Improved Binary Symbiotic Organism Search Algorithm With Transfer Functions for Feature Selection

Abstract

Symbiotic Organism Search (SOS) algorithm is highly praised by researchers for its excellent convergence performance, global optimization ability and simplicity in solving various continuous practical problems. However, in the real world, there are many binary problems, which can only take values of 0 and 1, that still need to be solved. Since the original SOS algorithm cannot directly solve the binary problem, the original ASOS Binary SOS (BSOS) algorithm has the disadvantage of premature convergence. In order to improve the limitations of the ASBSOS algorithm, we propose an Improved BSOS (IBSOS) algorithm. As we all know, the transfer function is very important in the binarization of continuous optimization algorithms. Therefore, we used 9 transfer functions in the IBSOS algorithm to binarize the continuous SOS algorithm and analyzed the impact of each transfer function on the performance of the BSOS algorithm. Moreover, we use the same three biological symbiosis strategies as the continuous SOS algorithm in our proposed IBSOS algorithm to binarize the SOS algorithm to improve The diversity of the algorithm execution process and the ability to balance algorithm exploration and development. In order to verify the performance of IBSOS using different transfer functions, we use 13 benchmark functions to show the global optimization capability and convergence speed of the BSOS algorithm. Finally, we apply the algorithm to feature selection in the ten data sets of UCI. The experimental results with low classification error and few features further verify the excellent performance of the IBSOS algorithm.

Keywords

• Binary symbiotic organism search
• transfer function
• swarm intelligence
• feature selection