Please wait a minute...
浙江大学学报（理学版）
浙江大学学报（理学版）  2016, Vol. 43 Issue (3): 357-363    DOI: 10.3785/j.issn.1008-9497.2016.03.017
城市科学     
基于SVM和LS-SVM的住宅工程造价预测研究
秦中伏1, 雷小龙1, 翟东1, 金灵志2
1. 浙江大学 建筑工程学院, 浙江 杭州 310058;
2. 杭州市发展规划研究院, 浙江 杭州 310006
Forecasting the costs of residential construction based on support vector machine and least squares-support vector machine
QIN Zhongfu1, LEI Xiaolong1, ZHAI Dong1, JIN Lingzhi2
1. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China;
2. Hangzhou Development Planning & Research Institute, Hangzhou 310006, China
 全文: PDF(445 KB)  
摘要： 为在方案设计初期与工程造价相关信息很少的条件下,准确快速地预测住宅工程造价,在分析既往相关理论和方法优劣的基础上,选取支持向量机构建住宅工程造价预测模型,并通过主成分分析对原始数据进行降噪处理.选取住宅工程造价预测指标集与样本,对输入指标的数据进行主成分分析,消除指标相关性的同时对原始数据降维,将处理后的数据分别导入到"标准支持向量机"和"最小二乘支持向量机"模型中进行训练和预测,并对预测结果进行对比分析,选取较为合理的预测模型,通过参数寻优进一步优化预测效果.所构建预测模型的相对误差均控制在±7%以内,预测精度较高,结果稳定.
关键词： 造价预测;  主成分分析;  支持向量机;  最小二乘支持向量机    
Abstract: To forecast the costs of a residential construction rapidly and accurately at the initial stage of construction that lacks relevant information, in view of the strengths and weaknesses of previous approaches, we choose support vector machine (SVM) and principal component analysis (PCA). Firstly, a residential project cost forecasting index set is selected; The data of the input index is then analyzed and the correlation is eliminated by PCA; Thirdly, the processed data are imported into the standard support vector machine and trained by the least squares support vector machine model. The prediction results are compared and analyzed, and then a more reasonable prediction model is adopted; Finally, the prediction result of the model is optimized by model parameter optimization. Experiments show that the relative error of the prediction model is controlled within ±7%, and the result is stable.
Key words: construction cost forecasting    principal component analysis    support vector machine    least squares support vector machine
收稿日期: 2015-11-30 出版日期: 2016-03-01
CLC:  TU-9  
基金资助: 国网浙江省电力公司经济技术研究院资助项目(12-513205-007,名称:输电线路工程造价预测快速实现).
通讯作者: 翟东,ORCID:http://orcid.org//0000-0001-5309-060X,E-mail:0012078@zju.edu.cn.     E-mail: 0012078@zju.edu.cn
作者简介: 秦中伏(1965-),ORCID:http://orcid.org//0000-0003-3894-1263,男,副教授,博士,主要从事人工智能、建筑经济等研究,E-mail:qinzhongfu@zju.edu.cn.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

秦中伏, 雷小龙, 翟东, 金灵志. 基于SVM和LS-SVM的住宅工程造价预测研究[J]. 浙江大学学报（理学版）, 2016, 43(3): 357-363.

QIN Zhongfu, LEI Xiaolong, ZHAI Dong, JIN Lingzhi. Forecasting the costs of residential construction based on support vector machine and least squares-support vector machine. Journal of ZheJIang University(Science Edition), 2016, 43(3): 357-363.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2016.03.017    或    https://www.zjujournals.com/sci/CN/Y2016/V43/I3/357

[1] 毛义华.建筑工程经济[M].杭州:浙江大学出版社,2012:145. MAO Yihua.Construction Economy[M]. Hangzhou:Zhejiang University Press, 2012:145.
[2] 薛向阳.一种改进的线性回归预测模型[J].科学技术与工程,2010,10(12):2970-2973. XUE Xiangyang. Improved linear regression forecast model[J].Science Technology and Engineering,2010,10(12):2970-2973.
[3] KAYACAN E, ULUTAS B, KAYNAK O. Grey system theory-based models in time series prediction[J]. Expert Systems with Applications,2010,37(2):1784-1789.
[4] 余昕.基于数据挖掘的时间序列预测的研究与应用 [D]. 北京:中国地质大学,2011. YU Xin. Research and Application on Time Series Prediction Based on Data Mining Method[D]. Beijing:Chinese University of Geosciences,2011.
[5] 陈智勇, 廉海涛, 吴星星.一种改进的神经网络分支预测技术[J].微电子学与计算机,2014,31(11):152-155. CHEN Zhiyong, LIAN Haitao,WU Xingxing. An improved branch prediction based on the neural network[J]. Microelectronics and Computer,2014,31(11):152-155.
[6] 祝文娟.基于遗传模糊神经网络的建筑工程造价估算模型[D].焦作:河南理工大学,2010. ZHU Wenjuan. Building Project Cost Estimate Model Based on Genetic Fuzzy Neural Network[D]. Jiaozuo:Henan Polytechnic University,2010.
[7] YIN M S. Fifteen years of grey system theory research: A historical review and bibliometric analysis[J]. Expert Systems with Applications,2013,40(7):2767-2775.
[8] 孙涛.灰色系统预测理论在建筑工程造价中的应用 [D].西安:西北工业大学,2006. SUN Tao. Gray Forecast Theory in the Construction Costs[D]. Xi'an: Northwestern Polytechnical University,2006.
[9] VAPNIK V N. Statistical Learning Theory[M]. New York: John Wiley,1998:34-42.
[10] ALDRICH C, AURET L. Statistical learning theory and kernel-based methods[C] // Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods. London: Springer , 2013: 117-181.
[11] 蒋丽娜.基于支持向量机的建筑工程造价预测研究[D]. 邯郸: 河北工程大学,2009. JIANG Lina. Research on the Predict of the Construction Cost Based on Support Vector Machine[D]. Handan: Hebei University of Engineering,2009.
[12] 白鹏,张喜斌,张斌. 支持向量机理论及工程应用实例 [M].西安:西安电子科技大学出版社, 2008:13-36. BAI Peng, ZHANG Xibin, ZHANG Bin. Support Vector Machine Theory and Engineering Application Examples[M]. Xi'an:: Xidian University Press, 2008:13-36.
[13] PENG X. TSVR: An efficient twin support vector machine for regression[J]. Neural Networks,2010,23(3):365-372.
[14] SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letter,1999(3):293-300.
[15] 邢永忠.最小二乘支持向量机的若干问题与应用研究[D].南京: 南京理工大学,2009. XING Yongzhong. A Number of Problems and Applications of the Least Squares Support Vector Machine[D]. Nanjing: Nanjing University of Science and Technology, 2009.
[16] 彭光金,俞集辉,韦俊涛,等.特征提取和小样本学习的电力工程造价预测模型[J].重庆大学学报,2009,32(9):1104-1110. PENG Guangjin, YU Jihui, WEI Juntao, et al. Cost forecast model for power engineering based on feature extraction and small-sample learning[J].Journal of Chongqing University,2009,32(9):1104-1110.
[17] 申瑞娜,曹昶,樊重俊.基于主成分分析的支持向量机模型对上海房价的预测研究[J].数学的实践与认识,2013,43(23):11-16. SHEN Ruina, CAO Chang, FAN Chongjun. Support vector machine model based on principal component analysis for the Shanghai real estate price of prediction[J]. Mathematics in Practice and Theory,2013,43(23):11-16.
[18] 刘健. 基于支持向量机的在线学习算法研究[D]. 杭州:浙江大学,2013. LIU Jian. Study on the Online Learning Algorithm Based on Support Vector Machine[D]. Hangzhou: Zhejiang University,2013.
[19] 顾燕萍,赵文杰,吴占松.最小二乘支持向量机的算法研究[J].清华大学学报:自然科学版,2010(07):1063-1066,1071. GU Yanping, ZHAO Wenjie, WU Zhansong. Algorithm for least squares support vector machine[J]. Journal of Tsinghua University :Natural Science Edition, 2010(07):1063-1066,1071.
[20] ABDI H, WILLIAMS L J. Principal component analysis[J]. Wiley Interdisciplinary Reviews: Computational Statistics,2010,2(4):433-459.
[21] CRISTIANINI N, SHAWE-TAYLOR J. An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods [M]. Cambridge: Cambridge University Press,2000:30-34.
[22] BOOLCHANDANI D, SAHULA V. Exploring efficient kernel functions for support vector machine based feasibility mod
[1] 胡海涛,赵银君,石敏,赵国亮,朱登明. 三维鱼体参数化建模[J]. 浙江大学学报（理学版）, 2022, 49(1): 19-26.
[2] 邓惠俊. 排序支持的交互数据分类算法及其应用[J]. 浙江大学学报（理学版）, 2021, 48(1): 9-17.
[3] 陈珍慧, 鲁益飞, 胡江琴, 张漪, 金孝锋. 中国特有植物诸葛菜属(十字花科)的分类研究[J]. 浙江大学学报（理学版）, 2017, 44(2): 201-205.