The Bedbug Meta-heuristic Algorithm to Solve Optimization Problems

Small parasitic Hemipteran insects known as bedbugs (Cimicidae) feed on warm-blooded mammal's blood. The most famous member of this family is the Cimex lectularius or common bedbug. The current paper proposes a novel swarm intelligence optimization algorithm called the Bedbug Meta-Heuristic Algorithm (BMHA). The primary inspiration for the bedbug algorithm comes from the static and dynamic swarming behaviors of bedbugs in nature. The two main stages of optimization algorithms, exploration, and exploitation, are designed by modeling bedbug social interaction to search for food. The proposed algorithm is benchmarked qualitatively and quantitatively using many test functions including CEC2019. The results of evaluating BMHA prove that this algorithm can improve the initial random population for a given optimization problem to converge towards global optimization and provide highly competitive results compared to other well-known optimization algorithms. The results also prove the new algorithm's performance in solving real optimization problems in unknown search spaces. To achieve this, the proposed algorithm has been used to select the features of fake news in a semi-supervised manner, the results of which show the good performance of the proposed algorithm in solving problems.

Automated summary

This paper introduces a novel swarm intelligence optimization algorithm called the Bedbug Meta-Heuristic Algorithm (BMHA), which is inspired by the swarming behaviors of bedbugs. The algorithm models the social interaction of bedbugs to perform exploration and exploitation in search for food. Benchmarking tests show that BMHA can improve the initial random population and achieve global optimization, outperforming other well-known algorithms. The algorithm also demonstrates its performance in solving real optimization problems in unknown search spaces.