A discrete bacterial algorithm for feature selection in classification of microarray gene expression cancer data

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

86 Scopus Citations
View graph of relations



Original languageEnglish
Pages (from-to)8-19
Number of pages12
Journal / PublicationKnowledge-Based Systems
Online published12 Apr 2017
Publication statusPublished - 15 Jun 2017
Externally publishedYes


When mining in high dimensional data, the curse of dimensionality is one of the major difficulty to overcome. In this paper, a weighted feature selection strategy is developed and embedded in bacterial based algorithms to reduce the feature dimension in classification. The proposed weighted feature selection strategy distinguishes the features by their classification performances as well as the occurrence frequency in population according to the two matrices. The objectives of minimizing the number of features, maximizing the performance, and minimizing the computational cost are all considered. Regarding the drawback of bacterial based algorithms, Bacterial Colony Optimization based feature selection algorithm is proposed to decrease the computational complexity as well as improve the search ability even in discrete optimization problems. To test the effectiveness of the proposed feature selection method, four bacterial based methods with the weighted strategy embedded have been compared with four classical feature selection methods and three well-known population based algorithms using 15 cancer micro-array datasets with different numbers of features and classes. The results show that the weighted feature selection strategies embedded have improved the feature selection capability of bacterial algorithms. The new proposed mechanisms embedded in Bacterial Colony Optimization method can overcome the limitation of the traditional bacterial based algorithms using premature termination to decrease the computational time, and provide comparable or in most cases better solutions than other feature selection methods considered in the comparison.

Research Area(s)

  • Feature selection, Bacterial Colony Optimization, Bacterial Foraging Optimization, Cancer classification, FEATURE SUBSET, OPTIMIZATION, INFORMATION, REDUNDANCY, FRAMEWORK, RELEVANCE