In this article, a new metaheuristic optimization algorithm (named as, student psychology based optimization (SPBO)) is proposed. The proposed SPBO algorithm is based on the psychology of the students who are trying to give more effort to improve their performance in the examination up to the level for becoming the best student in the class. Performance of the proposed SPBO is analyzed while applying the algorithm to solve thirteen 50 dimensional benchmark functions as well as fifteen CEC 2015 benchmark problems. Results of the SPBO is compared to the performance of ten other state-of-the-art optimization algorithms such as particle swarm optimization, teaching learning based optimization, cuckoo search algorithm, symbiotic organism search, covariant matrix adaptation with evolution strategy, success-history based adaptive differential evolution, grey wolf optimization, butterfly optimization algorithm, poor and rich optimization algorithm, and barnacles mating optimizer. For fair analysis, performances of all these algorithms are analyzed based on the optimum results obtained as well as based on convergence mobility of the objective function. Pairwise and multiple comparisons are performed to analyze the statistical performance of the proposed method. From this study, it may be established that the proposed SPBO works very well in all the studied test cases and it is able to obtain an optimum solution with faster convergence mobility.

本文提出了一种新的元启发式优化算法（称为基于学生心理学的优化（SPBO））。提出的SPBO算法是基于学生的心理，他们试图付出更多的努力来提高自己的考试成绩，直至成为班上最好的学生。在将算法应用于解决13个50维基准功能以及15个CEC 2015基准问题的同时，对提出的SPBO的性能进行了分析。将SPBO的结果与其他十种最先进的优化算法的性能进行了比较，例如粒子群优化，基于教学的优化，布谷鸟搜索算法，共生生物搜索，具有进化策略的协变矩阵自适应，成功历史基于自适应差分进化 灰太狼优化，蝴蝶优化算法，贫富算法和藤壶交配优化器。为了公平分析，将基于获得的最佳结果以及目标函数的收敛性对所有这些算法的性能进行分析。进行成对和多重比较以分析所提出方法的统计性能。通过这项研究，可以确定所提出的SPBO在所有研究的测试案例中都可以很好地工作，并且能够以更快的收敛性获得最优的解决方案。基于获得的最佳结果以及目标函数的收敛性，对所有这些算法的性能进行了分析。进行成对和多重比较以分析所提出方法的统计性能。通过这项研究，可以确定所提出的SPBO在所有研究的测试案例中都能很好地工作，并且能够以更快的收敛性获得最优的解决方案。基于获得的最佳结果以及目标函数的收敛性，对所有这些算法的性能进行了分析。进行成对和多重比较以分析所提出方法的统计性能。通过这项研究，可以确定所提出的SPBO在所有研究的测试案例中都可以很好地工作，并且能够以更快的收敛性获得最优的解决方案。