Probabilistic Regularized Extreme Learning for Robust Modeling of Traffic Flow Forecasting
Probabilistic Regularized Extreme Learning for Robust Modeling of Traffic Flow Forecasting
复制标题
用于交通流预测鲁棒建模的概率正则极限学习
DOI：
10.1109/tnnls.2020.3027822
复制
发表时间：
2020-10
影响因子：
10.4
通讯作者：
Li Zechao
中科院分区：
文献类型：
--
作者：
Lou Jungang;Jiang Yunliang;Shen Qing;Wang Ruiqin;Li Zechao
自适应神经模糊推理系统（ANFIS）是一种结构化的多输出学习机，已成功地应用于无噪声和无异常值的学习问题。然而，它并不适用于有噪声或异常值的学习问题。由于复杂交通状况的噪声或异常值的影响，对交通流量进行高精度实时预测是非常困难的。本文提出了一种新的概率学习系统——结合ANFIS （probabilistic R-ELANFIS）的概率正则化极值学习机来捕捉交通流数据之间的相关性，从而提高交通流预测的准确性。新的学习系统采用了一个奇妙的目标函数，使模型偏差的均值和方差都最小化。基于现实交通流数据的实验结果表明，与一些基于核函数的方法、神经网络方法和传统的ANFIS学习系统相比，本文提出的概率R-ELANFIS在预测能力和泛化能力方面具有竞争力。
The adaptive neurofuzzy inference system (ANFIS) is a structured multioutput learning machine that has been successfully adopted in learning problems without noise or outliers. However, it does not work well for learning problems with noise or outliers. High-accuracy real-time forecasting of traffic flow is extremely difficult due to the effect of noise or outliers from complex traffic conditions. In this study, a novel probabilistic learning system, probabilistic regularized extreme learning machine combined with ANFIS (probabilistic R-ELANFIS), is proposed to capture the correlations among traffic flow data and, thereby, improve the accuracy of traffic flow forecasting. The new learning system adopts a fantastic objective function that minimizes both the mean and the variance of the model bias. The results from an experiment based on real-world traffic flow data showed that, compared with some kernel-based approaches, neural network approaches, and conventional ANFIS learning systems, the proposed probabilistic R-ELANFIS achieves competitive performance in terms of forecasting ability and generalizability.
登录
查看更多内容
基于鲁棒最优控制核学习方法的乘性噪声非线性随机时空系统在线辨识
DOI：
10.1109/tnnls.2018.2843883
发表时间：
2019
影响因子：
10.4
作者：
Ning Hanwen;Qing Guangyan;Tian Tianhai;Jing Xingjian
通讯作者：
Jing Xingjian
DOI：
10.1109/cica.2014.7013226
发表时间：
2014-12
期刊：
2014 IEEE Symposium on Computational Intelligence in Control and Automation (CICA)
影响因子：
--
作者：
G. N. Pillai;Jagtap Pushpak;M. Germin Nisha
通讯作者：
G. N. Pillai;Jagtap Pushpak;M. Germin Nisha
用于噪声数据鲁棒建模的概率正则极限学习机
影响因子：
11.8
作者：
Lu Xinjiang;Ming Li;Liu Wenbo;Li Han-Xiong
通讯作者：
Li Han-Xiong
SVR交通流预测模型中的混合进化算法
影响因子：
4
作者：
Hong, Wei-Chiang;Dong, Yucheng;Wei, Shih Yung
通讯作者：
Wei, Shih Yung
DOI：
10.1109/tits.2013.2267735
发表时间：
2013-12-01
影响因子：
8.5
作者：
Jeong, Young-Seon;Byon, Young-Ji;Easa, Said M.
通讯作者：
Easa, Said M.