A self-adaptive quantum equilibrium optimizer with artificial bee colony for feature selection.

Feature selection (FS) is a popular data pre-processing technique in machine learning to extract the optimal features to maintain or increase the classification accuracy of the dataset, which is a combinatorial optimization problem, requiring a powerful optimizer to obtain the optimum subset. The equilibrium optimizer (EO) is a recent physical-based metaheuristic algorithm with good performance for various optimization problems, but it may encounter premature or the local convergence in feature selection. This work presents a self-adaptive quantum EO with artificial bee colony for feature selection, named SQEOABC. In the proposed algorithm, the quantum theory and the self-adaptive mechanism are employed into the updating rule of EO to enhance convergence, and the updating mechanism from the artificial bee colony is also incorporated into EO to achieve appropriate FS solutions. In the experiments, 25 benchmark datasets from the UCI repository are investigated to verify SQEOABC, which is compared with several state-of-the-art metaheuristic algorithms and the variants of EO. The statistical results of fitness values and accuracy demonstrate that SQEOABC has better performance than the compared algorithms and the variants of EO. Finally, a real-world FS problem from COVID-19 illustrates the effectiveness and superiority of SQEOABC.

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

Several feature selection methods have been developed to extract the optimal features from a dataset in medical datasets classification. Creating an efficient technique has become a challenge because of the high dimensions, noise, and redundant information. In this paper, we propose a hybrid filter-wrapper approach for feature selection. An ensemble of filter methods, ReliefF and Fuzzy Entropy (RFE) is developed, and the union of top-n features from each method are considered. The Equilibrium Optimizer (EO) technique is combined with Opposition Based Learning (OBL), Cauchy Mutation operator and a novel search strategy to enhance its capabilities. The OBL strategy improves the diversity of the population in the search space. The Cauchy Mutation operator enhances its ability to evade the local optima during the search, and the novel search strategy improves the exploration capability of the algorithm. This enhanced form of EO is integrated with eight time-varying S and V-shaped transfer functions to convert the solutions into binary form, Binary Enhanced Equilibrium Optimizer (BEE). The features from the ensemble are given as input to the Binary Enhanced Equilibrium Optimizer to extract the essential features. Fuzzy KNN based on Bonferroni mean is used as the learning algorithm. Twenty-two benchmark datasets and four microarray datasets are used to test the algorithm's efficiency. This method is also applied to a COVID-19 case study. The results demonstrate the superiority of the proposed approach, RFE-BEE, among other methods in terms of fitness values, accuracy, precision, sensitivity, and F-measure, among several other state-of-the-art algorithms. RFE-BEE can be applied to various biomedical, computer vision and engineering applications such as electromyography pattern recognition, COVID-19 diagnosis, face recognition and fault diagnosis.

An efficient multi-thresholding based COVID-19 CT images segmentation approach using an improved equilibrium optimizer

Optimization is the process of searching for the optimal (best-so-far) solution among a wide range of solutions. Besides, in the last two decades, a family of algorithms known as metaheuristic algorithms (MHs) has been widely used. MHs have attracted researchers’ interest due to their efficiency, easy implementation, and understanding. The equilibrium optimizer (EO) is a recent MH that has been used to tackle several real world problems. Despite the robustness of the EO algorithm, it suffers of the unbalance between the exploration and exploitation phases, this situation causes that the search process be trapped in local optimal values. In this study, an improved version of the EO that combines the standard operators with the dimension learning hunting (DLH) is introduced. The proposed method called I-EO is tested over the CEC’2020 benchmark functions. Quantitative and qualitative results confirmed the robustness and superiority of the proposed algorithm compared to a set of well-known optimization methods. Besides, I-EO is proposed to tackle a real-world application;the multi-level thresholding segmentation for a set of CT images of COVID-19 by maximizing the fuzzy entropy. The segmentation results show the excellent performance in all experiments and confirmed that the proposed I-EO could be an efficient tool for image segmentation. The different elements of the CT are properly segmented by the I-EO based approach. Moreover, the statistical analysis, quality metrics, comparisons and non-parametric tests validates the performance of the I-EO to segment CT images of COVID-19. © 2021 Elsevier Ltd