Glee: A granularity filter for feature selection

Ba, Jing; Wang, Pingxin; Yang, Xibei; Yu, Hualong; Yu, Dong‐Jun

doi:10.1016/j.engappai.2023.106080

Cited by 13 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ba et al [23] present Glee, a novel Granular Computing (GrC) based framework for efficient and effective feature selection. Glee calculates the granularity value for each feature, reorders them accordingly, and adds features to the selection pool one by one until a termination condition is met.…”

Section: Related Workmentioning

confidence: 99%

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

Bouke

Abdullah

Frnda³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Feature interaction is a vital aspect of Machine Learning (ML) algorithms, and gaining a deep understanding of these interactions can significantly enhance model performance. This paper introduces the BukaGini algorithm, an innovative and robust approach for feature interaction analysis that capitalizes on the Gini impurity index. By exploiting the unique properties of the BukaGini index, our proposed algorithm effectively captures both linear and nonlinear feature interactions, providing a richer and more comprehensive representation of the underlying data. We thoroughly evaluate the BukaGini algorithm against traditional Gini index-based methods on various real-world datasets. These datasets include the High School Students' Performance (HSSP) dataset, which examines factors affecting student performance; Cancer Data, which focuses on identifying cancer types based on gene expression; Spambase, which targets spam email classification; and the UNSW-NB15 dataset, which addresses network intrusion detection. Our experimental results demonstrate that the BukaGini algorithm consistently outperforms traditional Gini index-based methods in terms of accuracy. Across the tested datasets, the BukaGini algorithm achieves improvements ranging from 0.32% to 2.50%, underscoring its effectiveness in handling diverse data types and problem domains. This performance gain highlights the potential of the BukaGini algorithm as a valuable tool for feature interaction analysis in various ML applications.INDEX TERMS BukaGini algorithm, Gini index, ensemble learning, feature interaction analysis, data mining.

show abstract

Section: Related Workmentioning

confidence: 99%

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

Bouke

Abdullah

Frnda³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Generally speaking, we need to evaluate the significance of attributes in AT, eliminate low-quality attributes from the reduct pool, and select qualified attributes. Based on the greedy searching for attribute reduction [44][45][46], Definition 15 provides a significance attribute about our proposed quality-to-entropy ratio.…”

Section: Theorem 1 For a Given Decision System Ds A Radiusmentioning

confidence: 99%

Forward Greedy Searching to κ-Reduct Based on Granular Ball

et al. 2023

View full text Add to dashboard Cite

As a key part of data preprocessing, namely attribute reduction, is effectively applied in the rough set field. The purpose of attribute reduction is to prevent too many attributes from affecting classifier operations and reduce the dimensionality of data space. Presently, in order to further improve the simplification performance of attribute reduction, numerous researchers have proposed a variety of methods. However, given the current findings, the challenges are: to reasonably compress the search space of candidate attributes; to fulfill multi-perspective evaluation; and to actualize attribute reduction based on guidance. In view of this, forward greedy searching to κ-reduct based on granular ball is proposed, which has the following advantages: (1) forming symmetrical granular balls to actualize the grouping of the universe; (2) continuously merging small universes to provide guidance for subsequent calculations; and (3) combining supervised and unsupervised perspectives to enrich the viewpoint of attribute evaluation and better improve the capability of attribute reduction. Finally, based on three classifiers, 16 UCI datasets are used to compare our proposed method with six advanced algorithms about attribute reduction and an algorithm without applying any attribute reduction algorithms. The experimental results indicate that our method can not only ensure the result of reduction has considerable performance in the classification test, but also improve the stability of attribute reduction to a certain degree.

show abstract

“…The main target of feature selection is obtaining a representative feature combination from the original feature set to maximize the OA [41], which is an important evaluation criterion, but how to decrease the number of selected features is also a crucial target in feature selection. In this paper, the objective function is used to evaluate the feature combination searched by agents [42]; it is described in Equation (7).…”

Section: The Objective Functionmentioning

confidence: 99%

“…Feature extraction involves the linear or nonlinear transformation of the original high-dimensional features, such as combining different features into a new feature set [6], where the features lose their original physical meaning. Feature selection involves selecting the most representative feature combination from the dataset; it detects representative features and decreases redundant information or noise from data, which improves classification accuracy and enhances comprehensibility [7]. Due to the difficulty in interpreting selected features from feature extraction, feature selection is widely used in the processing of HSI datasets.…”

Section: Introductionmentioning

confidence: 99%

Discarding–Recovering and Co-Evolution Mechanisms Based Evolutionary Algorithm for Hyperspectral Feature Selection

Liao,

Li,

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the improvement of spectral resolution, the redundant information in the hyperspectral imaging (HSI) datasets brings computational, analytical, and storage complexities. Feature selection is a combinatorial optimization problem, which selects a subset of feasible features to reduce the dimensionality of data and decrease the noise information. In recent years, the evolutionary algorithm (EA) has been widely used in feature selection, but the diversity of agents is lacking in the population, which leads to premature convergence. In this paper, a feature selection method based on discarding–recovering and co-evolution mechanisms is proposed with the aim of obtaining an effective feature combination in HSI datasets. The feature discarding mechanism is introduced to remove redundant information by roughly filtering the feature space. To further enhance the agents’ diversity, the reliable information interaction is also designed into the co-evolution mechanism, and if detects the event of stagnation, a subset of discarded features will be recovered using adaptive weights. Experimental results demonstrate that the proposed method performs well on three public datasets, achieving an overall accuracy of 92.07%, 92.36%, and 98.01%, respectively, and obtaining the number of selected features between 15% and 25% of the total.

show abstract

Glee: A granularity filter for feature selection

Cited by 13 publications

References 54 publications

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

BukaGini: A Stability-Aware Gini Index Feature Selection Algorithm for Robust Model Performance

Forward Greedy Searching to κ-Reduct Based on Granular Ball

Discarding–Recovering and Co-Evolution Mechanisms Based Evolutionary Algorithm for Hyperspectral Feature Selection

Contact Info

Product

Resources

About