A Hybrid Detective Behavior Algorithm with Particle Swarm Optimization for Continuous Function Optimization

Standard Detective Behavior Algorithm (DBA) may exhibit limited exploitation in later iterations, insufficient use of individual historical information, and unstable local search on complex continuous optimization problems. To address these limitations, this paper proposes a hybrid DBA with particle swarm optimization, denoted as DBA-PSO. The method retains the search-space-centered exploration, Lévy-flight-based local search, direct-attack refinement, and opposition-based learning mechanisms of DBA, while introducing the velocity update and personal-best/global-best guidance mechanisms of particle swarm optimization (PSO). At each iteration, DBA-PSO generates one DBA candidate and one PSO candidate and selects the next position through a fixed probabilistic fusion rule. Experiments on 23 classical benchmark functions and the CEC2017 test suite, together with supplementary CEC2022 and constrained engineering-design tests, show that DBA-PSO improves the mean fitness or stability on several functions compared with DBA or PSO and remains competitive on many test cases. Overall, the results support the usefulness of PSO-based velocity memory and historical-best guidance for improving the later-stage search behavior of DBA, while the mixed CEC2022 ranks, uneven engineering feasibility rates, and fixed fusion probability show that the method does not provide uniform dominance across all problem classes.