Beetle Swarm Optimization Combines Antenna Search with Particle Swarms

Summary

The article explains Beetle Swarm Optimization (BSO), a population-based optimizer that combines Particle Swarm Optimization (PSO) with Beetle Antennae Search (BAS). Each beetle probes objective values on either side of its position, then combines that local directional cue with movement toward its own best result and the swarm’s best result. The article walks through the update equations and a worked two-dimensional example, including the roles of the inertia weight, antenna step size, and mixing coefficient.

It also describes an MQL5 implementation intended for a shared optimization test bench and reports comparison results: BSO scores 43% and ranks near the bottom of the tested algorithms. The author lists many parameters and susceptibility to getting stuck as drawbacks, and identifies no advantages in the reported assessment. These findings are specific to the article’s test setup; it cautions that implementations may differ from canonical algorithms and that its conclusions reflect the experiments conducted.

Key ideas

• BSO combines BAS antenna comparisons with PSO attraction toward personal and swarm best positions.
• Each beetle estimates a local search direction by comparing objective values at two antenna points.
• The mixing coefficient balances swarm movement against the antenna-based increment.
• Inertia and antenna step sizes decay over iterations to shift from broad exploration toward local search.
• The reported benchmark score is 43%, with the method noted as parameter-heavy and prone to getting stuck.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.