基于ACP方法的平行手机信令数据分析系统

王迎春; 韩双双; 胡成云; 宋瑞琦; 要婷婷; 曹东璞; 王飞跃

doi:10.16383/j.aas.2018.c170156

基于ACP方法的平行手机信令数据分析系统

doi: 10.16383/j.aas.2018.c170156

王迎春^1,2,,
韩双双^1,2, ,,
胡成云^1,2,3,,
宋瑞琦^1,2,3,,
要婷婷^1,2,3,,
曹东璞^2,4,,
王飞跃^1,5,

1.
中国科学院自动化研究所复杂系统管理与控制国家重点实验室北京 100190 中国
2.
青岛智能产业技术研究院青岛 266000 中国
3.
青岛慧拓智能机器有限公司青岛 266000 中国
4.
英国克兰菲尔德大学驾驶员认知与自动驾驶实验室克兰菲尔德 MK43 0AL 英国
5.
国防科学技术大学军事计算实验与平行系统技术研究中心长沙 410073 中国

基金项目:

国家自然科学基金 61533019

国家自然科学基金 71232006

国家自然科学基金 61501461

详细信息

作者简介:
王迎春  中国科学院自动化研究所复杂系统管理与控制国家重点实验室工程师.2015年获得北京大学智能科学与技术硕士学位.主要研究方向为平行驾驶, 数据挖掘, 机器学习.E-mail:yingchun.wang@ia.ac.cn

胡成云  中国科学院自动化研究所复杂系统管理与控制国家重点实验室工程师.2016年获得北京大学电子与通信工程硕士学位.主要研究方向为自动驾驶, 平行测试.E-mail:chengyun.hu@ia.ac.cn

宋瑞琦中国科学院自动化研究所复杂系统管理与控制国家重点实验室工程师.2016年获得北京航空航天大学电子科学与技术工学硕士学位.主要研究方向为平行驾驶, 目标识别与语义分割.E-mail:ruiqi.song@ia.ac.cn

要婷婷  中国科学院自动化研究所复杂系统管理与控制国家重点实验室工程师.2015年、2016年分别获得英国伯明翰大学、北京交通大学硕士学位.主要研究方向为平行驾驶与数据挖掘.E-mail:tingting.yao@ia.ac.cn

曹东璞  英国克兰菲尔德大学驾驶员认知与自动驾驶实验室主任.中科院自动化所客座研究员.主要研究方向为自动驾驶, 人车协同, 与平行驾驶.E-mail:d.cao@cranfield.ac.uk

王飞跃  中国科学院自动化研究所复杂系统管理与控制国家重点实验室研究员.国防科学技术大学军事计算实验与平行系统技术研究中心教授.主要研究方向为智能系统和复杂系统的建模、分析与控制.E-mail:feiyue.wang@ia.ac.cn

通讯作者:
韩双双中国科学院自动化研究所复杂系统管理与控制国家重点实验室助理研究员.2013年获得加拿大阿尔伯塔大学博士学位.主要研究方向为平行网络, 物联网, 智能交通, 无线通信关键技术.本文通信作者.E-mail:shuangshuang.han@ia.ac.cn

计量
- 文章访问数: 2302
- HTML全文浏览量: 308
- PDF下载量: 505
- 被引次数: 0
出版历程
- 收稿日期: 2017-03-23
- 录用日期: 2017-11-06
- 刊出日期: 2019-05-20

Mobile Phone Signaling Data Analysis System Based on ACP Approach

WANG Ying-Chun^{1,2
,},
HAN Shuang-Shuang^{1,2
, ,},
HU Cheng-Yun^{1,2,3
,},
SONG Rui-Qi^{1,2,3
,},
YAO Ting-Ting^{1,2,3
,},
CAO Dong-Pu^{2,4
,},
WANG Fei-Yue^{1,5
,}

1.
The State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.
Qingdao Academy of Intelligent Industries, Qingdao 266000, China
3.
Qingdao Huituo Intelligent Machine Company, Qingdao 266000, China
4.
Driver Cognition and Automated Driving Laboratory, Cranfield University, Cranfield MK43 0AL, UK
5.
Research Center for Computational Experiments and Parallel Systems Technology, National University of Defense Technology, Changsha 410073, China

Funds:

National Natural Science Foundation of China 61533019

National Natural Science Foundation of China 71232006

National Natural Science Foundation of China 61501461

More Information

Author Bio:
Engineer at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. She received her master degree in intelligent science and technology from Peking University in 2015. Her research interest covers parallel driving, data mining, and machine learning

Engineer at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. He received his master degree in electronics and communication engineering from Peking University in 2016. His research interest covers automated driving and parallel testing

Engineer at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. He received his master degree in electronic science and technology from Beihang University in 2016. His research interest covers automated driving, target recognition, and semantic segmentation

Engineer at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. She received her master degrees from University of Birmingham and Beijing Jiaotong University in 2015 and 2016, respectively. Her research interest covers parallel driving and data mining

Director of Driver Cognition and Automated Driving Laboratory, Cranfleld University, UK. Visiting professor at Institute of Automation, Chinese Academy of Sciences. His research interest covers automated driving, driver-automation collaboration, and parallel driving

Professor at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. Professor at the Research Center for Computational Experiments and Parallel Systems Technology, National University of Defense Technology. His research interest covers modeling, analysis, and control of intelligent systems and complex systems

Corresponding author: HAN Shuang-Shuang Assistant professor at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. She received her Ph. D. degree from University of Alberta, Canada in 2013. Her research interest covers parallel networks, internet of things, intelligent transportation system and wireless communications. Corresponding author of this paper

摘要

摘要: 随着交通拥堵和公共安全问题的日趋严重，传统方案在道路监测和区域监测方面不仅成本高，准确性和可靠性也无法保证，因此无法给用户提供一整套综合全面的出行路线规划及旅游目的地选择等方面的相关指导.本文提出基于ACP方法的平行手机信令数据分析系统，将解决上述问题.本文主要基于ACP方法，包括人工社会、计算实验和平行执行，构建基于手机信令的人工监控场景和实际监控场景.实际监控场景和人工监控场景平行执行，人工监控场景用来模拟和实验复杂的实际监控场景，通过大量计算实验，进行各种模型的训练与评估，通过平行执行不断地更新和优化，实时指导实际监控场景；同时实际监控场景将结果反馈给人工监控场景，对人工监控场景模型进行修正.通过实际监控场景和人工监控场景之间的不断优化，可有效提高手机信令系统的实时性、准确性和可靠性，并最终满足不断增长的实时用户需求，保证用户出行的舒适性及安全性.
- 平行方法 /
- 手机信令 /
- 道路监控 /
- 区域人流监控
Abstract: The issue of traffic congestion and public security is becoming more and more important. Traditional solutions are not only high cost in terms of road monitoring and regional monitoring, but also the accuracy and reliability can not be guaranteed. Thus, the traditional solutions can not provide users comprehensive guidance about the travel route planning and travel destination selection and other related guidance. This paper proposes a mobile phone signaling data analysis system based on the ACP approach to solve the aforementioned problems. The ACP approach includes artificial society, computational experiments and parallel execution which build artificial monitoring scene and actual monitoring scene based on mobile phone signaling. The actual monitoring scene and artificial monitoring scene are executed in parallel. Artificial monitoring scene is used to simulate and test the complex actual monitoring scene. Through a large number of computational experiments, various models are trained and evaluated; Artificial monitoring scene constantly updates, optimizes and guides the actual monitoring scene through parallel execution; The actual monitoring scene will feedback the results to the artificial monitoring scene, thus artificial monitoring scene model is continuously amended. The continuous optimization between the actual monitoring scene and artificial monitoring scene can effectively improves the real-time efficiency, accuracy and reliability of the mobile phone signaling system. The proposed system would meet the requirements of ever-increasing real-time, and ensure the comfort and safety for the travel of the users.
- ACP method /
- mobile phone signaling /
- road condition monitoring /
- regional flow monitoring
注释:

1) 本文责任编委张敏灵

HTML全文

图 1 基于ACP方法的平行手机信令数据分析系统的框架

Fig. 1 The framework of mobile phone signaling data analysis system based on ACP approach

下载: 全尺寸图片幻灯片

图 2 人工监控场景框架

Fig. 2 The framework of manual monitoring scene

下载: 全尺寸图片幻灯片

图 3 道路监控预测方法

Fig. 3 The method of road monitoring and forecasting

下载: 全尺寸图片幻灯片

图 4 登录界面

Fig. 4 System login interface

下载: 全尺寸图片幻灯片

图 5 交通流监控

Fig. 5 The traffic flow monitoring

下载: 全尺寸图片幻灯片

图 6 重点区域人流密度

Fig. 6 The distribution of population flow in focused area

下载: 全尺寸图片幻灯片

图 7 用户的归属地分析

Fig. 7 The attribution of population flow in focused area

下载: 全尺寸图片幻灯片

图 8 进出重点区域人数

Fig. 8 The in/out number of population in focused area

下载: 全尺寸图片幻灯片

图 9 平行与非平行手机信令数据系统定量分析结果

Fig. 9 Quantitative analysis of parallel and general parallel mobile signaling data system

下载: 全尺寸图片幻灯片

表 1 手机信令数据格式

Table 1 The structure of mobile phone signaling data

字段名称	描述	类型
标识号	唯一标识, 随机生成	TEXT, 加密
TimeStamp	时间戳	UINT32类型数字
LAC	位置区编号	UINT32类型数字
E	经度	UINT32类型数字
N	纬度	UINT32类型数字
EventID	事件类型	UINT8类型数字
号码归属地编码	号码归属地信息(省+市)	字符串数据类型(省-市)
Type	基站类型0, 1	UINT32类型数字

下载: 导出CSV

表 2 道路基站与用户路径基站匹配表

Table 2 Mactching between base stations of road and user

Linkname	Roadpoint	Usertrajectory	Match
link-01	(120.346277, 36.231411)	(120.341874, 36.241635)	link-01
$\cdots$	$\cdots$	(120.291309, 36.236508)	link-02
	(120.160276, 36.243413)	(120.280959, 36.235056)	link-02
	(120.152630, 36.234506)	(120.239843, 36.231848)	link-03
	(120.145490, 36.246401)	(120.239456, 36.231008)	link-03
	(120.136701, 36.239830)	(120.178939, 36.241566)	link-03
	(120.123239, 36.235142)	(120.160276, 36.243413)	link-04
	(120.072134, 36.222112)	(120.136701, 36.239830)	link-04
link-05	(120.072091, 36.215935)	(120.123239, 36.235142)	link-04
$\cdots$	$\cdots$	(120.072134, 36.222112)	link-04
$\cdots$	$\cdots$	(120.064562, 36.232949)	no
link-06	(120.105853, 36.076972)	(120.061622, 36.237668)	no

下载: 导出CSV

参考文献(32)

[1]	杨兆升.基础交通信息融合技术及其应用.北京:中国铁道出版社, 2005. Yang Zhao-Sheng. Basic Traffic Information Fusion Technology and Its Application. Beijing:China Railway Publishing House, 2005.
[2]	Xia M, Chen Y H, Huang H C, Wang X Y, Chen Y F. Environment-adaptive road traffic measurement with single wireless geomagnetic sensor node. In:Proceedings of the International Conference on Wireless Communication and Sensor Network (WCSN 2015). Changsha, China:World Scientific, 2016. 720-727
[3]	何兆成, 卢瑞琪, 聂佩林.基于浮动车定位数据的高速公路区间平均速度估计.公路交通科技, 2011, 28(6):128-135 doi: 10.3969/j.issn.1002-0268.2011.06.021 He Zhao-Cheng, Lu Rui-Qi, Nie Pei-Lin. Estimation on freeway segment average speed based on probe vehicle data. Journal of Highway and Transportation Research and Development, 2011, 28(6):128-135 doi: 10.3969/j.issn.1002-0268.2011.06.021
[4]	刘俏.基于浮动车技术的城市道路网状况研究[硕士学位论文], 武汉理工大学, 中国, 2013. Liu Qiao. Studies on the condition of urban road networks based on floating car technology[Master dissertation], Wuhan University of Technology, China, 2013.
[5]	曹艺华.面向视频监控的大尺度人群行为分析[硕士学位论文], 上海交通大学, 中国, 2013. Cao Yi-Hua. The large-scale crowd analysis in video surveillance[Master dissertation], Shanghai Jiao Tong University, China, 2013.
[6]	肖坦, 杨栩, 李黄煌.基于视频监控的铁路客运站人群密度分析算法.铁道通信信号, 2010, 46(8):80-82 doi: 10.3969/j.issn.1000-7458.2010.08.029 Xiao Tan, Yang Xu, Li Huang-Huang. Railway passenger station crowd density estimation algorithm based video surveillance. Railway Signalling & Communication, 2010, 46(8):80-82 doi: 10.3969/j.issn.1000-7458.2010.08.029
[7]	Casas O, López M, Quílez M, Martinez-Farre X, Hornero G, Rovira C, Pinilla M R, RamosP M, Borges B, Marques H, Girão S. Wireless sensor network for smart composting monitoring and control. Measurement, 2014, 47:483-495 doi: 10.1016/j.measurement.2013.09.026
[8]	郑建湖, 王明华.动态交通信息采集技术比较分析.交通标准化, 2009, (4):42-47 http://d.old.wanfangdata.com.cn/Periodical/jtbzh200904045 Zheng Jian-Hu, Wang Ming-Hua. Comparative analysis of collection technologies for dynamic traffic information. Transport Standardization, 2009, (4):42-47 http://d.old.wanfangdata.com.cn/Periodical/jtbzh200904045
[9]	李祖芬, 于雷, 高永, 吴亦政, 龚大鹏, 宋国华.基于手机信令定位数据的居民出行时空分布特征提取方法.交通运输研究, 2016, 2(1):51-57 http://d.old.wanfangdata.com.cn/Periodical/jtbzh201601008 Li Zu-Fen, Yu Lei, Gao Yong, Wu Yi-Zheng, Gong Da-Peng, Song Guo-Hua. Extraction method of temporal and spatial characteristics of residents' trips based on cellular signaling data. Transportation Standardization, 2016, 2(1):51-57 http://d.old.wanfangdata.com.cn/Periodical/jtbzh201601008
[10]	唐小勇, 周涛, 陆百川.基于手机信令的大范围人流移动分析.重庆交通大学学报(自然科学版), 2017, 36(1):82-87, 109 http://d.old.wanfangdata.com.cn/Periodical/cqjtxyxb201701015 Tang Xiao-Yong, Zhou Tao, Lu Bai-Chuan. Analysis of wide range population flow analysis based on mobile phone signaling. Journal of Chongqing Jiaotong University (Natural Science), 2017, 36(1):82-87, 109 http://d.old.wanfangdata.com.cn/Periodical/cqjtxyxb201701015
[11]	吴松, 雒江涛, 周云峰, 林举厅, 舒忠玲.基于移动网络信令数据的实时人流量统计方法.计算机应用研究, 2014, 31(3):776-779 doi: 10.3969/j.issn.1001-3695.2014.03.033 Wu Song, Luo Jiang-Tao, Zhou Yun-Feng, Lin Ju-Ting, Shu Zhong-Ling. Method of real-time traffic statistics using mobile network signaling. Application Research of Computers, 2014, 31(3):776-779 doi: 10.3969/j.issn.1001-3695.2014.03.033
[12]	Hellinga B, Fu L P, Takada H. Obtaining traveller information via mobile phone location referencing-challenges and opportunities. In: Proceedings of the Annual Conference of the Transportation Association of Canada. St. John's, Canada: National Academy of Sciences, 2003. 21-24
[13]	White J, Quick J, Philippou P. The use of mobile phone location data for traffic information. In: Proceedings of the 12th IEE International Conference on Road Transport Information and Control. London, UK: IEEE, 2004. 321-325
[14]	Rose G. Mobile phones as traffic probes:practices, prospects and issues. Transport Reviews, 2006, 26(3):275-291 doi: 10.1080/01441640500361108
[15]	Qiu Z J, Cheng P. State of the art and practice: cellular probe technology applied in advanced traveler information system. In: Transportation Research Board 86th Annual Meeting (TRB2007). Washington DC, USA: Transportation Research Board. 2007.
[16]	Caceres N, Wideberg J P, Benitez F G. Review of traffic data estimations extracted from cellular networks. IET Intelligent Transport Systems, 2008, 2(3):179-192 doi: 10.1049/iet-its:20080003
[17]	Valerio D. Road Traffic Information from Cellular Network Signaling, Technical Report FTW-TR-2009-003, Telecommunications Research Center Vienna, Austria, 2009.
[18]	郭晓妮.基于手机信令的交通流监测与出行信息服务系统.通讯世界, 2017, (14):157 doi: 10.3969/j.issn.1006-4222.2017.14.112 Guo Xiao-Ni. Traffic flow monitoring and travel information service system based on mobile phone signaling. Telecom World, 2017, (14):157 doi: 10.3969/j.issn.1006-4222.2017.14.112
[19]	陈欢.基于手机信令数据的人员出行特征跟踪调查.交通与运输, 2017, (S1):92-94, 98 http://d.old.wanfangdata.com.cn/Periodical/jtyys2017z1022 Chen Huan. Survey of pedestrian travel characteristics based on mobile phone signaling data. Traffic & Transportation, 2017, (S1):92-94, 98 http://d.old.wanfangdata.com.cn/Periodical/jtyys2017z1022
[20]	Wang F Y. Parallel control and management for intelligent transportation systems:concepts, architectures, and applications. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(3):630-638
[21]	王飞跃.平行系统方法与复杂系统的管理和控制.控制与决策, 2004, 19(5):485-489, 514 doi: 10.3321/j.issn:1001-0920.2004.05.002 Wang Fei-Yue. Parallel system methods for management and control of complex systems. Control and Decision, 2004, 19(5):485-489, 514 doi: 10.3321/j.issn:1001-0920.2004.05.002
[22]	王飞跃.人工社会、计算实验、平行系统——关于复杂社会经济系统计算研究的讨论.复杂系统与复杂性科学, 2004, 1(4):25-35 doi: 10.3969/j.issn.1672-3813.2004.04.002 Wang Fei-Yue. Artificial societies, computational experiments, and parallel systems:a discussion on computational theory of complex social-economic systems. Complex Systems and Complexity Science, 2004, 1(4):25-35 doi: 10.3969/j.issn.1672-3813.2004.04.002
[23]	王飞跃.计算实验方法与复杂系统行为分析和决策评估.系统仿真学报, 2004, 16(5):893-897 doi: 10.3969/j.issn.1004-731X.2004.05.009 Wang Fei-Yue. Computational experiments for behavior analysis and decision evaluation of complex systems. Journal of System Simulation, 2004, 16(5):893-897 doi: 10.3969/j.issn.1004-731X.2004.05.009
[24]	王飞跃.关于复杂系统研究的计算理论与方法.中国基础科学, 2004, 6(5):3-10 doi: 10.3969/j.issn.1009-2412.2004.05.001 Wang Fei-Yue. Computational theory and method on complex system. China Basic Science, 2004, 6(5):3-10 doi: 10.3969/j.issn.1009-2412.2004.05.001
[25]	Zhang N, Wang F Y, Zhu F H, Zhao D B, Tang S M. DynaCAS:computational experiments and decision support for ITS. IEEE Intelligent Systems, 2008, 23(6):19-23 doi: 10.1109/MIS.2008.101
[26]	王飞跃, 刘德荣, 熊刚, 程长建, 赵冬斌.复杂系统的平行控制理论及应用.复杂系统与复杂性科学, 2012, 9(3):1-12 doi: 10.3969/j.issn.1672-3813.2012.03.001 Wang Fei-Yue, Liu De-Rong, Xiong Gong, Cheng Chang-Jian, Zhao Dong-Bin. Parallel control theory of complex systems and applications. Complex Systems and Complexity Science, 2012, 9(3):1-12 doi: 10.3969/j.issn.1672-3813.2012.03.001
[27]	Wang F Y, Wang X, Li L X, Li L. Steps toward parallel intelligence. IEEE/CAA Journal of Automatica Sinica, 2016, 3(4):345-348 doi: 10.1109/JAS.2016.7510067
[28]	Wang F Y, Yang L Q, Cheng X, Han S S, Yang J. Network softwarization and parallel networks:beyond software-defined networks. IEEE Network, 2016, 30(4):60-65 doi: 10.1109/MNET.2016.7513865
[29]	王飞跃, 杨柳青, 胡晓娅, 程翔, 韩双双, 杨坚.平行网络与网络软件化:一种新颖的网络架构.中国科学:信息科学, 2017, 47(7):811-831 http://www.cnki.com.cn/Article/CJFDTOTAL-PZKX201707001.htm Wang Fei-Yue, Yang Liu-Qing, Hu Xiao-Ya, Cheng Xiang, Han Shuang-Shuang, Yang Jian. Parallel networks and network softwarization:a novel network architecture. Scientia Sinica (Informationis), 2017, 47(7):811-831 http://www.cnki.com.cn/Article/CJFDTOTAL-PZKX201707001.htm
[30]	李力, 林懿伦, 曹东璞, 郑南宁, 王飞跃.平行学习——机器学习的一个新型理论框架.自动化学报, 2017, 43(1):1-8 doi: 10.3969/j.issn.1003-8930.2017.01.001 Li Li, Lin Yi-Lun, Cao Dong-Pu, Zheng Nan-Ning, Wang Fei-Yue. Parallel learning——a new framework for machine learning. Acta Automatica Sinica, 2017, 43(1):1-8 doi: 10.3969/j.issn.1003-8930.2017.01.001
[31]	Lv Y S, Duan Y J, Kang W W, Li Z X, Wang F Y. Traffic flow prediction with big data:a deep learning approach. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2):865-873
[32]	Wen J, Zhao J L, Luo S W, Han Z. The improvements of BP neural network learning algorithm. In: Proceedings of the 5th International Conference on Signal Processing. Beijing, China: IEEE, 2000, 3: 1647-1649