[1]郭强,邹广天.基于决策树分类的可拓建筑策划预测方法[J].智能系统学报,2017,12(1):117-123.[doi:10.11992/tis.201610015]
GUO Qiang,ZOU Guangtian.Prediction methods for extension architecture programming based on decision tree classification[J].CAAI Transactions on Intelligent Systems,2017,12(1):117-123.[doi:10.11992/tis.201610015]
点击复制
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
12
期数:
2017年第1期
页码:
117-123
栏目:
学术论文—智能系统
出版日期:
2017-02-25
- Title:
-
Prediction methods for extension architecture programming based on decision tree classification
- 作者:
-
郭强1,2,3, 邹广天1,2,3
-
1. 哈尔滨工业大学 建筑学院, 黑龙江 哈尔滨 150006;
2. 哈尔滨工业大学 建筑计划与设计研究所, 黑龙江 哈尔滨 150006;
3. 黑龙江省寒地建筑科学重点实验室, 黑龙江哈尔滨, 150006
- Author(s):
-
GUO Qiang1,2,3, ZOU Guangtian1,2,3
-
1. School of Architecture, Harbin Institute of Technology, Harbin 150006, China;
2. Architectural Planning and Design Institute, Harbin Institute of Technology, Harbin 150006, China;
3. Heilongjiang Cold Region Architectural Science Key Laboratory, Harbin 150006, China
-
- 关键词:
-
可拓建筑策划; 决策树; 分类; 指标预测; 可拓变换
- Keywords:
-
extension architectural program; decision tree; classification; indicators prediction; extension transformation
- 分类号:
-
TP18;TU18
- DOI:
-
10.11992/tis.201610015
- 摘要:
-
为提升建筑师在策划过程中科学预测的能力,提出了一种基于决策树分类的可拓建筑策划预测方法。首先,运用数据采集软件批量采集互联网中的建筑案例数据,将数据预处理后存储至建筑案例库中;其次,通过评价特征选取、评价信息元集生成、决策树构建等步骤,获得决策树模型;最后,运用该模型预测当前策划项目的性能指标是否满足要求,并给出不满足要求情况下性能指标变换的途径。案例检验表明,该方法能有效提高建筑师运用互联网数据的能力,能够挖掘决策树分类知识,从而加速计算机辅助可拓建筑策划的进程。
- Abstract:
-
To improve the prediction ability of architects, a prediction method for extension architecture programming (EAP) based on decision tree classification was proposed. First, the architectural case data from the Internet were obtained by data acquisition software, and stored in an architectural case database after data preprocessing. Second, through evaluation characteristics selection, evaluation information element set generation and decision tree construction, the decision tree model was discovered. Then, the performance indicators of the current project were predicted using this model, providing transformation approaches if the result did not satisfy the requirement. This study indicates that the proposed method can effectively improve an architects ability to use Internet data and mine decision tree classification knowledge, thus accelerating the process of computer aided EAP.
备注/Memo
收稿日期:2016-10-13;改回日期:。
基金项目:国家自然科学基金项目(51178132).
作者简介:郭强,男,1985年生,博士研究生,中国人工智能学会会员,主要研究方向为可拓建筑学、可拓建筑策划数据挖掘,参加完成国家自然科学基金项目1项,参编《中国原创学科——可拓学发展报告2016》;邹广天,男,1960年生,教授,博士生导师,博士,中国人工智能学会可拓学专业委员会副主任、中国建筑学会建筑师分会建筑策划专业委员会副主任、中国环境行为学会副会长,主要研究方向为建筑计划学、可拓建筑学、建筑设计创新学、环境行为心理学。主持完成国家自然科学基金项目2项,出版专著1部,主编与参编论文集多部,发表学术论文200余篇,被EI、CSSCI检索论文20余篇。
通讯作者:邹广天.E-mail:zougt@hit.edu.cn.
更新日期/Last Update:
1900-01-01