基于高斯过程回归的短时交通量不确定性预测
Short-Term Traffic Volume Uncertainty Prediction Based on Gaussian Process Regression
DOI: 10.12677/OJTT.2023.123025, PDF,    科研立项经费支持
作者: 廖 于, 廖梦媛, 刘雅澜, 杨佳麒, 康 杰：重庆交通大学信息科学与工程学院，重庆；刘佳嘉：重庆交通大学交通运输学院，重庆
关键词: 交通量预测；高斯回归；机器学习；贝叶斯后概率公式；Traffic Volume Prediction； Gaussian Regression； Machine Learning； Bayesian Post Probability Formula
摘要: 智能交通预测对解决交通难题具有重要意义。针对现有模型预测不精准的问题，本文提出一种全新的短期交通量预测模型——高斯回归模型(GPR)，这是基于贝叶斯理论和统计学习理论发展起来的机器学习算法。首先对数据进行归一化处理后，将数据划分为训练集和测试集，建立标准高斯回归方程，利用贝叶斯后验概率公式，建立高斯回归预测模型，并采用无效覆盖率(KP)和区间宽度(Width)两个评价指标，将GPR与GARCH、BOOTSTRAP模型做对比，结果显示本模型表现出的性能最优。
Abstract: Intelligent traffic prediction plays an important role in solving traffic problems. To solve the problem of inaccurate prediction of existing models, this paper proposes a new short-term traffic volume prediction model—Gaussian regression model (GPR), which is a machine learning algorithm developed based on Bayesian theory and statistical learning theory. Firstly, the data was normalized and divided into training set and test set, and the standard Gaussian regression equation was established. The Gaussian regression prediction model was established by using Bayesian posterior probability formula. Two evaluation indexes of invalid coverage (KP) and interval Width were used to compare GPR with GARCH and BOOTSTRAP models. The results show that the performance of this model is optimal.
文章引用：廖于, 廖梦媛, 刘雅澜, 刘佳嘉, 杨佳麒, 康杰. 基于高斯过程回归的短时交通量不确定性预测[J]. 交通技术, 2023, 12(3): 220-227. https://doi.org/10.12677/OJTT.2023.123025

参考文献

[1] Lv, Y., Duan, Y., Kang, W., Li, Z. and Wang, F.Y. (2015) Traffic Flow Prediction with Big Data: A Deep Learning Ap-proach. IEEE Transactions on Intelligent Transportation Systems, 16, 865-873.
[2] 焦琴琴. 基于深度学习的路网短时交通流预测[D]: [硕士学位论文]. 西安: 长安大学, 2016.
[3] 张玺君, 余光杰, 崔勇, 尚继洋. 基于聚类算法和图神经网络的短时交通量预测[J/OL]. 吉林大学学报(工学版): 1-9. https://kns.cnki.net/kcms/detail/22.1341.t.20221104.1545.008.html, 2022-11-07.
[4] 傅贵, 韩国强, 逯峰, 等. 基于支持向量机回归的短时交通量预测模型[J]. 华南理工大学学报(自然科学版), 2013, 41(9): 71-76.
[5] 吕磊. 短时交通量预测与线路推荐研究[D]: [硕士学位论文]. 济南: 山东大学, 2016.
[6] 朴春俊, 蔡满军, 吴忠强. 一种新的自回归——滑动平均模型[J]. 信息技术, 2001(8): 1-3.
[7] 谭满春, 冯荦斌, 徐建闽. 基于ARIMA与人工神经网络组合模型的交通流预测[J]. 中国公路学报, 2007, 20(4): 118-121.
[8] 杨明极, 张贵山. 基于栈式自动编码机的语音质量评价方法[J]. 小型微型计算机系统, 2018, 39(10): 2134-2137.
[9] 姜宗辰, 马毅, 江涛, 等. 基于深度置信网络(DBN)的赤潮高光谱遥感提取研究[J]. 海洋技术学报, 2019, 38(2): 1-7.
[10] Han, L. and Huang, Y.S. (2020) Short-Term Traffic Flow Prediction of Road Network Based on Deep Learning. IET Intelligent Transport Systems, 14, 495-503. [Google Scholar] [CrossRef] 
[11] Li, J., Guo, F., Sivakumar, A., Dong, Y.J. and Krishnan, R. (2021) Transferability Improvement in Short-Term Traffic Prediction Using Stacked LSTM Network. Transportation Research Part C: Emerging Technologies, 124, Article ID: 102977. [Google Scholar] [CrossRef] 
[12] Wang, Q.M., Fan, A.W. and Shi, H.S. (2017) Network Traffic Prediction Based on Improved Support Vector Machine. International Journal of System Assurance Engineering and Management, 8, 1976-1980. [Google Scholar] [CrossRef] 
[13] Wu, C.H., Wei, C.C., Su, D.C., Chang, M.H. and Ho, J.M. (2003) Travel Time Prediction with Support Vector Regression. Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems, Shanghai, 12-15 October 2003, 1438-1442.
[14] Zheng, Z., Chen, W.H., Wu, X.M., Chen, P.C.Y. and Liu, J.M. (2017) LSTM Network: A Deep Learning Approach for Short-Term Traffic Forecast. IET Intelligent Transport Systems, 11, 68-75. [Google Scholar] [CrossRef] 
[15] Guo, Z.Q., Zhao, X., Chen, Y.X., Wu, W. and Yang, J. (2019) Short-Term Passenger Flow Forecast of Urban Rail Transit Based on GPR and KRR. IET Intelligent Transport Systems, 13, 1374-1382. [Google Scholar] [CrossRef] 
[16] Zhou, B., Ma, X.J., Luo, Y.H. and Yang, D.S. (2019) Wind Power Prediction Based on LSTM Networks and Nonparametric Kernel Density Estimation. IEEE Access, 7, 165279-165292. [Google Scholar] [CrossRef] 
[17] 宗文婷, 卫志农, 孙国强, 等. 基于改进高斯过程回归模型的短期负荷区间预测[J]. 电力系统及其自动化学报, 2017, 29(8): 22-28.
[18] 黄亚, 易灵, 肖伟华, 等. 基于高斯过程回归模型的径流短期预测研究[J]. 水力发电, 2020, 46(12): 9-12.
[19] 彭虹桥, 顾洁, 胡玉, 等. 基于混沌粒子群——高斯过程回归的饱和负荷概率预测模型[J]. 电力系统自动化, 2017, 41(21): 25-32, 155.
[20] 甘迪, 柯德平, 孙元章, 等. 基于集合经验模式分解和遗传——高斯过程回归的短期风速概率预测[J]. 电工技术学报, 2015, 30(11): 138-147.
[21] Alamaniotis, M., Chatzidakis, S. and Tsoukalas, L.H. (2014) Monthly Load Forecasting Using Kernel Based Gaussian Process Regression. MedPower 2014, Athens, 2-5 November 2014, 1-8. [Google Scholar] [CrossRef] 
[22] Yan, W., Qiu, H. and Xue, Y. (2009) Gaussian Process for Long-Term Time-Series Forecasting. 2009 International Joint Conference on Neural Networks, Atlanta, 14-19 June 2009, 3420-3427. [Google Scholar] [CrossRef] 
[23] Rasmussen, C.E. and Williams, C.K.I. (2006) Gaussian Processes for Machine Learning. MIT Press, Massachusetts. [Google Scholar] [CrossRef] 
[24] 李振刚. 基于高斯过程回归的网络流量预测模型[J]. 计算机应用, 2014, 34(5): 1251-1254.
[25] 闫晓楠. 基于改进BOOTSTRAP方法的短时交通流不确定性预测[D]: [硕士学位论文]. 南京: 东南大学, 2020.

为你推荐