Search

In the majority of data mining tasks, feature selection serves as an essential pre-processing step. The most important attributes are selected to lower the dimensionality reduction of data set and enhance the precision of classification. Natural heuristic algorithms are extensively employed in the realm of encapsulated feature selection. Based on the wrapper feature selection method, seven natural heuristic algorithms are used to solve feature selection problems and perform performance comparison, which include Slime Mold Algorithm (SMA), Whale Optimization Algorithm (WOA), Harris Hawks Optimization Algorithm (HHO), Marine Predator Algorithm (MPA), Butterfly Optimization Algorithm (BOA), Cuckoo Search (CS) and Firefly Algorithm (FA). At the same time, performance tests are carried out on 21 standard UCI data sets to verily the functionality of various algorithms, and the convergence curves and accuracy boxplots of 7 natural heuristic algorithms on 21 data sets are given. The simulation outcomes were assessed utilizing the mean and standard deviation of fitness, as well as the number of chosen features, and the running time, with the optimal value in bold. By comparing the comprehensive performance indexes, MPA obtained the maximum mean fitness value in most data sets (16 data sets), followed by FA (6 data sets). SMA obtained the best performance and finds the minimum eigenvalues (20 data sets) in multiple data sets and has an advantage in computing time. [ABSTRACT FROM AUTHOR]

Coati Optimization Algorithm (COA) is a novel heuristic algorithm that simulates the intricate behavioral repertoire of coatis manifestations during their pursuit of iguanas as well as their evasive tactics against predators. Aiming to elevate the convergence characteristics regarding speed and precision of the original algorithmic process, and addressing the issue of susceptibility to local optima, an enhanced Coati Optimization Algorithm is suggested based on Cauchy mutation and chaotic maps. Firstly, the Cauchy mutation is embedded in the process of coatis hunting for iguanas. Subsequently, each of ten chaotic maps was incorporated into the probing phase of the COA, generating ten unique enhanced versions. This augments the algorithm's precision in optimization, bolsters the equilibrium between exploration and exploitation and enhances its itinerancy and non-redundancy. The enhanced optimization algorithm exhibiting the aggregated optimal performance is selected from ten types of different enhanced COA and used for subsequent comparisons with other algorithms for function optimization and engineering optimization. Thirty benchmark functions from the CEC-BC-2022 datasets were incorporated for evaluation on performance metrics of the improved COA with Cauchy mutation and ten types of chaotic maps, and then the performance of the Chebyshev map enhanced COA and other six swarm intelligent algorithms are compared for optimization purposes. Finally, optimization was performed on four distinct engineering design problems. The outcomes of the simulation experiment evidence that the advanced Cauchy mutation chaotic COA yields satisfactory outcomes in addressing both function optimization and engineering optimization. The algorithm exhibits superiority in balancing exploration and exploitation during the iterative procedure of optimization, thereby enhancing convergence precision. [ABSTRACT FROM AUTHOR]