A novel dissimilarity metric based on feature‐to‐feature scatter frequencies for clustering‐based feature selection in biomedical data

Sheikhi, Ghazaal; Altınçay, Hakan

doi:10.1111/coin.12470

Cited by 3 publications

(1 citation statement)

References 57 publications

(90 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to reduce dimensionality, filter feature selection techniques have been extensively employed in biological data analysis. Sheikhi has proposed [20], a brand-new dissimilarity metric based on feature-to-feature (F2F) scatter frequencies is proposed for clustering-based filter feature selection. The suggested metric is calculated using sample-level ranks and a list of the characteristics that give each sample a similar rank.…”

Section: Literature Reviewmentioning

confidence: 99%

Clustering of Microarray Data Using Endist

2023

Preprint

View full text Add to dashboard Cite

Microarray gene expressions shed light on genetic indicators that help distinguish between healthy and malignant cells. An unsupervised learning technique called clustering divides the data into groups depending on how similar they are. Clustering of microarray data helps us to identify the expression profiles of the genes. This identifies genes with similar functions like upregulated genes and downregulated genes. The distance measure helps precisely ascertain how dissimilar two items are to one another which is a fundamental idea for these analytical jobs and applications. This research proposes a novel distance measure for microarray datasets. For clustering tasks, the benchmark algorithm k-medoids is employed. ENDIST findings are compared with those of other widely used distance measures, including Manhattan and the Euclidean distance measure. The utilized data are central nervous system dataset, lung cancer dataset, brain cancer dataset, endometrial cancer dataset and the dataset for prostate cancer. The preprocessing technique involves transformation of raw data into logarithm values followed by both binary and ternary discretization. The quality of the clusters by using ENDIST were validated through the Dunn index.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Clustering of Microarray Data Using Endist

2023

Preprint

View full text Add to dashboard Cite

show abstract

Improved gene expression diagnosis via cascade entropy-fisher score and ensemble classifiers

Bolourchi

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Majority voting based on different feature ranking techniques from gene expression

Blourchi¹,

Ghasemzadeh²

2023

IFS

View full text Add to dashboard Cite

In bioinformatics studies, many modeling tasks are characterized by high dimensionality, leading to the widespread use of feature selection techniques to reduce dimensionality. There are a multitude of feature selection techniques that have been proposed in the literature, each relying on a single measurement method to select candidate features. This has an impact on the classification performance. To address this issue, we propose a majority voting method that uses five different feature ranking techniques: entropy score, Pearson’s correlation coefficient, Spearman correlation coefficient, Kendall correlation coefficient, and t-test. By using a majority voting approach, only the features that appear in all five ranking methods are selected. This selection process has three key advantages over traditional techniques. Firstly, it is independent of any particular feature ranking method. Secondly, the feature space dimension is significantly reduced compared to other ranking methods. Finally, the performance is improved as the most discriminatory and informative features are selected via the majority voting process. The performance of the proposed method was evaluated using an SVM, and the results were assessed using accuracy, sensitivity, specificity, and AUC on various biomedical datasets. The results demonstrate the superior effectiveness of the proposed method compared to state-of-the-art methods in the literature.

show abstract

A novel dissimilarity metric based on feature‐to‐feature scatter frequencies for clustering‐based feature selection in biomedical data

Cited by 3 publications

References 57 publications

Clustering of Microarray Data Using Endist

Clustering of Microarray Data Using Endist

Improved gene expression diagnosis via cascade entropy-fisher score and ensemble classifiers

Majority voting based on different feature ranking techniques from gene expression

Contact Info

Product

Resources

About