基于概念漂移检测的土石坝压实质量评价模型更新研究
|
摘要
土石坝压实质量评价模型的更新对保证其长期高精度评价压实质量具有重要的意义,然而目前对于压实质量模型的更新还缺乏相应的研究.借鉴流数据中概念漂移检测的思想,同时针对碾压施工流数据具有不平衡数据、含有噪声且流速缓慢的特点,本文提出了一种基于概念漂移检测的土石坝压实质量评价模型更新方法.首先提出基于K-means的下抽样技术处理不平衡数据;其次提出基于增强概率神经网络(enhancedprobabilisticneuralnetwork,EPNN)和可变窗口技术(variablewindowtechnique,VWT)的碾压施工流数据概念漂移检测方法;最后若检测到有概念漂移则进行压实质量评价模型的更新.工程应用表明:基于K-means的下抽样技术能保证分类器具有较高的一致性;基于EPNN与VWT的方法能有效地检测出碾压施工流数据概念漂移;同时以出现概念漂移为条件而更新的压实质量评价模型能够长期高精度评价压实质量.
Updating the compaction quality assessment model of earth-rock dams is important to ensure long-term and high-precision evaluation of the compaction quality. However,there is a lack of research on the update of the compaction quality model.In this study,based on the idea of concept drift detection in stream data,as well as the characteristics of construction stream data such as slow velocity,existing noise data,and unbalanced data,a method of detecting concept drift and updating the compaction quality assessment model is proposed. First,a down sampling technology based on K-means is designed to address the unbalanced data. Second,a concept drift detection method based on enhanced probabilistic neural network(EPNN)and variable window technique(VWT)is proposed. The compaction quality assessment model is updated if a concept drift is detected. The engineering application shows that the down sampling method based on K-means ensures high consistency of classifier. The method based on EPNN and VWT can effectively detect the concept drift of compaction stream data.
Updating the compaction quality assessment model of earth-rock dams is important to ensure long-term and high-precision evaluation of the compaction quality. However,there is a lack of research on the update of the compaction quality model.In this study,based on the idea of concept drift detection in stream data,as well as the characteristics of construction stream data such as slow velocity,existing noise data,and unbalanced data,a method of detecting concept drift and updating the compaction quality assessment model is proposed. First,a down sampling technology based on K-means is designed to address the unbalanced data. Second,a concept drift detection method based on enhanced probabilistic neural network(EPNN)and variable window technique(VWT)is proposed. The compaction quality assessment model is updated if a concept drift is detected. The engineering application shows that the down sampling method based on K-means ensures high consistency of classifier. The method based on EPNN and VWT can effectively detect the concept drift of compaction stream data.
引文
[1]Meehan C L,Cacciola D V,Tehrani F S,et al.Assessing soil compaction using continuous compaction control and location-specific in situ tests[J].Automation in Construction,2017,73:31-44.
[2]刘东海,王光烽.实时监控下土石坝碾压质量全仓面评估[J].水利学报,2010,41(6):720-726.Liu Donghai,Wang Guangfeng.Compaction quality evaluation of the entire rolled unit of earth dam based on real-time monitoring[J].Journal of Hydraulic Engineering,2010,41(6):720-726(in Chinese).
[3]Wang Jiajun,Zhong Denghua,Wu Binping,et al.Evaluation of compaction quality based on SVR with CFA:Case study on compaction quality of earth-rock dam[J].Journal of Computing in Civil Engineering,2018,32(3):05018001.
[4]金澈清,钱卫宁,周傲英.流数据分析与管理综述[J].软件学报,2004,15(8):1172-1181.Jin Cheqing,Qian Weining,Zhou Aoying.Analysis and management of streaming data:A survey[J].Journal of Software,2004,15(8):1172-1181(in Chinese).
[5]文益民,强保华,范志刚.概念漂移数据流分类研究综述[J].智能系统学报,2013,8(2):95-104.Wen Yimin,Qiang Baohua,Fan Zhigang.A survey of the classification of data streams with concept drift[J].CAAI Transactions on Intelligent Systems,2013,8(2):95-104(in Chinese).
[6]Nishida K,Yamauchi K.Detecting concept drift using statistical testing[C]//International Conference on Discovery Science.Berlin,Germany,2007:264-269.
[7]陈小东,孙力娟,韩崇,等.基于模糊聚类的数据流概念漂移检测算法[J].计算机科学,2016,43(4):219-223.Chen Xiaodong,Sun Lijuan,Han Chong,et al.Detecting concept drift of data stream based on fuzzy clustering[J].Computer Science,2016,43(4):219-223(in Chinese).
[8]Katakis I,Tsoumakas G,Vlahavas I.Tracking recurring contexts using ensemble classifiers:An application to email filtering[J].Knowledge and Information Systems,2010,22(3):371-391.
[9]张杰,赵峰.流数据概念漂移的检测算法[J].控制与决策,2013,28(1):29-35.Zhang Jie,Zhao Feng.Detecting algorithm of concept drift from stream data[J].Control and Decision,2013,28(1):29-35(in Chinese).
[10]张育培,柴玉梅,王黎明.基于鞅的数据流概念漂移检测方法[J].小型微型计算机系统,2013,34(8):1787-1792.Zhang Yupei,Cai Yumei,Wang Liming.Method of concept drifting detection based on martingale in data stream[J].Journal of Chinese Computer Systems,2013,34(8):1787-1792(in Chinese).
[11]Liu Donghai,Li Zilong,Lian Zhenhong.Compaction quality assessment of earth-rock dam materials using roller-integrated compaction monitoring technology[J].Automation in Construction,2014,44:234-246.
[12]Zhong Denghua,Cui Bo,Liu Donghai,et al.Theoretical research on construction quality real-time monitoring and system integration of core rockfill dam[J].Science in China Series E:Technological Sciences,2009,52(11):3406-3412.
[13]Zhong Denghua,Liu Donghai,Cui Bo.Real-time compaction quality monitoring of high core rockfill dam[J].Science China Technological Sciences,2011,54(7):1906-1913.
[14]Chawla N V,Bowyer K W,Hall L O,et al.SMOTE:Synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002,16(1):321-357.
[15]Batista G E,Prati R C,Monard M C.A study of the behavior of several methods for balancing machine learning training data[J].ACM SIGKDD Explorations Newsletter,2004,6(1):20-29.
[16]Duan K,Keerthi S S,Poo A N.Evaluation of simple performance measures for tuning SVM hyperparameters[J].Neurocomputing,2003,51(2):41-59.
[17]林智勇.基于核方法的不平衡数据学习[D].广州:算机科学与工程学院,华南理工大学,2009.Lin Zhiyong.Imbalanced Data Learning Based on Kernel Methods[D].Guangzhou:School of Computer Science and Engineering,South China University of Technology,2009(in Chinese).
[18]Wibisono A,Jatmiko W,Wisesa H A,et al.Traffic big data prediction and visualization using fast incremental model trees-drift detection(FIMT-DD)[J].Knowledge-Based Systems,2016,93:33-46.
[19]Ahmadlou M,Adeli H.Enhanced probabilistic neural network with local decision circles:A robust classifier[J].Integrated Computer-Aided Engineering,2010,17(17):197-210.
[20]Olmeda D,Premebida C,Nunes U,et al.Pedestrian detection in far infrared images[J].Integrated ComputerAided Engineering,2013,20(4):347-360.
[21]Esposito S,Iervolino I,D′Onofrio A,et al.Simulation-based seismic risk assessment of gas distribution networks[J].Computer-Aided Civil and Infrastructure Engineering,2015,30(7):508-523.
[22]Veksler O.Fast Variable window for stereo correspondence using integral images[C]//IEEE Computer Society Conference on Computer Vision&Pattern Recognition.Madison,USA,2003:556-561.
[23]郭永水,牛建伟,覃少华,等.基于可变窗口的流媒体缓存算法研究与实现[J].计算机工程与应用,2004,40(35):41-43,63.Guo Yongshui,Niu Jianwei,Qin Shaohua,et al.Research and implementation of streaming data media caching algorithm based on variable window[J].Computer Engineering and Applications,2004,40(35):41-43,63(in Chinese).
[24]郭龙源,孙长银,张国云,等.基于相位一致性的可变窗口立体匹配算法[J].计算机科学,2015,42(增1):13-15.Guo Longyuan,Sun Changyin,Zhang Guoyun,et al.Variable window stereo matching based on phase congruency[J].Computer Science,2015,42(Suppl1):13-15(in Chinese).
[2]刘东海,王光烽.实时监控下土石坝碾压质量全仓面评估[J].水利学报,2010,41(6):720-726.Liu Donghai,Wang Guangfeng.Compaction quality evaluation of the entire rolled unit of earth dam based on real-time monitoring[J].Journal of Hydraulic Engineering,2010,41(6):720-726(in Chinese).
[3]Wang Jiajun,Zhong Denghua,Wu Binping,et al.Evaluation of compaction quality based on SVR with CFA:Case study on compaction quality of earth-rock dam[J].Journal of Computing in Civil Engineering,2018,32(3):05018001.
[4]金澈清,钱卫宁,周傲英.流数据分析与管理综述[J].软件学报,2004,15(8):1172-1181.Jin Cheqing,Qian Weining,Zhou Aoying.Analysis and management of streaming data:A survey[J].Journal of Software,2004,15(8):1172-1181(in Chinese).
[5]文益民,强保华,范志刚.概念漂移数据流分类研究综述[J].智能系统学报,2013,8(2):95-104.Wen Yimin,Qiang Baohua,Fan Zhigang.A survey of the classification of data streams with concept drift[J].CAAI Transactions on Intelligent Systems,2013,8(2):95-104(in Chinese).
[6]Nishida K,Yamauchi K.Detecting concept drift using statistical testing[C]//International Conference on Discovery Science.Berlin,Germany,2007:264-269.
[7]陈小东,孙力娟,韩崇,等.基于模糊聚类的数据流概念漂移检测算法[J].计算机科学,2016,43(4):219-223.Chen Xiaodong,Sun Lijuan,Han Chong,et al.Detecting concept drift of data stream based on fuzzy clustering[J].Computer Science,2016,43(4):219-223(in Chinese).
[8]Katakis I,Tsoumakas G,Vlahavas I.Tracking recurring contexts using ensemble classifiers:An application to email filtering[J].Knowledge and Information Systems,2010,22(3):371-391.
[9]张杰,赵峰.流数据概念漂移的检测算法[J].控制与决策,2013,28(1):29-35.Zhang Jie,Zhao Feng.Detecting algorithm of concept drift from stream data[J].Control and Decision,2013,28(1):29-35(in Chinese).
[10]张育培,柴玉梅,王黎明.基于鞅的数据流概念漂移检测方法[J].小型微型计算机系统,2013,34(8):1787-1792.Zhang Yupei,Cai Yumei,Wang Liming.Method of concept drifting detection based on martingale in data stream[J].Journal of Chinese Computer Systems,2013,34(8):1787-1792(in Chinese).
[11]Liu Donghai,Li Zilong,Lian Zhenhong.Compaction quality assessment of earth-rock dam materials using roller-integrated compaction monitoring technology[J].Automation in Construction,2014,44:234-246.
[12]Zhong Denghua,Cui Bo,Liu Donghai,et al.Theoretical research on construction quality real-time monitoring and system integration of core rockfill dam[J].Science in China Series E:Technological Sciences,2009,52(11):3406-3412.
[13]Zhong Denghua,Liu Donghai,Cui Bo.Real-time compaction quality monitoring of high core rockfill dam[J].Science China Technological Sciences,2011,54(7):1906-1913.
[14]Chawla N V,Bowyer K W,Hall L O,et al.SMOTE:Synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research,2002,16(1):321-357.
[15]Batista G E,Prati R C,Monard M C.A study of the behavior of several methods for balancing machine learning training data[J].ACM SIGKDD Explorations Newsletter,2004,6(1):20-29.
[16]Duan K,Keerthi S S,Poo A N.Evaluation of simple performance measures for tuning SVM hyperparameters[J].Neurocomputing,2003,51(2):41-59.
[17]林智勇.基于核方法的不平衡数据学习[D].广州:算机科学与工程学院,华南理工大学,2009.Lin Zhiyong.Imbalanced Data Learning Based on Kernel Methods[D].Guangzhou:School of Computer Science and Engineering,South China University of Technology,2009(in Chinese).
[18]Wibisono A,Jatmiko W,Wisesa H A,et al.Traffic big data prediction and visualization using fast incremental model trees-drift detection(FIMT-DD)[J].Knowledge-Based Systems,2016,93:33-46.
[19]Ahmadlou M,Adeli H.Enhanced probabilistic neural network with local decision circles:A robust classifier[J].Integrated Computer-Aided Engineering,2010,17(17):197-210.
[20]Olmeda D,Premebida C,Nunes U,et al.Pedestrian detection in far infrared images[J].Integrated ComputerAided Engineering,2013,20(4):347-360.
[21]Esposito S,Iervolino I,D′Onofrio A,et al.Simulation-based seismic risk assessment of gas distribution networks[J].Computer-Aided Civil and Infrastructure Engineering,2015,30(7):508-523.
[22]Veksler O.Fast Variable window for stereo correspondence using integral images[C]//IEEE Computer Society Conference on Computer Vision&Pattern Recognition.Madison,USA,2003:556-561.
[23]郭永水,牛建伟,覃少华,等.基于可变窗口的流媒体缓存算法研究与实现[J].计算机工程与应用,2004,40(35):41-43,63.Guo Yongshui,Niu Jianwei,Qin Shaohua,et al.Research and implementation of streaming data media caching algorithm based on variable window[J].Computer Engineering and Applications,2004,40(35):41-43,63(in Chinese).
[24]郭龙源,孙长银,张国云,等.基于相位一致性的可变窗口立体匹配算法[J].计算机科学,2015,42(增1):13-15.Guo Longyuan,Sun Changyin,Zhang Guoyun,et al.Variable window stereo matching based on phase congruency[J].Computer Science,2015,42(Suppl1):13-15(in Chinese).
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |