Abstract

The circulation of library literature can reflect the utilization of literature, which is of great significance to the prediction. In this study, the Radial Basis Function (RBF) neural network was optimized by Grey Wolf Optimizer (GWO), and the optimization effect of GWO was improved by tent chaotic sequence. The improved GWO-RBF (IGWO-RBF) optimization model was obtained and applied to the prediction of library literature circulation. The experimental results showed that the IGWO-RBF could accurately predict the circulation of literature, with very small prediction error. The RBF prediction curve had the highest fitting degree with the actual curve, followed by the GWO-RBF model and IGWO-RBF model, and both the root-mean-square error (RMSE) and mean absolute percentage error (MAPE) of IGWO were small, indicating good prediction accuracy. This study proves the effectiveness of the RBF optimized model in the prediction of library circulation, and it can be popularized and applied in practice.

中文翻译：

---

基于RBF神经网络优化模型的高校图书馆文献借阅量预测与分析。

摘要

图书馆文献的流通可以反映文献的利用，这对预测具有重要意义。本研究利用灰狼优化器（GWO）对径向基函数（RBF）神经网络进行了优化，并通过帐篷混沌序列提高了神经网络的优化效果。获得了改进的GWO-RBF（IGWO-RBF）优化模型，并将其应用于图书馆文献发行量的预测。实验结果表明，IGWO-RBF可以准确预测文献的发行量，预测误差很小。RBF预测曲线与实际曲线的拟合程度最高，其次是GWO-RBF模型和IGWO-RBF模型，IGWO的均方根误差（RMSE）和平均绝对百分比误差（MAPE）均为小，表示预测精度好。