With the increasing dimensionality of the data,High-dimensional featureselection(HFS)becomes an increasingly dif-ficult *** is not simple to find the best subset of features due to the breadth of the search space and...
详细信息
With the increasing dimensionality of the data,High-dimensional featureselection(HFS)becomes an increasingly dif-ficult *** is not simple to find the best subset of features due to the breadth of the search space and the intricacy of the interactions between *** of the featureselection(FS)approaches now in use for these problems perform sig-nificantly less well when faced with such intricate situations involving high-dimensional search *** is demonstrated that meta-heuristic algorithms can provide sub-optimal results in an acceptable amount of *** paper presents a new binary Boosted version of the Spider Wasp Optimizer(Bswo)called Binary Boosted swo(BBswo),which combines a number of successful and promising strategies,in order to deal with *** shortcomings of the original Bswo,including early convergence,settling into local optimums,limited exploration and exploitation,and lack of population diversity,were addressed by the proposal of this new variant of *** concept of chaos optimization is introduced in Bswo,where initialization is consistently produced by utilizing the properties of sine chaos mapping.A new convergence parameter was then incorporated into Bswo to achieve a promising balance between exploration and *** exploration mechanisms were then applied in conjunction with several exploitation strategies to effectively enrich the search process of Bswo within the search ***,quantum-based optimization was added to enhance the diversity of the search agents in *** proposed BBswo not only offers the most suitable subset of features located,but it also lessens the data's redundancy *** was evaluated using the k-Nearest Neighbor(k-NN)classifier on 23 HFS problems from the biomedical domain taken from the UCI *** results were compared with those of traditional Bswo and other well-known meta-heuristics-based *** findings indicate that,in comparison to other competing techn
暂无评论