|本期目录/Table of Contents|

[1]王颖林,赖芨宇,郭丰敏.建设需求量预测分析中的人工神经网络和多元回归方法[J].武汉工程大学学报,2013,(11):77-80,86.[doi:103969/jissn16742869201311016]
　WANG Ying\|lin,LAI Ji\|yu,GUO Feng\|min.Construction demand forecasting by Artificial Neural Networks and Multiple Regression[J].Journal of Wuhan Institute of Technology,2013,(11):77-80,86.[doi:103969/jissn16742869201311016]
点击复制

建设需求量预测分析中的人工神经网络和多元回归方法(/HTML)
分享到：

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
期数:
2013年11
页码:
77-80,86
栏目:
资源与土木工程
出版日期:
2013-11-30

文章信息/Info

Title:
Construction demand forecasting by Artificial Neural Networks and Multiple Regression
文章编号:
16742869(2013)11007704
作者:
王颖林; 赖芨宇; 郭丰敏
福建农林大学交通与土木工程学院，福建 福州 350001
Author(s):
WANG Ying\|lin;  LAI Ji\|yu;  GUO Feng\|min
Fujian Agriculture and Forestry University, College of Transportation and Civil Engineering, Fuzhou 350002, China
关键词:
建设需求; 人工神经网络; 回归分析; 预测
Keywords:
construction demand;  artificial neural networks;  regression;  forecasting
分类号:
F281
DOI:
103969/jissn16742869201311016
文献标志码:
A
摘要:
利用人工神经网络（ANN）和多元回归（MR）预测方法分别基于中国统计年鉴和香港房屋署的相关数据对中国内地和香港地区的建设需求量进行预测，并对两种预测手段得到的预测结果的可信度和离散程度进行对比分析.基于ANN和MR两种预测手段的不同特性，从预测结果中可以看出，就香港地区的预测情况而言， ANN方法产生的结果比回归模型更加精确；从内地的预测结果来看， ANN和MR的预测精度几乎一致.对于存在较大波动性的数据而言，ANN模型建立的非线性关系可以更精确地描述预测结果，反之，两种预测模型的应用均可得出良好结果.同时，经预测得知，两地的建筑需求量都存在上升趋势，有关部门应采取相应措施提前做好规划工作.
Abstract:
Based on the relevant data from China Statistical Yearbook and the Hong Kong Housing Department, Artificial Neural Networks (ANN) and Multiple Regression (MR) were adopted to forecast construction requirement for China mainland and Hong Kong, the credibility and the degree of dispersion of forecasting results were analyzed. According to different characteristics of ANN and MR, for Hong Kong case, ANN method generates a more accurate result than regression model, but for the mainland, both ANN and MR perform well. The data which has great volatility is described more accuracy by non\|linear relationship model which is generated by ANN method. Otherwise, the forecasting results with same credibility are generated by both two methods. Meanwhile, according to forecasting results, building demands have a raising tendency, as a result, the relevant departments should take appropriate measures to plan the work ahead of time.

参考文献/References:

［1］赵利,鹿吉祥,顾洪滨.建筑垃圾综合治理产业化运作与对策研究［J］．建筑经济，2011（5）：16\|20．ZHAO Li, LU Ji\|xiang,GU Hong\|bin.Comprehensive management of construction waste Industrial Operation and Countermeasures［J］．Construction Economics，2011（5）：16\|20．(in Chinese)［2］赵黎明，沈艳丰，宫晓玲.建筑市场需求预测中的神经网络方法［J］.系统工程理论与实践，2000（10）：121\|125. ZHAO Li\|ming, SHEN Yan\|feng, GONG Xiao\|ling.Neural Networks Using in Construction Market Demand Forecasting ［J］.Systems Engineering Theory and Practice,2000（10）：121\|125. (in Chinese)［3］Khanna T. Foundation of Neural Networks ［M］. Boston:Addison\|Wesley,1990.［4］欧阳红祥，李欣，张信娟.人工神经网络在建筑材料价格预测中的应用［J］.武汉理工大学学报:信息与管理工程版, 2013(1):115\|118.OUYANG Hong\|xiang, LI Xin,ZHANG Xin\|juan.Construction Materials Price Prediction by using Artificial Neural Networks［J］.Wuhan University of Technology: Information & Management Engineering，2013(1):115\|118.(in Chinese)［5］李丽，张海涛.基于BP人工神经网络的小城镇生态环境质量评价模型［J］．应用生态学报,2008(12)：2693\|2698．LI Li,ZHANG Hai\|tao.Small Towns Ecological Environment Quality Evaluation Model based on BP Artificial Neural Network［J］．Journal of Applied Ecology,2008(12)：2693\|2698．(in Chinese)［6］喻伟，李百战，杨明宇，等.基于人工神经网络的建筑多目标预测模型［J］．中南大学学报：自然科学版，2012（12）：4949\|4955．YU Wei,LI Bai\|zhan,YANG Ming\|yu,et al.Architecture multi\|target prediction mo del based on artificial neural network［J］．Central South University:Natural Science Edition,2012(12)：4949\|4955．［7］王蓉，张仁陟，陈英.基于多元回归分析和灰色模型的康乐县城乡建设用地预测［J］．甘肃农业大学学报，2012(1)：134\|139．WANG Rong,ZHANG Ren\|bu,CHEN Ying.Kang Le County Rural Construction Land Prediction based on Multivariate Regression Analysis and Gray Model［J］．Journal of Gansu Agricultural University，2012(1)：134\|139．(in Chinese)［8］Victor Kipnis, Douglas Midthune, Laurence S Freedman,et al.Regression calibration with more surrogates than mismeasured variables［J］．Statist Med，2012,31:23.［9］杜家龙.国内生产总值回归预测新探［J］．统计与决策,2013(9)：9\|14．DU Jia\|long.GDP regression Exploration［J］．Statistics and Decision,2013(9)：9\|14．(in Chinese)

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：20130929基金项目： 国家社会科学基金资助项目（13BGL150）作者简介：王颖林（1987\|），女，山西运城人，博士研究生.研究方向：项目管理.
更新日期/Last Update: 2013-12-03