A Survey on Feature Selection Algorithms

Kumar, Amit

doi:10.17762/ijritcc2321-8169.150431

Cited by 5 publications

(2 citation statements)

References 64 publications

(73 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature selection (FS) is one of the essential machine learning pre-processing steps that eliminates redundant and irrelevant data with the goal of improving prediction accuracy and minimizing computing complexity. According to Saxena [5], there are mainly two basic types of FS methods: filter methods and wrapper methods. According to various evaluation factors, filter methods assign a score to each of the features.…”

Section: Some Feature Selection Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

An Exhaustive Wrapper Method for Feature Selection in Large Dimensional Datasets (WFS)

Patel¹

2023

cienc.eng.

View full text Add to dashboard Cite

In this paper, a novel algorithm for randomly selecting a small subset of features from a dataset is presented. Using different combinations of features across a number of trials, the algorithm discovers the best subsets of features. When these subsets of features are obtained, the classification accuracies produced by three classifiers (K-Nearest Neighbor, Support Vector Machines, and Random Forest) are considered to evaluate the performance criterion of the proposed wrapper-based method. Further, to improve the classification accuracy and reduce the cardinality of the selected feature sets, an exhaustive feature selection method (the wrapper method) is used. The proposed algorithm is simulated on eighteen datasets, and the results are compared with those reported using nine comparable algorithms using three classifiers to justify the performance of the proposed algorithm. The average classification accuracies of eighteen datasets achieved are 88.66% in K-NN, 89.88% in SVM, and 89.14% in RF classifier with at most 10 features. The proposed algorithm archives better CA compared to nine comparable algorithms and the results of the experiments prove the proposed algorithm's performance is better in selecting the most effective features compared to other algorithms.

show abstract

Section: Some Feature Selection Techniquesmentioning

confidence: 99%

“…An unsupervised algorithm [4] is one in which the patterns are classified without any previous information (such as class) being provided. Many supervised FS [5] techniques make use of neural networks [6], fuzzy logic [7], and K-NN [8] search algorithms.…”

Section: Introductionmentioning

confidence: 99%