An efficient binary chimp optimization algorithm for feature selection in biomedical data classification
Özet
Accurate classification of high-dimensional biomedical data highly depends on the efficient recognition of the data’s main
features which can be used to assist diagnose related diseases. However, due to the existence of a large number of irrelevant
or redundant features in biomedical data, classification approaches struggle to correctly identify patterns in data without a
feature selection algorithm. Feature selection approaches seek to eliminate irrelevant and redundant features to maintain or
enhance classification accuracy. In this paper, a new wrapper feature selection method is proposed based on the chimp
optimization algorithm (ChOA) for biomedical data classification. The ChOA is a newly proposed metaheuristic algorithm
whose capability for solving feature selection problems has not been investigated yet. Two binary variants of the ChoA are
introduced for the feature selection problem. In the first approach, two transfer functions (S-shaped and V-shaped) are used
to convert the continuous version of ChoA to binary. In addition to the transfer function, the crossover operator is utilized
in the second approach to improve the ChOA’s exploratory behavior. To validate the efficiency of the proposed
approaches, five publicly available high-dimensional biomedical datasets, and a few datasets from different domains such
as life, text, and image are employed. The proposed approaches were then compared with six well-known wrapper-based
feature selection methods, including multi-objective genetic algorithm (GA), particle swarm optimization (PSO), Bat
algorithm (BA), ant colony optimization (ACO), firefly algorithm (FA), and flower pollination (FP) algorithm, as well as
two standard filter-based feature selection methods using three different classifiers. The experimental results demonstrate
that the proposed approaches can effectively remove the least significant features and improve classification accuracy. The
suggested wrapper feature selection techniques also outperform the GA, PSO, BA, ACO, FA, FP, and other existing
methods in the terms of the number of selected genes, and classification accuracy in most cases.
Cilt
34Sayı
8Bağlantı
https://hdl.handle.net/11363/5772Koleksiyonlar
Aşağıdaki lisans dosyası bu öğe ile ilişkilidir: