BPSO algorithm is a swarm intelligence optimization algorithm, which has the characteristics of good optimization effect, high efficiency and easy to implement. In recent years, it has been used to optimize a variety of machine learning and deep learning models, such as CNN, LSTM, SVM, etc. But it is easy to fall into local optimum for the lack of exploitation ability. It is found that in the article, which is different from previous studies, The reason for the poor performance is an error existing in their velocity update function, which leads to abnormal and chaotic behavior of particles. This not only makes the algorithm difficult to converge, but also often searches the repeated space. So, traditionally, it has to rely on a low w value in the later stage to force these algorithms to converge, but also makes them quickly lose their search ability and prone to getting trapped in local optima. This article proposes a velocity legacy term correction method for all V-shaped BPSOs. Experimentals based on 0/1 knapsack problems show that it has a significant effect on accuracy and efficiency for all of the 4 commonly used V-Shaped BPSOs. Therefore it is an significant breakthrough in the field of swarm intelligence.

翻译：BPSO算法是一种群体智能优化算法，具有优化效果好、效率高、易于实现的特点。近年来，它被用于优化多种机器学习和深度学习模型，如CNN、LSTM、SVM等。但由于其开发能力不足，容易陷入局部最优。本文发现，与以往研究不同，其性能不佳的原因在于速度更新函数中存在一个误差，该误差导致粒子行为异常且混乱。这不仅使算法难以收敛，还经常搜索重复空间。因此，传统上这些算法在后期不得不依赖较低的w值来强制收敛，但这也使其迅速丧失搜索能力，容易陷入局部最优。本文针对所有V型BPSO算法提出了一种速度遗留项修正方法。基于0/1背包问题的实验表明，该方法对4种常用V型BPSO算法的精度和效率均有显著提升。因此，这是群体智能领域的一项重要突破。