A hybrid filter-wrapper feature selection using Fuzzy KNN based on Bonferroni mean for medical datasets classification: A COVID-19 case study

Vommi, Amukta Malyada; Battula, Tirumala Krishna

doi:10.1016/j.eswa.2023.119612

Cited by 38 publications

(13 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These applications can be broken down into three categories: screening, prediction, and diagnosis [7,16]. Combining MAs with FS methods from clinical datasets has resulted in the recent development of diagnostic methods for detecting individuals infected with the COVID-19 [37,100,101]. This paper uses and evaluates the BMCMBO algorithm to predict patients with the COVID-19 using an FS model combined with the KNN classifier.…”

Section: Application Of Bmcmbo Algorithm In Fs For the Covid-19 Diagn...mentioning

confidence: 99%

Binary modified Cat and Mouse based Optimizer for medical feature selection: A COVID-19 case study

Parizi

2024

Preprint

View full text Add to dashboard Cite

Recent technological advances in medical diagnosis have led to the generation of high-dimensional datasets. The presence of redundant and irrelevant features in these datasets can have adverse effects on the performance of machine learning (ML) methods and reduce the accuracy of their results. Therefore, feature selection (FS), i.e., a popular preprocessing method in ML, is used to select the optimal subsets of features to improve the accuracy of ML methods. This performance enhancement is more crucial while addressing high-dimensional medical issues. Since FS is a multiobjective binary optimization problem, it is necessary to develop efficient FS algorithms. Although metaheuristic algorithms (MAs) have been widely used for FS in medicine, they face different challenges in most applications, e.g., a lack of sufficient effectiveness and scalability to select the most effective features in small and large medical datasets. The cat and mouse-based optimizer (CMBO) is a novel MA based on the natural competitive behavior of cats and mice. Despite its acceptable performance in a variety of problems, the CMBO faces various challenges such as limited exploitation abilities, an unbalanced search mechanism, and high fluctuation in solutions to complex problems, e.g., FS. This paper proposes a modified and binary version of the CMBO called the BMCMBO to enhance the performance in selecting effective features from medical datasets. The BMCMBO involves significant modifications to the method of updating the positions of search agents, the method of selecting mice, the effect of the positional information of the most optimal member of the population, and the addition of the adaptive step size. These modifications are meant to improve the exploitation abilities, boost the accuracy of the solutions, and balance the search process when dealing with the FS problem in medical datasets. The performance of the proposed algorithm on 12 real medical datasets was compared with the performance of the most effective MA and CMBO variants. The statistical results demonstrated that BMCMBO was more effective than other evaluated methods. In addition, the BMCMBO algorithm was employed to select features and diagnose COVID-19 in a real case study. The proposed algorithm identified healthy and infected COVID-19 correctly samples with an accuracy of 98.4\%, demonstrating its superiority.

show abstract

Section: Application Of Bmcmbo Algorithm In Fs For the Covid-19 Diagn...mentioning

confidence: 99%

Binary modified Cat and Mouse based Optimizer for medical feature selection: A COVID-19 case study

Parizi

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Genetic feature selection algorithms employ a heuristic to simultaneously optimize both filter and wrapper fitness functions [9] , [18] , [38] . Recent studies have tried to take this approach further by combining several genetic algorithms to search for the optimal feature subset [50] . While genetic algorithms can be appropriate in some cases, the added complexity of the algorithms does not justify the incremental improvements.…”

Section: Literaturementioning

confidence: 99%

Nested ensemble selection: An effective hybrid feature selection method

Kamalov,

Sulieman,

Moussa

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…Consequently, there is a need for feature selection to determine the optimal feature subset. Presently, filter-based and wrapper-based methods dominate the realm of feature selection [46,47]. The filter-based method [48,49] offers advantages such as simplicity and high efficiency, but it does not include the high intercorrelation between feature variables.…”

Section: Introductionmentioning

confidence: 99%

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Lin,

Ren,

et al. 2023

Forests

View full text Add to dashboard Cite

An accurate and efficient estimation of eucalyptus plantation areas is of paramount significance for forestry resource management and ecological environment monitoring. Currently, combining multidimensional optical and SAR images with machine learning has become an important method for eucalyptus plantation classification, but there are still some challenges in feature selection. This study proposes a feature selection method that combines multi-temporal Sentinel-1 and Sentinel-2 data with SLPSO (social learning particle swarm optimization) and RFE (Recursive Feature Elimination), which reduces the impact of information redundancy and improves classification accuracy. Specifically, this paper first fuses multi-temporal Sentinel-1 and Sentinel-2 data, and then carries out feature selection by combining SLPSO and RFE to mitigate the effects of information redundancy. Next, based on features such as the spectrum, red-edge indices, texture characteristics, vegetation indices, and backscatter coefficients, the study employs the Simple Non-Iterative Clustering (SNIC) object-oriented method and three different types of machine-learning models: Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machines (SVM) for the extraction of eucalyptus plantation areas. Each model uses a supervised-learning method, with labeled training data guiding the classification of eucalyptus plantation regions. Lastly, to validate the efficacy of selecting multi-temporal data and the performance of the SLPSO–RFE model in classification, a comparative analysis is undertaken against the classification results derived from single-temporal data and the ReliefF–RFE feature selection scheme. The findings reveal that employing SLPSO–RFE for feature selection significantly elevates the classification precision of eucalyptus plantations across all three classifiers. The overall accuracy rates were noted at 95.48% for SVM, 96% for CART, and 97.97% for RF. When contrasted with classification outcomes from multi-temporal data and ReliefF–RFE, the overall accuracy for the trio of models saw an increase of 10%, 8%, and 8.54%, respectively. The accuracy enhancement was even more pronounced when juxtaposed with results from single-temporal data and ReliefF-RFE, at increments of 15.25%, 13.58%, and 14.54% respectively. The insights from this research carry profound theoretical implications and practical applications, particularly in identifying and extracting eucalyptus plantations leveraging multi-temporal data and feature selection.

show abstract

A hybrid filter-wrapper feature selection using Fuzzy KNN based on Bonferroni mean for medical datasets classification: A COVID-19 case study

Cited by 38 publications

References 48 publications

Binary modified Cat and Mouse based Optimizer for medical feature selection: A COVID-19 case study

Binary modified Cat and Mouse based Optimizer for medical feature selection: A COVID-19 case study

Nested ensemble selection: An effective hybrid feature selection method

Eucalyptus Plantation Area Extraction Based on SLPSO-RFE Feature Selection and Multi-Temporal Sentinel-1/2 Data

Contact Info

Product

Resources

About