摘 要:在位置预测研究中,历史轨迹通常呈现分布稀疏和结构单一的特点,导致预测模型准确率下降。针对此问题,利用用户属性特征和历史轨迹特征度量用户相似性,对相似用户进行分簇;并提出基于相似用户簇的LSTM 神经网络预测模型SG-LSTM(Similar Group based LSTM model),以改善轨迹数据的稀疏性问题。实验表明,模型能够较好地捕捉用户的移动规律,预测准确率超过87.90%,在准确率和时间复杂度方面均优于传统模型。
关键词:稀疏时空数据;用户相似性;LSTM;位置预测
中图分类号:TN92 文献标识码:A 文章编号:2096-4706(2020)24-0164-05
Location Prediction Based on Wi-Fi Spatiotemporal Data
ZHANG Shuqin,WANG Jinyang,BAI Guangyao,ZHANG Minzhi
(School of Computer Science,Zhongyuan University of Technology,Zhengzhou 450007,China)
Abstract:In the research of location prediction,historical trajectories usually show the characteristics of sparse distribution and single structure,which leads to a decline in the accuracy of the prediction model. To solve this problem,the similarity of users is measured by using user attribute characteristics and historical track characteristics,and similar users are clustered;and proposes similar user cluster based LSTM neural network prediction model SG-LSTM(Similar Group based LSTM model)to improve the sparsity of trajectory data. The experimental results show that the model can better capture the user’s movement rule,and the prediction accuracy is more than 87.90%,which is better than the traditional model in terms of accuracy and time complexity.
Keywords:sparse spatiotemporal data;user similarity;LSTM;location prediction
基金项目:河南省高校重点科研项目(18B520044,19A520048,21A520053); 河南省科技攻关项目(182102210526);河南省教育厅青年骨干教师项目(2017GGJS118)
参考文献:
[1] 徐彪,霍欢,陈尚也,等. 基于位置服务的轨迹预测方法 [J].小型微型计算机系统,2016,37(6):1191-1196.
[2] ALAHI A,GOEL K,RAMANATHAN V,et al. SocialLSTM:Human Trajectory Prediction in Crowded Spaces [C]//2016IEEE Conference on Computer Vision and Pattern Recognition( CVPR).Las Vegas:IEEE,2016:961-971.
[3] LEE N H,CHOI W,VERNAZA P,et al. DESIRE:DistantFuture Prediction in Dynamic Scenes with Interacting Agents [C]//2017IEEE Conference on Computer Vision and Pattern Recognition( CVPR).Honolulu:IEEE,2017:2165-2174.
[4] ZHENG Y,LIU Y C,YUAN J,et al. Urban Computing withTaxicabs [C]//Proceedings of the 13th ACM International Conference onUbiquitous Computing.Beijing:Ubicomp,2011:98-98.
[5] 孙未未,毛江云. 轨迹预测技术及其应用——从上海外滩踩踏事件说起 [J]. 科技导报,2016,34(9):48-54.
[6] 李寒露,解庆,唐伶俐,等. 融合时空信息和兴趣点重要性的POI 推荐算法 [J]. 计算机应用,2020,40(9):2600-2605.
[7] GIANNOTTI F,NANNI M,PINELLI F,et al. Trajectorypattern mining [C]//Proceedings of the 13th ACM SIGKDD internationalconference on Knowledge discovery and data mining.New York:Association for Computing Machinery,2007:330-339.
[8]GAMBS S,KILLIJIAN M,NUNEZ M. Next place prediction using mobility Markov chains [C]//EuroSys2012 Workshop on Measurement,Privacy,andMobility.New York:Association for Computing Machinery,2012:1-6.
[9] CHEN M,LIU Y,YU X. NLPMM:A Next LocationPredictor with Markov Modeling [C]//Pacific-Asia Conference onKnowledge Discovery and Data Mining.Cham:Springer,2014.
[10] MONREALE A,PINELLI F,TRASARTI R,et al.WhereNext:a location predictor on trajectory pattern mining [C]//The 15thACM SIGKDD International Conference on Knowledge Discovery and DataMining.New York:Association for Computing Machinery,2009:637-646.
[11] 高雅,江国华,秦小麟,等. 基于LSTM 的移动对象位置预测算法 [J]. 计算机科学与探索,2019,13(1):23-34.
作者简介:
张书钦(1978—),男,汉族,河南禹州人,副教授,博士后,主要研究方向:物联网、数据挖掘、网络攻防、无线网络;
王金洋(1995—),男,汉族,河南周口人,硕士研究生在读,主要研究方向:大数据挖掘、自然语言处理;
白光耀(1996—),男,回族,河南郑州人,硕士研究生在读,主要研究方向:物联网大数据;
张敏智(1998—),女,汉族,河南郑州人,硕士研究生在读,主要研究方向:物联网大数据。