.png){kind=icon}
返回
Feature Selection based nature inspired Capuchin Search Algorithm for solving classification problems
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2023.121128.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Identification of the optimal subset of features for Feature Selection (FS) problems is a demanding problem in machine learning and data mining. A trustworthy optimization approach is required to cope with the concerns involved in such a problem. Here, a Binary version of the Capuchin Search Algorithm (CSA), referred to as BCSA, was developed to select the optimal feature combination. Owing to the imbalance of parameters and random nature of BCSA, it may sometimes fall into the trap of an issue called local maxima. To beat this problem, the BCSA could be further improved with the resettlement of its individuals by adopting some methods of repopulating the individuals during foraging. Levy flight was applied to augment the exploitation and exploration abilities of BCSA, a method referred to as LBCSA. A Chaotic strategy is used to reinforce search behavior for both exploration and exploitation potentials of BCSA, which is referred to as CBCSA. Finally, Levy flight and chaotic sequence are integrated with BCSA, referred to as LCBCSA, to increase solution diversity and boost the openings of finding the global optimal solutions. The proposed methods were assessed on twenty-six datasets collected from the UCI repository. The results of these methods were compared with those of other FS methods. Overall results show that the proposed methods render more precise solutions in terms of accuracy rates and fitness scores than other methods.
Keyword:
Feature Selection
Binary Capuchin Search Algorithm
Classification
Transfer function
Optimization
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
Studies in the flexibility of macrocyclic ligands. Crystal and molecular structure of 2,13-dimethy1-3,6,9,12,18-pentaazabicyclo (12.3.1) octadeca-(18),14,16-triene-dichloroion (III) hexafluorophosphate.png)
Polyhedron
PolyhedronIF0
PREAI
分享收藏Fitness of three chemotypes of Fusarium graminearum species complex in major winter wheat-producing areas of ChinaPLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Binary Horse herd optimization algorithm with crossover operators for feature selection基于交叉算子的特征选择二元马群优化算法
PREAI
分享收藏
分享收藏Memory based hybrid crow search algorithm for solving numerical and constrained global optimization problems基于记忆的混合crow搜索算法求解数值和约束全局优化问题
PREAI
分享收藏分享收藏
查看更多内容