《计算机应用研究》|Application Research of Computers

基于梯度提升决策模型的空间占用检测研究

Occupancy detection based on extreme gradient boosting decision model

免费全文下载 (已被下载 次)  
获取PDF全文
作者 徐新卫,丁敬安,柳智才,王多梅,腾翔,邵瑞瑞
机构 1.安徽工业大学 管理科学与工程学院,安徽 马鞍山 243000;2.南京大学 计算软件新技术国家重点实验室,南京 210000;3.河海大学 公共管理学院,南京 210000
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)03-019-0736-06
DOI 10.19734/j.issn.1001-3695.2017.09.0907
摘要 随着绿色建筑和绿色生态城区经济激励机制基本形成,面对大量多维空间占用数据,大数据绿色建筑节能体系应运而生。然而大量多维的建筑数据却没有被充分利用,且传统空间占用检测模型分类精度还不够准确,模型时间复杂度较高。利用UCI占用检测数据集,在原始数据集上加入时间戳,使模型分类精度均获得提高,同时利用MCMR(最大相关最小冗余)方法进行特征选择,通过随机森林作为分类器验证分类效果,获取最优特征子集。利用选取的特征子集构建占用检测模型,其中XGBoost模型与随机森林模型(RF)进行比对,分类精度较高,且时间复杂度更低。
关键词 大数据绿色建筑;空间占用检测;最大相关最小冗余;梯度提升算法
基金项目 国家社科基金资助项目(15BJL014)
本文URL http://www.arocmag.com/article/01-2019-03-019.html
英文标题 Occupancy detection based on extreme gradient boosting decision model
作者英文名 Xu Xinwei, Ding Jing’an, Liu Zhicai, Wang Duomei, Teng Xiang, Shao Ruirui
机构英文名 1.SchoolofManagementScience&Engineering,AnhuiUniversityofTechnology,MaanshanAnhui243000,China;2.StateKeyLaboratoryforNovelSoftwareTechnology,NanjingUniversity,Nanjing210000,China;3.SchoolofPublicAdministration,HohaiUniversity,Nanjing210000,China
英文摘要 With the green buildings and green-economic environmental cities are gradually formed, big data green building energy conservation systems come into being. However, a large number of multi-dimensional building data are not fully utilized and occupancy detection with accuracy of traditional algorithms is not accurate with the higher time complexity. This article acquired the data of occupancy detection from UCI. Adding a timestamp to the original dataset, it increased the accuracy. Using the MCMR method to select features with maximum correlation and minimum redundancy, it used random forest as classifier to verify classification effect. The XGBoost model constructed by the optimal subset was compared with the random forest model (RF), and the classification accuracy is higher and the time complexity is lower.
英文关键词 big data of green buildings; occupancy detection; MCMR; XGBoost
参考文献 查看稿件参考文献
  [1] 仇保兴. 我国绿色建筑发展和建筑节能的形势与任务[J] . 城市发展研究, 2012, 19(5):1-7, 11. (Qiu Baoxing. Situation and tasks of green building developrnent and building energy saving in china[J] . Urban Studies, 2012, 19(5):1-7, 11. )
[2] 郭萍, 李国刚. 浅析中国当前绿色建筑发展的问题及对策[J] . 土木建筑与环境工程, 2015, 37(S1):96-98. (Guo Ping, Li Guogang. Analysis on the problems and countermeasures of the current green building development in China[J] . Civil Construction and Environmental Engineering, 2015, 37(S1):96-98. )
[3] 徐涛, 王祁. 基于模式识别的传感器故障诊断[J] . 控制与决策, 2007, 22(7):783-786. (Xu Tao, Wang Qi. Sensor fault diagnosis based on pattern recognition[J] . Control and Decision, 2007, 22(7):783-786. )
[4] 金连文, 钟卓耀, 杨钊, 等. 深度学习在手写汉字识别中的应用综述[J] . 自动化学报, 2016, 42(8):1125-1141. (Jin Lianwen, Zhong Zhuoyao, Yang Zhao, et al. Application of deep learning for handwritten Chinese character recognition:a review[J] . Acta Automatica Sinica, 2016, 42(8):1125-1141. )
[5] 杨赛, 赵春霞, 刘凡. 多核学习融合局部和全局特征的人脸识别算法[J] . 电子学报, 2016, 44(10):2344-2350. (Yang Sai, Zhao Chunxia, Liu Fan. Fusion of local and global features using multiple kernel learning for face recognition[J] . Acta Electronica Sinica, 2016, 44(10):2344-2350.
[6] Erickson V L, Carreira-Perpinán M , Cerpa A E. OBSERVE:occupancy-based system for efficient reduction of HVAC energy[C] //Proc of the 10th International Conference on Information Processing in Sensor Networks. Piscataway, NJ:IEEE Press, 2011:258-269.
[7] Erickson V L, Carreira-Perpinán M , Cerpa A. E. Occupancy modeling and prediction for building energy management[J] . ACM Trans on Sensor Network, 2014, 10(3):article No. 42.
[8] Dong Bing, Andrews B. Sensor-based occupancy behavioral pattern recognition for energy and comfort management in intelligent buildings[C] //Proc of the 11th International Conference on IBPSA. 2009:1444-1451.
[9] Brooks J, Goyal S, Subramany R, et al An experimental investigation of occupancy-based energy-efficient control of commercial building indoor climate[C] //Proc of the 53rd IEEE Conference on Decision and Control . Piscataway, NJ:IEEE Press, 2014:5680-5685.
[10] Brooks J, Kumar S, Goyal S, et al. Energy-efficient control of under-actuated HVAC zones in commercial buildings[J] . Energy and Buildings, 2015, 93(4):160-168.
[11] Tomastik R, Narayanan S, Banaszuk A, et al. Model-based real-time estimation of building occupancy during emergency egress[M] //Pedestrian and Evacuation Dynamics. Berlin:Springer, 2008:215-224.
[12] Scott J, Bernheim Brush A J, Krumm J, et al. PreHeat:controlling home heating using occupancy prediction[C] //Proc of the 13th International Conference on Ubiquitous Computing. New York:ACM Press, 2011:281-290.
[13] Ghai S K, Thanayankizil L V, Seetharam D P, et al. Chakraborty:occupancy detection in commercial buildings using opportunistic context sources[C] //Proc of IEEE International Conference on Pervasive Computing and Communications Workshops. Piscataway, NJ:IEEE Press, 2012:463-466.
[14] Hailemariam E, Goldstein R, Attar R, et al. Real-time occupancy detection using decision trees with multiple sensor types[C] //Proc of Symposium on Simulation for Architecture and Urban Design. 2011:141-148.
[15] Candanedo L M, Feldheim V. Accurate occupancy detection of an office room from light, temperature, humidity and CO2 measurements using statistical learning models[J] . Energy and Buildings, 2016, 112(1):28-39.
[16] Chen Tianqi, He Tong. Higgs boson discovery with boosted trees[C] //Proc of International Conference on High-Energy Physics and Machine Learning. 2014:69-80.
[17] Chen Tianqi, Guestrin C. XGboost:a scalable tree boosting system[C] //Proc of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2016:785-794.
[18] Song Rongwei, Chen Siding, Deng Bailong, et al. eXtreme gradient boosting for identifying individual users across different digital devices[C] //Proc of international conference on Web-Age Information Management. [S. l. ] :Springer International Publishing, 2016:43-54.
[19] 姚旭, 王晓丹, 张玉玺, 等. 特征选择方法综述[J] . 控制与决策, 2012, 27(2):161-166, 192. (Yao Xu, Wang Xiaodan, Zhang Yuxi, et al. Summary of feature selection algorithms[J] . Control and Decision, 2012, 27(2):161-166, 192. )
[20] 毛勇, 周晓波, 夏铮, 等. 特征选择算法研究综述[J] . 模式识别与人工智能, 2007, 20(2):211-218. (Mao Yong, Zhou Xiaobo, Xia Zheng, et al. A survey for study of feature selection algorithm[J] . Pattern Recognition and Artificial Intelligence, 2007, 20(2):211-218. )
[21] 仇利克, 郭忠文, 刘青, 等. 基于冗余分析的特征选择算法[J] . 北京邮电大学学报, 2017, 40(1):36-41. (Qiu Like, Guo Zhongwen, Liu Qing, et al. Feature selection algorithm based on redundancy analysis[J] . Journal of Beijing University of Posts and Telecommunications, 2017, 40(1):36-41. )
[22] Yu Lei, Liu Huan. Efficient feature selection via analysis of relevance and redundancy[J] . Journal of Machine Learning Research, 2004, 5:1205-1224.
[23] 李扬, 顾雪平. 基于改进最大相关最小冗余判据的暂态稳定评估特征选择[J] . 中国电机工程学报, 2013, 33(34):179-186. (Li Yang, Gu Xueping. Feature selection of transient stability assessment based on improved maximal relevance and minimal redundancy criterion[J] . Proceeding of the CSEE, 2013, 33(34):179-186. )
[24] 赵伟卫, 李艳颖, 赵风芹, 等. 基于互信息和随机森林的混合变量选择算法[J] . 吉林大学学报:理学版, 2017, 55(4):933-939. (Zhao Weiwei, Li Yanying, Zhao Fengqin, et al. Hybrid variable selection algorithm based on mutual information and random forest[J] . Journal of Jilin University:Science Edition, 2017, 55(4):933-939. )
[25] 徐峻岭, 周毓明, 陈林, 等. 基于互信息的无监督特征选择[J] . 计算机研究与发展, 2012, 49(2):372-382. (Xu Junling, Zhou Yu-ming, Chen Lin, et al. An unsupervised feature selection approach based on mutual information[J] . Journal of Computer Research and Development, 2012, 49(2):372-382. )
[26] 张振海, 李士宁, 李志刚, 等. 一类基于信息熵的多标签特征选择算法[J] . 计算机研究与发展, 2013, 50(6):1177-1184. (Zhang Zhenhai, Li Shining, Li Zhigang, et al. Multi-label feature selection algorithm based on information entropy[J] . Journal of Computer Research and Development, 2013, 50(6):1177-1184. )
[27] 董红斌, 滕旭阳, 杨雪. 一种基于关联信息熵度量的特征选择方法[J] . 计算机研究与发展, 2016, 53(8):1684-1695. (Dong Hongbin, Teng Xuyang, Yang Xue. Feature selection based on the measurement of correlation information entropy[J] . Journal of Computer Research and Development, 2016, 53(8):1684-1695. )
[28] 薛薇. 基于R统计分析与数据挖掘[M] . 北京:中国人民大学出版社, 2014:1-399. (Xue Wei. Statistical analysis and data mining based on R[M] . Beijing:Renmin University of China Press, 2014:1-399. )
[29] 周志华. 机器学习[M] . 北京:清华大学出版社, 2016:1-425. (Zhou Zhihua. Machine learning[M] . Beijing:Tsinghua University Press, 2016:1-425. )
[30] 赵静娴, 倪春鹏, 詹原瑞, 等. 一种高效的连续属性离散化算法[J] . 系统工程与电子技术, 2009, 31(1):195-199. (Zhao Jing-xian, Ni Chunpeng, Zhan Yuanrui, et al. Efficient discretization algorithm for continuous attributes[J] . Systems Engineering and Electronics, 2009, 31(1):195-199. )
[31] 杨萍, 杨天社, 杜小宁, 等. 一种基于类别属性关联程度最大化离散算法[J] . 控制与决策, 2011, 26(4):592-596. (Yang Ping, Yang Tianshe, Du Xiaoning, et al. A class-attribute interdependency maximization based algorithm for supervised discretization[J] . Control and Decision, 2011, 26(4):592-596. )
收稿日期 2017/9/4
修回日期 2017/11/20
页码 736-741
中图分类号 TP301.6
文献标志码 A