<![CDATA[This paper proposes an optimization algorithm based on pheasant foraging behavior, the Pheasant Foraging Algorithm (PFA). The algorithm simulates the collective cooperation and strategy selection of pheasant groups in the foraging process and is used to solve high-dimensional optimization problems. Based on the analysis of pheasant foraging patterns, an adaptive improvement strategy is proposed to improve local search efficiency while maintaining global search capabilities. Experimental results show that compared with classical optimization methods such as particle swarm optimization (PSO) and genetic algorithm (GA), the PFA algorithm has better performance on many standard optimization problems, stronger global search capabilities and more stable convergence performance. The core innovation of PFA lies in its adaptive improvement strategy, which dynamically adjusts search behavior based on environmental feedback to balance global exploration and local exploitation. Unlike PSO and GA, which often suffer from premature convergence or limited local refinement, PFA introduces role-based cooperation and adaptive flight mechanisms inspired by pheasant group foraging behavior. ]]>
Copyrights © 2025
