Travel Mode Choice Modeling: A Comparison of Bayesian Networks and Neural Networks

Travel Mode Choice Modeling: A Comparison of Bayesian Networks and Neural Networks
复制标题

出行方式选择建模:贝叶斯网络和神经网络的比较

DOI:
10.4028/www.scientific.net/amm.209-211.717
复制
发表时间:
2012-10
期刊:
Applied Mechanics and Materials
影响因子:
--
通讯作者:
Tang Dounan, Yang Min, Zhang Meihui
Tang Dounan, Yang Min, Zhang Meihui
中科院分区:
其他
文献类型:
--
作者:
Tang Dounan, Yang Min, Zhang Meihui

文献摘要

参考文献

相似文献

近年来,贝叶斯网络和神经网络被广泛应用于交通需求预测领域。然而,它们的预测性能很少直接比较。通过使用相同数据集进行的实验测试,本文首次比较了贝叶斯网络模型和神经网络模型在出行方式分析中的应用。研究发现,当网络本身相当复杂时,完全贝叶斯网络模型倾向于过拟合训练集。TAN结构具有更好的泛化性能,其预测精度为75.4%± 0.63%,而BP神经网络模型的预测精度为72.2%± 3.01%。实验和统计测试表明贝叶斯网络的优越性,我们建议使用贝叶斯网络,特别是TAN,而不是神经网络在出行方式选择预测领域。
In recent years, Bayesian networks and neural networks have been widely applied to the travel demand prediction area. However, their prediction performance is rarely directly compared. By experimental tests conducted using the same dataset, a Bayesian network model and a neural network model are compared for the travel mode analysis for the first time in this paper. It is found that the fully Bayesian network model tends to overfit the training set when the network itself is considerable complicated. The TAN structure otherwise has a better generalization performance and can achieve a better and more stable prediction performance, for its prediction accuracy 75.4%±0.63%, compared to the BP neural network model ,which prediction accuracy is 72.2%±3.01%. Experiment and statistical tests demonstrate the superiority of Bayesian networks and we propose using Bayesian networks, especially TAN, instead of neural networks in the travel mode choice prediction field.
DOI: 10.1016/s0925-2312(00)00204-6
发表时间: 2000-06
期刊: Neurocomputing
影响因子: 6
作者:
R. Hecht-Nielsen
通讯作者: R. Hecht-Nielsen
DOI: 10.1109/ijcnn.2000.860810
发表时间: 2000-07
期刊: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
影响因子: --
作者:
A. Dantas;Koshi Yamamoto;M. V. Lamar;Y. Yamashita
通讯作者: A. Dantas;Koshi Yamamoto;M. V. Lamar;Y. Yamashita
学习贝叶斯网络
DOI: 10.4018/978-1-60566-010-3.ch174
发表时间: 2009
期刊: Advanced Materials
影响因子: 29.4
作者:
M. Ramoni;P. Sebastiani
通讯作者: P. Sebastiani
DOI: 10.1038/359463a0
发表时间: 1992
期刊: Nature
影响因子: 64.8
作者:
John A. Hertz
通讯作者: John A. Hertz
DOI: 10.1145/1327942.1327961
发表时间: 2007-08
影响因子: 4
作者:
R. Neapolitan
通讯作者: R. Neapolitan