We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Natural Heuristic Algorithms to Solve Feature Selection Problem.
- Authors
Yu-Cai Wang; Jie-Sheng Wang; Jia-Ning Hou; Yu-Xuan Xing
- Abstract
In most data mining tasks, feature selection is an essential pre-processing stage. Select the most important attributes to reduce the dimension of the data set, thus improving the accuracy of the classification. Natural heuristic algorithms are widely used in encapsulated feature selection. Based on the wrapper feature selection method, 7 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 verify the performance of various algorithms, and the convergence curves and accuracy boxplots of 7 natural heuristic algorithms on 21 data sets are given. The simulation results were evaluated according to the mean and standard deviation of fitness, the number of selected features, and the running time, with the optimal value in bold. By comparing the comprehensive performance indexes, MPA obtained the highest average 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.
- Subjects
HEURISTIC algorithms; MATHEMATICAL optimization; MYXOMYCETES; DATA mining; ALGORITHMS; FEATURE selection
- Publication
Engineering Letters, 2023, Vol 31, Issue 1, p1
- ISSN
1816-093X
- Publication type
Article