Sand Cat Swarm Optimization Based on Stochastic Variation With Elite Collaboration
원문 초록
The sand cat swarm optimization (SCSO) is a new heuristic optimization algorithm that simulates the behavior of sand cat groups in the desert using hearing to hunt. To address the shortcomings of low accuracy of SCSO solution, slow convergence in late iterations and easy convergence stagnation, a sand cat swarm optimization based on stochastic variation and elite collaboration (SE-SCSO) is pro- posed. SE-SCSO first introduces a nonlinear periodic adjustment mechanism to balance the exploration and local exploitation ability of the algorithm and accelerate the convergence of the algorithm.Secondly, the pseudo-opposition and pseudo-reflection learning mechanisms are used to speed up the optimization-seeking efficiency of the SCSO algorithm and improve the global convergence capability. Designing elite collab- orative strategies with random variation to enable the algorithm to jump away from the local extrema, further improving the algorithm’s optimization-seeking accuracy and convergence speed. In the simulation experiments, SE-SCSO is compared with Sand Cat Swarm Optimization (SCSO), Sine Cosine Algorithm (CSA), Circle Search Algorithm (SCA), Salp Swarm Algorithm (SSA), Harris Hawks Optimization (HHO), Whale Optimization Algorithm (WOA), and Golden Jackal Optimization (GJO) are tested for compari- son. The experimental results validate the effectiveness of the proposed improvement strategies. Finally, SE-SCSO is applied to three engineering optimization problems. The results show that the improved strategy can effectively improve the performance performance of the algorithm, which gives SE-SCSO the advantages of high convergence accuracy, fast convergence, and the ability to jump out of local optimal solutions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reduced-Order Neural Operators: Learning Lagrangian Dynamics on Highly Sparse Graphs
AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration
Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
Pretrained Language Models as Visual Planners for Human Assistance
RMMDet: Road-Side Multitype and Multigroup Sensor Detection System for Autonomous Driving
Learning to Simulate Daily Activities via Modeling Dynamic Human Needs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.