基于联合特征和XGBoost的活动语义识别方法

doi:10.11772/j.issn.1001-9081.2020030301

计算机应用 ›› 2020, Vol. 40 ›› Issue (11): 3159-3165.DOI: 10.11772/j.issn.1001-9081.2020030301

基于联合特征和XGBoost的活动语义识别方法

郭茂祖^1,2, 张彬^1,2, 赵玲玲³, 张昱^1,2,4

1. 北京建筑大学电气与信息工程学院, 北京 100044;
2. 建筑大数据智能处理方法研究北京市重点实验室(北京建筑大学), 北京 100044;
3. 哈尔滨工业大学计算机科学与技术学院, 哈尔滨 150001;
4. 深部岩土力学与地下工程国家重点实验室(中国矿业大学), 北京 100083

收稿日期:2020-03-18 修回日期:2020-06-19 出版日期:2020-11-10 发布日期:2020-11-24
通讯作者: 赵玲玲(1980-),女,黑龙江齐齐哈尔人,讲师,博士,主要研究方向:机器学习、智慧城市、生物信息学;zhaoll@hit.edu.cn
作者简介:郭茂祖(1966-),男,山东德州人,教授,博士生导师,博士,主要研究方向:机器学习、智慧城市、生物信息学;张彬(1994-),男,河北石家庄人,硕士研究生,主要研究方向:机器学习、智慧城市;张昱(1979-),男,内蒙古呼和浩特人,副教授,博士,主要研究方向:大数据、机器学习、智慧城市
基金资助:
国家自然科学基金面上项目（61871020）；北京市教委科技计划重点项目（KZ201810016019）；北京市属高校高水平创新团队建设计划项目（IDHT20190506）；教育部2018产学合作协同育人项目（201801113001）；北京建筑大学优秀主讲教师培育计划项目（21082718041）；北京建筑大学市属高校基本科研业务费专项资金资助项目（X18018）；北京建筑大学2020年度研究生创新项目（PG202005）。

Activity semantic recognition method based on joint features and XGBoost

GUO Maozu^1,2, ZHANG Bin^1,2, ZHAO Lingling³, ZHANG Yu^1,2,4

1. School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
2. Beijing Key Laboratory of Intelligent Processing for Building Big Data;(Beijing University of Civil Engineering and Architecture), Beijing 100044, China;
3. School of Computer Science and Technology, Harbin Institute of Technology, Harbin Heilongjiang 150001, China;
4. State Key Laboratory for Geomechanics and Deep Underground Engineering(China University of Mining and Technology), Beijing 100083, China

Received:2020-03-18 Revised:2020-06-19 Online:2020-11-10 Published:2020-11-24
Supported by:
This work is partially supported by General Program of the National Natural Science Foundation of China (61871020),the Key Project of Science and Technology Plan of Beijing Municipal Commission of Education (KZ201810016019), the Beijing University High-level Innovation Team Building Plan (IDHT20190506), the Industry-University Cooperative Education Project of Ministry of Education (201801113001), the Excellent Teachers Development Foundation of Beijing University of Civil Engineering and Architecture (21082718041), the Fundamental Research Funds for Beijing University of Civil Engineering and Architecture (X18018), the Graduate Innovation Project of Beijing University of Civil Engineering and Architecture in 2020 (PG202005).

摘要/Abstract

摘要： 针对以往活动语义识别研究单纯提取时间维度上的序列特征以及周期特征、缺乏对空间信息的深度挖掘等问题，提出一种基于联合特征和极限梯度提升（XGBoost）的活动语义识别方法。首先，挖掘时间信息中的活动周期性特征和空间信息中的经纬度特征；然后，使用经纬度信息通过具有噪声的基于密度的聚类（DBSCAN）算法提取空间区域热度特征，将这些特征组成特征向量来刻画用户活动语义；最后，采用集成学习方法中的XGBoost算法建立活动语义识别模型。在FourSquare的两个公共签到数据集上，基于联合特征的模型比基于时间特征的模型在识别准确率上提高了28个百分点，与上下文感知混合（CAH）方法和时空活动偏好（STAP）方法对比，所提方法的识别准确率分别提高了30个百分点和5个百分点。实验结果表明所提方法与对比方法相比在活动语义识别问题上更加准确有效。

关键词: 时空数据, 活动语义识别, 空间热度, 具有噪声的基于密度的聚类, 极限梯度提升算法

Abstract: The current research on the activity semantic recognition only extracts the sequence features and periodic features on the time dimension, and lacks deep mining of spatial information. To solve these problems, an activity semantic recognition method based on joint features and eXtreme Gradient Boosting (XGBoost) was proposed. Firstly, the activity periodic features in the temporal information as well as the latitude and longitude features in the spatial information were extracted. Then the latitude and longitude information was used to extract the heat features of the spatial region based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The user activity semantics was represented by the feature vectors combined with these features. Finally, the activity semantic recognition model was established through the XGBoost algorithm in the integrated learning method. On two public check-in datasets of FourSquare, the model based on joint features has a 28 percentage points improvement in recognition accuracy compared to the model with only temporal features, and compared with the Context-Aware Hybrid (CAH) method and the Spatial Temporal Activity Preference (STAP) method, the proposed method has the recognition accuracy increased by 30 percentage points and 5 percentage points respectively. Experimental results show that the proposed method is more accurate and effective on the problem of activity semantic recognition compared to the the comparison methods.

Key words: spatio temporal data, activity semantic recognition, spatial heat, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), eXtreme Gradient Boosting (XGBoost) algorithm

中图分类号:

TP181

郭茂祖, 张彬, 赵玲玲, 张昱. 基于联合特征和XGBoost的活动语义识别方法[J]. 计算机应用, 2020, 40(11): 3159-3165.

GUO Maozu, ZHANG Bin, ZHAO Lingling, ZHANG Yu. Activity semantic recognition method based on joint features and XGBoost[J]. Journal of Computer Applications, 2020, 40(11): 3159-3165.

参考文献

[1] CHO E,MYERS S A,LESKOVEC J. Friendship and mobility:user movement in location-based social networks[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2011:1082-1090.
[2] LIAN D,XIE X,ZHENG V W,et al. CEPR:a collaborative exploration and periodically returning model for location prediction[J]. ACM Transactions on Intelligent Systems and Technology, 2015,6(1):No. 8.
[3] YE J,ZHU Z,CHENG H. What's your next move:user activity prediction in location-based social networks[C]//Proceedings of the 2013 Society for Industrial and Applied Mathematics International Conference on Data Mining. Philadelphia, PA:SIAM, 2013:171-179.
[4] WANG Y,YUAN N J,LIAN D,et al. Regularity and conformity:location prediction using heterogeneous mobility data[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2015:1275-1284.
[5] YUAN N J,ZHENG Y,XIE X,et al. Discovering urban functional zones using latent activity trajectories[J]. IEEE Transactions on Knowledge and Data Engineering,2015,27(3):712-725.
[6] PAN G,QI G,WU Z,et al. Land-use classification using taxi GPS traces[J]. IEEE Transactions on Intelligent Transportation Systems,2013,14(1):113-123.
[7] CHENG C,YANG H,LYU M R,et al. Where you like to go next:successive point-of-interest recommendation[C]//Proceedings of the 23rd International Joint Conference on Artificial Intelligence. Palo Alto,CA:AAAI Press,2013:2605-2611.
[8] ZHANG J D,CHOW C Y. Spatiotemporal sequential influence modeling for location recommendations:a gravity-based approach[J]. ACM Transactions on Intelligent Systems and Technology, 2015,7(1):No. 11.
[9] ZAREZADE A,JAFARZADEH S,RABIEE H R. Spatio-temporal modeling of users'check-ins in location-based social networks[EB/OL].[2019-12-22]. https://arxiv.org/pdf/1611.07710.pdf.
[10] LI Z,WANG J,HAN J. Mining event periodicity from incomplete observations[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2012:444-452.
[11] RIZWAN M, WAN W, GWIAZDZINSKI L. Visualization, spatiotemporal patterns,and directional analysis of urban activities using geolocation data extracted from LBSN[J]. ISPRS International Journal of Geo-Information,2020,9(2):No. 137.
[12] RIZWAN M,WAN W,CERVANTES O,et al. Using locationbased social media data to observe check-in behavior and gender difference:bringing Weibo data into play[J]. ISPRS International Journal of Geo-Information,2018,7(5):No. 196.
[13] YING J J C,LEE W C,WENG T C,et al. Semantic trajectory mining for location prediction[C]//Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM,2011:34-43.
[14] CHEN C C,KUO C H,PENG W C. Mining spatial-temporal semantic trajectory patterns from raw trajectories[C]//Proceedings of the 2015 IEEE International Conference on Data Mining Workshop. Piscataway:IEEE,2015:1019-1024.
[15] REDONDO R P D,GARCIA-RUBIO C,VILAS A F,et al. A hybrid analysis of LBSN data to early detect anomalies in crowd dynamics[J]. Future Generation Computer Systems,2020,109:83-94.
[16] CAO K, GUO J, MENG G, et al. Points-of-interest recommendation algorithm based on LBSN in edgecomputing environment[J]. IEEE Access,2020,8:47973-47983.
[17] ZHONG H,LYU H,ZHANG S,et al. Measuring user similarity using check-ins from LBSN:a mobile recommendation approach for e-commerce and security services[J]. Enterprise Information Systems,2020,14(3):368-387.
[18] SAKKARI M,ALGARNI A D,ZAIED M. Urban crowd detection using SOM, DBSCAN and LBSN data entropy:a Twitter experiment in New York and Madrid[J]. Electronics,2019,8(6):No. 692.
[19] COELHO DA SILVA T L,ZEITOUNI K,DE MACÊDO J A F,et al. A framework for online mobility pattern discovery from trajectory data streams[C]//Proceedings of the 17th IEEE International Conference on Mobile Data Management. Piscataway:IEEE,2016:365-368.
[20] LIAO D,ZHONG Y,LI J. Location prediction through activity purpose:integrating temporal and sequential models[C]//Proceedings of the 2017 Pacific-Asia Conference on Knowledge Discovery and Data Mining, LNCS 10234. Cham:Springer, 2017:711-723.
[21] LV M,CHEN L,XU Z,et al. The discovery of personally semantic places based on trajectory data mining[J]. Neurocomputing,2016,173(Pt 3):1142-1153.
[22] 邓尧, 冀汶莉, 李勇军, 等. 基于LBSN用户生成短文本的细粒度位置推测技术[J]. 计算机科学,2019,46(10):316-321. (DENG Y,JI W L,LI Y J,et al. Fine-grained geolocalisation of user generated short text based on LBSN[J]. Computer Science, 2019,46(10):316-321.)
[23] FU C,MCKENZIE G,FRIAS-MARTINEZ V,et al. Identifying spatiotemporal urban activities through linguistic signatures[J]. Computers,Environment and Urban Systems,2018,72:25-37.
[24] CHEN T, GUESTRIN C. XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2016:785-794.
[25] YANG D,ZHANG D,ZHENG V W,et al. Modeling user activity preference by leveraging user spatial temporal characteristics in LBSNs[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems,2015,45(1):129-142.
[26] 廖东亮. 基于语义时空数据的人类移动性预测[D]. 合肥:中国科学技术大学,2019:13-93.(LIAO D L. Human mobility prediction based on semantics spatial temporal data[J]. Hefei:University of Science and Technology of China,2019:13-93.)
[27] 陆锋, 刘康, 陈洁. 大数据时代的人类移动性研究[J]. 地球信息科学学报,2014,16(5):665-672.(LU F,LIU K,CHEN J. Research on human mobility in big data era[J]. Journal of GeoInformation Science,2014,16(5):665-672.)
[28] 姚迪, 张超, 黄建辉, 等. 时空数据语义理解:技术与应用[J]. 软件学报,2018,29(7):2018-2045.(YAO D,ZHANG C, HUANG J H,et al. Semantic understanding of spatio-temporal data:technology and application[J]. Journal of Software,2018, 29(7):2018-2045.)
[29] 李德仁. 论时空大数据的智能处理与服务[J]. 地球信息科学学报,2019,21(12):1825-1831.(LI D R. The intelligent processing and service of spatiotemporal big data[J]. Journal of Geo-Information Science,2019,21(12):1825-1831.)

基于联合特征和XGBoost的活动语义识别方法

Activity semantic recognition method based on joint features and XGBoost

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

[1]	刘世泽, 秦艳君, 王晨星, 苏琳, 柯其学, 罗海勇, 孙艺, 王宝会. 基于深度残差长短记忆网络交通流量预测算法[J]. 计算机应用, 2021, 41(6): 1566-1572.
[2]	刘向宇, 夏国平, 夏秀峰, 宗传玉, 朱睿, 李佳佳. 个性化时空数据隐私保护[J]. 计算机应用, 2021, 41(3): 643-650.
[3]	刘黎, 胡海波, 杨涛. 探索会展环境时空数据的可视分析系统[J]. 计算机应用, 2020, 40(9): 2719-2727.
[4]	樊仲欣. 基于数据流的聚类趋势分析算法[J]. 计算机应用, 2020, 40(8): 2248-2254.
[5]	黄伟建, 李丹阳, 黄远. 面向空气质量的时空混合预测模型[J]. 计算机应用, 2020, 40(11): 3385-3392.
[6]	丁景全, 马博, 李晓. 基于融合时空数据的车辆加油行为多视图深度异常检测框架[J]. 计算机应用, 2019, 39(11): 3370-3375.
[7]	王雪菲, 丁维龙. 面向高速公路大数据的短时流量预测方法[J]. 计算机应用, 2019, 39(1): 87-92.
[8]	侯海耀, 钱育蓉, 英昌甜, 张晗, 卢学远, 赵燚. 基于Hilbert-R树分级索引的时空查询算法[J]. 计算机应用, 2018, 38(10): 2869-2874.
[9]	陈煜, 蒋伟, 周继恩. 基于预测模型的轨迹数据压缩方法[J]. 计算机应用, 2018, 38(1): 171-175.
[10]	徐晓伟, 杜一, 周园春. 基于多源出行数据的居民行为模式分析方法[J]. 计算机应用, 2017, 37(8): 2362-2367.
[11]	罗建平邬群勇朱莉. 面向对象的全时域移动对象数据模型[J]. 计算机应用, 2013, 33(04): 1015-1017.
[12]	吕国华;刘兆宏;袁正午;葛君伟；裴海英. 时空数据库中移动对象查询的选择性估算[J]. 计算机应用, 2005, 25(11): 2632-2634.