferreira, Artur J.; Figueiredo, Mário A. T.

doi:10.1016/j.patcog.2011.12.008

Cited by 123 publications

(66 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the methods using this approach are typically fast but they need a threshold as the stopping criterion for feature selection. Several filter-based methods have been proposed in the literature including information gain, 10 gain ratio, 11 term variance, 12 Gini index, 13 Laplacian score, 14 Fisher score, 15 minimal-redundancy-maximal-relevance, 16 random subspace method, 17 relevance-redundancy feature selection, 18 unsupervised feature selection method based on ant colony optimization (UFSACO), 19 relevance-redundancy feature selection based on ant colony optimization (RRFSACO), 20 graph clustering with node centrality for feature selection method (GCNC), 21 and graph clustering based ant colony optimization feature selection method (GCACO). 22 Wrapper-based methods combine feature selection with the design of the classifier and evaluate the feature subsets on the basis of the accuracy of classification.…”

Section: Related Workmentioning

confidence: 99%

“…In the case of S-shaped and V-shaped conversion functions, the number of each dimension feature data belonging to the optimal feature subset is counted, as shown in Figure 7. It can be seen from Figure 7 that the number of the 3rd, 13th, 22nd, 23rd, 24th, and 31st dimensions of the optimal feature subsets is the largest, but the final optimal feature subsets {1, 3,10,11,12,13,14,18,19,21,23,24,29,30,31} do not incorporate all of these higherfrequency features (that is, the optimal feature subset is not a simple combination of features with high frequency). The optimal feature subset does not necessarily include features with high frequency, since the feature subset selected by features of high frequency only may not have the best classification effect.…”

Section: V1mentioning

confidence: 99%

See 1 more Smart Citation

A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

et al. 2018

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Effective feature selection determines the efficiency and accuracy of a learning process, which is essential in human activity recognition. In existing works, for simplification purposes, feature selection algorithms are mostly based on the assumption of feature independence. However, in some scenarios, the optimization method based on this independence hypothesis results in poor recognition performance. This article proposes a correlation-based binary particle swarm optimization method for feature selection in human activity recognition. In the proposed algorithm, the particle swarm optimization algorithm is no longer used as a black box. Meanwhile, correlation coefficients among the features are added to binary particle swarm optimization as a feature correlation factor to determine the position of particles, so that the feature with more information is more likely to be selected. The k-nearest neighbor classifier is then used as the fitness function in the particle swarm optimization to evaluate the performance of the feature subset, that is, feature combination with the highest k-nearest neighbor classifier recognition rate would be picked as the eigenvector. Experimental results show that the proposed method can work well with six classifiers, namely, J48, random forest, knearest neighbor, multilayer perceptron, naïve Bayesian, and support vector machine, and the new algorithm can improve the classification accuracy in the OPPORTUNITY Activity Recognition dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: V1mentioning

confidence: 99%

A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

et al. 2018

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…Not all metrics cater to all the varieties as an example the most common metrics indicating the strength of the linear relationship between two variables; Pearson product-moment correlation coefficient needs both the variables to be numeric. Many algorithms require the features to be discrete There is an elaborate note in [42], on use of feature discretization and feature selection in conjunction. Many algorithms deal only with discretized data.…”

Section: Univariate Multivariate All Types Of Datamentioning

confidence: 99%

Feature Selection: A Practitioner View

Goswami¹,

Chakrabarti²

2014

IJITCS

View full text Add to dashboard Cite

Abstract-Feature selection is one of the most important preprocessing steps in data mining and knowledge Engineering. In this short review paper, apart from a brief taxonomy of current feature selection methods, we review feature selection methods that are being used in practice. Subsequently we produce a near comprehensive list of problems that have been solved using feature selection across technical and commercial domain. This can serve as a valuable tool to practitioners across industry and academia. We also present empirical results of filter based methods on various datasets. The empirical study covers task of classification, regression, text classification and clustering respectively. We also compare filter based ranking methods using rank correlation.

show abstract

“…Unsupervised Methods Recently, two scalar unsupervised FD methods, based on the Linde-Buzo-Gray (LBG) algorithm [25], have been proposed [26]. The first method, named U-LBG1, applies the LBG algorithm individually to each feature, and stops when the mean square error (MSE) distortion falls below a threshold ∆ or when a maximum number, q, of bits per feature is reached.…”

Section: Feature Discretizationmentioning

confidence: 99%

“…. , 10} has been shown to be adequate [26] for different types of data. Naturally, U-LBG1 may discretize features using a variable number of bits.…”

Section: Feature Discretizationmentioning

confidence: 99%

Towards a Classification Approach using Meta-Biclustering: Impact of Discretization in the Analysis of Expression Time Series

Carreiro

Ferreira

Figueiredo

et al. 2012

Journal of Integrative Bioinformatics

Self Cite

View full text Add to dashboard Cite

SummaryBiclustering has been recognized as a remarkably effective method for discovering local temporal expression patterns and unraveling potential regulatory mechanisms, essential to understanding complex biomedical processes, such as disease progression and drug response. In this work, we propose a classification approach based on meta-biclusters (a set of similar biclusters) applied to prognostic prediction. We use real clinical expression time series to predict the response of patients with multiple sclerosis to treatment with Interferon-β. As compared to previous approaches, the main advantages of this strategy are the interpretability of the results and the reduction of data dimensionality, due to biclustering. This would allow the identification of the genes and time points which are most promising for explaining different types of response profiles, according to clinical knowledge. We assess the impact of different unsupervised and supervised discretization techniques on the classification accuracy. The experimental results show that, in many cases, the use of these discretization methods improves the classification accuracy, as compared to the use of the original features.

show abstract

An unsupervised approach to feature discretization and selection

Cited by 123 publications

References 20 publications

A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

A correlation-based binary particle swarm optimization method for feature selection in human activity recognition

Feature Selection: A Practitioner View

Towards a Classification Approach using Meta-Biclustering: Impact of Discretization in the Analysis of Expression Time Series

Contact Info

Product

Resources

About