A review of unsupervised feature selection methods

Solorio-Fernández, Saúl; Carrasco-Ochoa, Jesús Ariel; Martínez-Trinidad, José Fco.

doi:10.1007/s10462-019-09682-y

Cited by 473 publications

(246 citation statements)

References 122 publications

Supporting

Mentioning

204

Contrasting

Unclassified

Order By: Relevance

“…For the sake of validating the results of the two mentioned experiments, it is essential to explain the main methodologies followed to validate unsupervised feature selection methods. The following points describe the main categories for unsupervised feature selection validation techniques as researched in [21].…”

Section: Analysis and Experimental Resultsmentioning

confidence: 99%

“…In[19] an inclusive research is done investigating various semi-supervised techniques in various fields and applications. Finally, the work in[20] introduces a new perspective for supervised feature selection methods, including more recent studies and different taxonomies comparing to the ones described in the latter papers.On the other hand, a few research studies concentrated their efforts to analyze unsupervised methods for feature selection such as, the work in[21] where they pointed out the lack of survey research in this area, and offered a detailed analysis of numerous unsupervised methods along with summarizing their advantages and disadvantages, as well as an experimental comparisons between them. The work in[22] narrowed down the scope of the research in[21] and instead, it focuses specifically on clustering algorithms for feature selection providing various clustering techniques for genetic, text, streaming and linked data.…”

mentioning

confidence: 99%

“…Finally, the work in[20] introduces a new perspective for supervised feature selection methods, including more recent studies and different taxonomies comparing to the ones described in the latter papers.On the other hand, a few research studies concentrated their efforts to analyze unsupervised methods for feature selection such as, the work in[21] where they pointed out the lack of survey research in this area, and offered a detailed analysis of numerous unsupervised methods along with summarizing their advantages and disadvantages, as well as an experimental comparisons between them. The work in[22] narrowed down the scope of the research in[21] and instead, it focuses specifically on clustering algorithms for feature selection providing various clustering techniques for genetic, text, streaming and linked data. Moreover, they finalized their review with some challenges that clustering algorithms for feature selection witness and elaborated with some suggestions to overcome the proposed challenges.In this paper, we narrowed down the scope even more, to include clustering feature selection algorithms using k-means clustering alone.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Feature Selection Using Recursive k-Means Silhouette Elimination (RkSE): A Two-Scenario Case Study for Fault Classification of High-Dimensional Sensor Data

Mallak¹,

Fathi²

2020

Preprint

View full text Add to dashboard Cite

Feature selection is a crucial step to overcome the curse of dimensionality problem in data mining. This work proposes Recursive k-means Silhouette Elimination (RkSE) as a new unsupervised feature selection algorithm to reduce dimensionality in univariate and multivariate time-series datasets. Where k-means clustering is applied recursively to select the cluster representative features, following a unique application of silhouette measure for each cluster and a user-defined threshold as the feature selection or elimination criteria. The proposed method is evaluated on a hydraulic test rig, multi sensor readings in two different fashions: (1) Reduce the dimensionality in a multivariate classification problem using various classifiers of different functionalities. (2) Classification of univariate data in a sliding window scenario, where RkSE is used as a window compression method, to reduce the window dimensionality by selecting the best time points in a sliding window. Moreover, the results are validated using 10-fold cross validation technique. As well as, compared to the results when the classification is pulled directly with no feature selection applied. Additionally, a new taxonomy for k-means based feature selection methods is proposed. The experimental results and observations in the two comprehensive experiments demonstrated in this work reveal the capabilities and accuracy of the proposed method.

show abstract

Section: Analysis and Experimental Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Feature Selection Using Recursive k-Means Silhouette Elimination (RkSE): A Two-Scenario Case Study for Fault Classification of High-Dimensional Sensor Data

Mallak¹,

Fathi²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…32 This remains an active field of research. 57 Similar features can also be grouped to achieve dimensionality reduction, and methods such as principal component analysis and independent component analysis are employed to this end. 58 Once features are selected, the task is to correlate these features-individually or in groups-to diagnostic and prognostic outcomes or to the underlying biology.…”

Section: Radiomics: From Feature Extraction To Correlation With Outcomesmentioning

confidence: 99%

Radiomics: from qualitative to quantitative imaging

Rogers

Seetha

Lieverse

et al. 2020

The British Journal of Radiology

225

130

View full text Add to dashboard Cite

Historically, medical imaging has been a qualitative or semi-quantitative modality. It is difficult to quantify what can be seen in an image, and to turn it into valuable predictive outcomes. As a result of advances in both computational hardware and machine learning algorithms, computers are making great strides in obtaining quantitative information from imaging and correlating it with outcomes. Radiomics, in its two forms “handcrafted and deep,” is an emerging field that translates medical images into quantitative data to yield biological information and enable radiologic phenotypic profiling for diagnosis, theragnosis, decision support, and monitoring. Handcrafted radiomics is a multistage process in which features based on shape, pixel intensities, and texture are extracted from radiographs. Within this review, we describe the steps: starting with quantitative imaging data, how it can be extracted, how to correlate it with clinical and biological outcomes, resulting in models that can be used to make predictions, such as survival, or for detection and classification used in diagnostics. The application of deep learning, the second arm of radiomics, and its place in the radiomics workflow is discussed, along with its advantages and disadvantages. To better illustrate the technologies being used, we provide real-world clinical applications of radiomics in oncology, showcasing research on the applications of radiomics, as well as covering its limitations and its future direction.

show abstract

“…The ultimate goal of such methods is to eliminate redundant, noisy, or irrelevant features to alleviate the learning of supervised or unsupervised algorithms. For the overview of the field and survey of the state-of-the-art algorithms for feature selection/extraction, refer to [41]- [44].…”

Section: B the Reduction Of A CVI Ensemblementioning

confidence: 99%

Weighted Cluster Ensemble Based on Partition Relevance Analysis With Reduction Step

Ilc

2020

IEEE Access

View full text Add to dashboard Cite

Over the last decade, the advent of the cluster ensemble framework has enabled more accurate and robust data analysis than traditional single clustering algorithms. The improved clustering of microarray data has had a particularly strong impact in the fields of genomics and medicine. However, when we bring several ensemble members together to form a consensus, low-quality data partitions can seriously compromise the final solution. One way to overcome this problem is the weighted cluster ensemble approach based on Partition Relevance Analysis (PRA), which uses internal cluster validity indices to evaluate and weight the ensemble members before the fusion. Unfortunately, the selection of appropriate validation indices for given data is far from trivial. In this paper, we propose an additional step in PRA that reduces the size of the committee of cluster validation indices. It does so by eliminating redundant and noisy indices using data dimensionality reduction methods. Our extension works in an unsupervised way, minimizing the amount of user intervention and required expert knowledge. We adapted three conventional consensus functions based on the principle of evidence accumulation to work with PRA weights. We demonstrate the advantages of the proposed reduction step of PRA based on extensive experiments with 25 gene expression and 15 non-genetic real-world datasets, where we compared 15 consensus functions.

show abstract

A review of unsupervised feature selection methods

Cited by 473 publications

References 122 publications

Unsupervised Feature Selection Using Recursive k-Means Silhouette Elimination (RkSE): A Two-Scenario Case Study for Fault Classification of High-Dimensional Sensor Data

Unsupervised Feature Selection Using Recursive k-Means Silhouette Elimination (RkSE): A Two-Scenario Case Study for Fault Classification of High-Dimensional Sensor Data

Radiomics: from qualitative to quantitative imaging

Weighted Cluster Ensemble Based on Partition Relevance Analysis With Reduction Step

Contact Info

Product

Resources

About