Search

In order to overcome the drawbacks of Archimedes optimization algorithm( AOA), such as weak global search ability, easily trapping into local optimum and prematurely converge, this paper put forward Archimedes optimization algorithm improved by multi-strategy collaborative( MAOA ) . Initially, it used the random Gaussian mutation strategy to increase the diversity of the population in the iterative process and strengthen the global search ability. Then, based on the randomness, ergodicity and diversity of multiple chaotic models, it introduced the local chaotic search strategy to expand the scope range of the chaotic space and enhance the local development capabilities of the algorithm. At the same time, it proposed a nonlinear dynamic density decreasing factor to coordinate the global exploration ability and local development ability of the algorithm. Finally, for the sake of increasing the diversity of the population during the iteration process, this paper adopted the golden sine strategy of the Levy flight guidance mechanism to perturb the population position and improve the ability of the algorithm to jump out of the local optimum. Through simulation experiments on 12 benchmark functions and part of the CEC2014 function set, the results show that the proposed algorithm can overcome the shortcomings of AOA' s weak global exploration ability and easy to fall into local optimality, and improve the accuracy and stability of AOA . In addition, the introduction of mechanical optimization design cases for testing and analysis will further verify the feasibility and applicability of MAOA on practical issues. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of normal SPBO, this paper analyzed the psychological characteristics of students ' learning, and put forward an improved student psychology based optimization algorithm ( HSSPBO) using hybrid strategy . Firstly, it took the inverse value of student ' s test scores as the fitness value of the student, and took the fitness value of the best students in the class as the benchmark, and then divided the students in the class into four categories : the best students, the good students, the ordinary students and the students who tried random improvement. Secondly, it used the dynamic switching probability of sine square and cosine square to balance global exploration and local development, so that the global exploration ability and local exploitation ability of the algorithm were improved effectively. Thirdly, by introducing Cauchy mutation strategy to change the local search step size, it improved effectively the local search ability of the algorithm and enhanced the ability of the algorithm to jump out of the local optimization. Finally, the HSSPBO algorithm used Levy flight strategy to make the individual search step length more random and flexible, which effectively enhanced the individual ' s searching ability, and further improved the optimization speed of the algorithm. Through simulation experiments of 12 benchmark functions and comparison with six optimization algorithms, the results show that HSSPBO ' s global search ability has been significantly improved, and it has faster global convergence speed, better optimization accuracy and stability in function optimization. [ABSTRACT FROM AUTHOR]

Meta-heuristic algorithm-SVM is a typical framework of multi-classification evaluation model, which has important theoretical and practical significance in multi-classification comprehensive decision-making. Therefore, this paper proposed a multi-classification evaluation algorithm of an improved whale optimization algorithm using Lévy flight and elite opposition-based learning SVM（LFEO-BWOA-SVM）. It used Lévy flight strategy instead of spiral trajectory strategy to update position information effectively, and could overcome the deficiency of whale optimization algorithm which was easy to fall into local optimization. It introduced the elite opposition-based learning mechanism to increase population diversity and improved the global optimization ability of whale optimization algorithm. The simulation results show that the classification accuracy of LFEO-BWOA-SVM algorithm is 17.84% and 4.51% higher than that of traditional SVM and BP neural network, the accuracy is 98.73%, and the training time is 9.34% and 84.94% shorter than that of standard WOA-SVM and PSO-SVM, respectively. The experimental results show that the optimization ability and convergence speed of LFEO-BWOA-SVM algorithm are obviously improved, and the accuracy and rapidity are good. [ABSTRACT FROM AUTHOR]