基于SCBANet模型的九寨沟景区客流量短期预测  

Short-term Prediction of Passenger Flow in Jiuzhaigou Scenic Area Based on SCBANet Model

作　　者：郭旭萍 刘小芳 姚蕊 GUO Xuping;LIU Xiaofang;YAO Rui(School of Computer Science and Engineering,Sichuan University of Science&Engineering,Yibin 644000,China)

机构地区：[1]四川轻化工大学计算机科学与工程学院,四川宜宾644000

出　　处：《新乡学院学报》2024年第3期32-38,共7页Journal of Xinxiang University

摘　　要：针对景区客流量短期预测时存在的特征提取能力差、预测误差大、难以捕捉非常规变化等问题,提出了一种神经网络模型SCBANet,该模型结合了时空归一化、卷积神经网络、双向长短期记忆网络以及注意力机制。首先利用时空归一化的两个模块分别对客流量数据的高频分量与局部分量进行细化;然后利用卷积神经网络对处理后的数据进行特征提取,接着双向长短期记忆网络利用提取到的特征进行景区客流量的预测,最后使用注意力机制捕捉过去不同时间频次对景区客流量的影响,从而提高预测的精确度并捕捉非常规变化。实验结果表明,与其他算法相比,SCBANet模型预测误差可下降97.63%,对未来一周景区客流量预测的每日相对误差均在4%以下,因此更适用于景区短期客流量的预测。Aiming at the problems of poor feature extraction ability,large prediction error,and difficulty in capturing unconventional changes in the short-term prediction of scenic spots,a neural network model SCBANet is proposed,which combines spatiotemporal normalization,convolutional neural network,two-way long short-term memory network and attention mechanism.Firstly,the two modules of spatiotemporal normalization are used to refine the high-frequency components and local parts of the passenger flow data;secondly,the convolutional neural network is used to extract the features of the processed data;then the two-way long short-term memory network uses the extracted features to predict the tourist flow of scenic spots;and finally the attention mechanism is used to capture the influence of different time frequencies on the passenger flow of scenic spots in the past,so as to improve the accuracy of prediction and capture unconventional changes.The experimental results show that compared with other algorithms,the prediction error of the model proposed in this paper can be reduced by 97.63%,and the daily relative error of the prediction of the passenger flow of scenic spots in the coming week is less than 4%,so it is more suitable for the prediction of short-term passenger flow of scenic spots.

关 键 词：客流量预测 时空归一化 卷积神经网络 双向长短期记忆网络 注意力机制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] F592.7[自动化与计算机技术—控制科学与工程]