| 基于局部权重及阈值调整算法的BP网络预测模型研究 |
| |
| 引用本文： | 莫礼平.基于局部权重及阈值调整算法的BP网络预测模型研究[J].甘肃联合大学学报(自然科学版),2007,21(1):49-52. |
| |
| 作者姓名： | 莫礼平 |
| |
| 作者单位： | 吉首大学,数学与计算机科学学院,湖南,吉首,416000 |
| |
| 摘 要： | 通过对基本BP算法的分析,提出了一种基于局部权重及阈值调整的改进BP算法.结合该改进算法,讨论了在Matlab中创建基于BP网络的交通运输需求预测模型并使用该模型进行预测的过程.同时,将基于局部权重及阈值调整的改进BP算法和加动量项的自适应学习率BP算法的模型的预测效果进行了比较,比较结果表明前者的预测效果优于后者.
|
| 关 键 词： | 人工神经网络 BP算法 预测 交通运输 |
| 文章编号： | 1672-691X（2007）01-0049-04 |
| 收稿时间： | 2006-08-16 |
| 修稿时间： | 2006年8月16日 |
Study on Prediction Model of BP Network Based on Partial Weight and Threshold Adjusting Algorithm |
| |
| MO Li-ping.Study on Prediction Model of BP Network Based on Partial Weight and Threshold Adjusting Algorithm[J].Journal of Gansu Lianhe University :Natural Sciences,2007,21(1):49-52. |
| |
| Authors: | MO Li-ping |
| |
| Abstract: | According to the analysis result of basic BP algorithm.a improved algorithm based on partial weight and threshold adjusting is put forward. Combining with this improved algorithm, the process of establishing and using prediction model of transport demand in the MATLAB is discussed. At the same time, the prediction effect of model based on improved BP algorithm and model based on BP algorithm which updates weight and threshold values according to gradient descent momentum and an adaptive learning rate are compared. The resuh shows that prediction effect of the former is better than the later. |
| |
| Keywords: | artificial neutral network BP algorithm prediction transport |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
