针对传统BP神经网络受初始权阈值影响大且易陷入局部极值，标准天牛须搜索算法局部搜索能力差、寻优精度低等问题，提出一种自适应步长因子的混沌天牛群算法用于优化BP神经网络分类模型。通过增加天牛种群，引入自适应步长更新策略优化天牛须搜索算法的局部搜索能力，使其跳出局部最优，提高算法的计算精度；利用Logisitic混沌映射产生新个体，替换性能较差的个体，增强全局搜索效果。为了改善BP神经网络对非均衡数据集中少数类的分类效果，采用SMOTE算法处理非均衡数据集。将改进的天牛须搜索算法用于优化BP神经网络中的初始权值和阈值，建立IBAS-BPNN（Improved Beetle Antennae Search and Back Propagation Neural Network）分类模型，提高BP神经网络分类模型的准确率。为验证分类模型的性能，将改进的BP神经网络分类模型与其他六种典型的分类算法进行比较，实验结果表明IBAS-BPNN分类模型的平均分类正确率高于其他算法。改进的混沌天牛群算法泛化能力强，鲁棒性好，具有一定的优越性。
Aiming at the problems of traditional BP neural network that are greatly affected by the initial weight threshold and easily fall into local extremes, and the standard beetle antennae search algorithm has poor local search ability and low optimization accuracy. Therefore, an adaptive step factor chaotic beetle swarm algorithm is proposed to optimize the BP neural network classification model. Optimize the local search ability of the beetle antennae search algorithm by increasing the beetle population and introducing an adaptive step size update strategy, so that the algorithm jumps out of the local optimum and improves the calculation accuracy of the algorithm; Logisitic chaotic mapping is used to generate new individuals, and individuals with poor performance are replaced, which enhances the global search effect. In order to improve the classification effect of the BP neural network on the minority classes in the unbalanced data set, the SMOTE algorithm is used to process the unbalanced data set. The improved Beetle Antennae Search and Back Propagation Neural Network (IBAS-BPNN) classification model is established to optimize the initial weight and threshold in the BP neural network to improve the accuracy of the BP neural network classification model. In order to verify the performance of the classification model, the improved BP neural network classification model is compared with other six typical classification algorithms. The experimental results show that the average classification accuracy of the IBAS-BPNN classification model is higher than other algorithms. The improved chaotic beetle swarm algorithm has strong generalization ability, good robustness, and certain advantages.
王丽,陈基漓,谢晓兰,等. 基于混沌天牛群算法优化的神经网络分类模型[J]. 科学技术与工程, 2022, 22(12): 4854-4863.
Wang Li, Chen Jili, Xie Xiaolan, et al. Neural Network Model for Classficiation Based on Chaotic Beetle Swarm Algorithm[J]. Science Technology and Engineering,2022,22(12):4854-4863.