基于潜在语义信息的城市功能区识别----广州市浮动车GPS时空数据挖掘

doi:10.11821/dlxb201603010

Abstract

Abstract:

China has been experiencing rapid urbanization at an unprecedented rate and as a result, urban internal space structure has evolved significantly. It is of great significance to label different functional regions (DFR) inside a city for urban structure analysis, policy making, and resource allocation. These DFRs include residential district, industrial district, education district, and the administration district. This paper explored the characteristics and distribution of urban functional regions based on big geographic data. With the latest road network data, the study area (i.e., 6 districts of Guangzhou city in Guangdong Province, China) was partitioned into 439 segments. By applying the employment of spatial and temporal semantic mining method to the one-week massive floating cars GPS data and the point of interest data, we developed a Latent Dirichlet Allocation (LDA) and Dirichlet Multinomial Regression (DMR) model. Moreover, OPTICS clustering method was employed to process the results of LDA and DMR to identify different functional zones. Meanwhile, status map of Guangzhou urban planning, and resident travel characteristics were used to verify the verification of mentioned results. The results show that this method can identify the obvious characteristics of urban functional areas, such as mature residential area, science and education culture area, commercial area, and development zone. The results also show that residential and commercial areas are dominant DFRs in Guangzhou city, which are surrounded by other types of functional regions. This paper brings a new perspective on using large-scale and high quality individual space-time data to study human migration and daily activities, as well as to explore social space to unveil the formation and mechanism of urban functional zones.

Key words: latent dirichlet allocation, functional regions, big geographic data, GPS data, point of interest, Guangzhou

Shili CHEN, Haiyan TAO, Xuliang LI, Li ZHUO. Discovering urban functional regions using latent semantic information: Spatiotemporal data mining of floating cars GPS data of Guangzhou[J].Acta Geographica Sinica, 2016, 71(3): 471-483.

Figures/Tables 10

Fig. 1

Tab. 1

Fig. 2

Fig. 3

Tab. 2

Overall POI density vector and ranking of functional zones (FD: Frequency Density, IR: Internal Ranking, F: Functional Zones)

POI类别	F0			F1		F2			F3		F4			F5			F6			F7			F8
POI类别	FD		IR		FD	IR		FD		IR	FD		IR		FD	IR	FD	IR	FD	IR	FD	IR	FD	IR
国际国外组织机构	0.0000	23		0.0008	26	0.0007	26		0.0005	28	0.0026	24		0.0000	27		0.0000	22		0.0000	25		0.0000	25
技术开发	0.0000	24		0.0035	23	0.0032	21		0.0025	21	0.0085	18		0.0022	22		0.0047	19		0.0002	23		0.0393	16
综合性大学	0.0000	25		0.0049	20	0.0054	19		0.0033	20	0.0060	21		0.0090	15		0.0000	23		0.0007	21		0.0187	19
综合医院	0.0000	26		0.0037	22	0.0004	28		0.0023	23	0.0012	25		0.0004	25		0.0000	24		0.0000	26		0.0075	23
广播电台	0.0005	22		0.0031	25	0.0015	23		0.0012	25	0.0028	23		0.0015	23		0.0000	25		0.0002	24		0.0019	24
会展中心	0.0000	27		0.0002	28	0.0011	25		0.0006	27	0.0002	29		0.0000	28		0.0000	26		0.0000	27		0.0000	26
博物馆	0.0000	28		0.0008	27	0.0007	27		0.0008	26	0.0005	27		0.0000	29		0.0000	27		0.0000	28		0.0000	27
体育机构各类场馆	0.0038	18		0.0167	17	0.0116	17		0.0113	16	0.0120	15		0.0071	16		0.0156	16		0.0035	16		0.0187	20
银行和保险服务	0.0213	9		0.1024	6	0.0827	7		0.0678	5	0.0857	5		0.0373	8		0.0779	6		0.0233	8		0.1758	5
农场林场,果场生产	0.0066	15		0.0035	24	0.0015	24		0.0025	22	0.0039	22		0.0052	17		0.0000	28		0.0009	19		0.0206	18
园艺销售	0.3623	1		0.0218	16	0.0187	16		0.0064	18	0.0068	19		0.0052	18		0.0125	17		0.0023	18		0.0094	21
电脑网络高新技术	0.0027	20		0.0599	8	0.0718	9		0.0601	7	0.2128	2		0.0523	6		0.0405	12		0.0042	15		1.2590	1
纺织服装生产厂	0.0776	5		0.4281	1	0.1597	3		0.0967	3	0.0772	7		0.1318	3		0.4798	1		0.2385	1		0.2469	4
化工原料及制品	0.0169	10		0.0586	9	0.0748	8		0.0292	13	0.0429	10		0.0358	9		0.0374	13		0.0138	11		0.0804	8
宾馆住宿	0.0098	12		0.0523	11	0.0600	10		0.0408	9	0.0538	9		0.0314	10		0.0561	8		0.0203	9		0.0692	10
酒吧,咖啡	0.1290	3		0.3013	2	0.2379	2		0.2183	1	0.2221	1		0.1736	1		0.2430	3		0.1342	3		0.3349	3
娱乐业	0.0098	13		0.0468	12	0.0506	11		0.0337	12	0.0386	12		0.0288	11		0.0607	7		0.0119	13		0.0561	13
旅游业	0.0087	14		0.0430	14	0.0444	13		0.0340	11	0.0319	13		0.0105	14		0.0421	11		0.0170	10		0.0486	14
自行车修理	0.0066	16		0.0041	21	0.0021	22		0.0017	24	0.0006	26		0.0015	24		0.0031	20		0.0007	22		0.0000	28
开发区	0.0000	29		0.0000	29	0.0000	29		0.0001	29	0.0003	28		0.0004	26		0.0000	29		0.0000	29		0.0000	29
商务办公楼	0.0038	19		0.0444	13	0.0491	12		0.0351	10	0.0423	11		0.0250	12		0.0436	10		0.0068	14		0.0823	7
大厦/写字楼	0.0011	21		0.0077	19	0.0066	18		0.0053	19	0.0092	17		0.0052	19		0.0171	15		0.0009	20		0.0094	22
住宅区	0.0317	7		0.2254	3	0.2521	1		0.1869	2	0.1646	4		0.1374	2		0.2196	4		0.0299	6		0.4284	2
布匹,服装辅料销售	0.0109	11		0.0985	7	0.0277	15		0.0272	15	0.0105	16		0.0045	21		0.0078	18		0.0128	12		0.0318	17
批发部	0.1366	2		0.1071	4	0.0842	6		0.0630	6	0.0833	6		0.0478	7		0.0467	9		0.0306	5		0.0786	9
商场商厦,购物中心	0.0240	8		0.0423	15	0.0334	14		0.0281	14	0.0253	14		0.0228	13		0.0327	14		0.0247	7		0.0599	11
物流仓储,速递运输	0.0322	6		0.0568	10	0.0864	5		0.0483	8	0.0558	8		0.0975	5		0.0872	5		0.1594	2		0.0861	6
车船修理,销售租赁	0.0853	4		0.1046	5	0.1080	4		0.0854	4	0.1992	3		0.1090	4		0.2664	2		0.0866	4		0.0599	12
道路附属	0.0060	17		0.0092	18	0.0049	20		0.0070	17	0.0068	20		0.0052	20		0.0016	21		0.0026	17		0.0412	15

Tab. 2

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Tab. 3

References 37

[1]	Li Dehua.Principles of Urban Planning. Beijing: China Architecture & Building Press, 2001.
	[李德华. 城市规划原理. 北京: 中国建筑工业出版社, 2001: 12]
[2]	Tian G, Wu J, Yang Z.Spatial pattern of urban functions in the Beijing metropolitan region. Habitat International, 2010, 34(2): 249-255. doi: 10.1016/j.habitatint.2009.09.010
[3]	Dou Zhi.Research on the spatial clustering algorithm for urban function zoning [D]. Chengdu: Sichuan Normal University, 2010.
	[窦智. 城市功能区划分空间聚类算法研究[D]. 成都: 四川师范大学, 2010.]
[4]	Li Xinyun.Research on methods and application for urban spatial data mining [D]. Taian: Shandong University of Science and Technology, 2004.
	[李新运. 城市空间数据挖掘方法与应用研究[D]. 泰安: 山东科技大学, 2004.]
[5]	Qu Guoqing, Jiang Yuchun.Cluster analysis and its application in land utilization classification. Resource Development & Market, 1999, 15(4): 4-7. doi: 10.3969/j.issn.1005-8141.1999.04.002
	[曲国庆, 姜玉春. 聚类分析及其在土地利用分类中的应用. 资源开发与市场, 1999, 15(4): 4-7.] doi: 10.3969/j.issn.1005-8141.1999.04.002
[6]	Shi Yufeng, Wang Yan.Study on urban function partition based on self-organizing neural network. Computer Engineering, 2006, 32(18): 206-207.
	[史玉峰, 王艳. 基于自组织神经网络的城市功能分区研究. 计算机工程, 2006, 32(18): 206-207.]
[7]	Wang Hui.Spatial impacts of new economies and the implications for city planning and decision-making. Geographical Research, 2007, 26(3): 577-589.
	[王慧. 城市"新经济"发展的空间效应及其启示: 以西安市为例. 地理研究, 2007, 26(3): 577-589.]
[8]	Wang Hui.Rise of new special development zones and polarization of socio-economic space in Xi'an. Acta Geographica Sinica, 2006, 61(10): 1011-1024.
	[王慧. 开发区发展与西安城市经济社会空间极化分异. 地理学报, 2006, 61(10): 1011-1024.]
[9]	Wang Hui, Tian Pingping, Liu Hong.Spatial structuring of the 'new economies' in Xi'an and its mechanisms. Geographical Research, 2006, 25(3): 539-550.
	[王慧, 田萍萍, 刘红. 西安城市"新经济"发展的空间特征及其机制. 地理研究, 2006, 25(3): 539-550.]
[10]	Wang Yan, Song Zhenbai, Wu Peilin.A study on spatial clustering of urban function partition. Areal Research and Development, 2009, 28(1): 27-31. doi: 10.3969/j.issn.1003-2363.2009.01.006
	[王艳, 宋振柏, 吴佩林. 城市功能分区的空间聚类方法研究及其应用: 以济南市为例. 地域研究与开发, 2009, 28(1): 27-31.] doi: 10.3969/j.issn.1003-2363.2009.01.006
[11]	Wu Wenheng, Xu Zewei, Yang Xinjun.Quantitative research of spatial development differentiation in Xi'an from the perspective of urban functional zoning. Geographical Research, 2012, 31(12): 2173-2184.
	[吴文恒, 徐泽伟, 杨新军. 功能分区视角下的西安市发展空间分异. 地理研究, 2012, 31(12): 2173-2184.]
[12]	Zhu Zhilin.Research on the urban function zoning divide based on fuzzy clustering. Dam and Safety, 2006(S): 28-31. doi: 10.3969/j.issn.1671-1092.2006.z1.011
	[朱枝琳. 基于模糊聚类的城市功能区划分研究. 大坝与安全, 2006(S): 28-31.] doi: 10.3969/j.issn.1671-1092.2006.z1.011
[13]	Joh C H, Hwang C A.Time-geographic analysis of trip trajectories and land use characteristics in Seoul metropolitan area by using multidimensional sequence alignment and spatial analysis. Washington, DC: AAG Annual Meeting, 2010.
[14]	Sun L, Lee D, Erath A, et al.Using smart card data to extract passenger's spatio-temporal density and train's trajectory of MRT system. Urban Computing, 2012: 142-148. doi: 10.1145/2346496.2346519
[15]	Zhong C, Huang X, Arisona S M, et al.Inferring building functions from a probabilistic model using public transportation data. Computers, Environment and Urban Systems, 2014, 48(6): 124-137. doi: 10.1016/j.compenvurbsys.2014.07.004
[16]	Qi G, Li X, Li S, et al.Measuring social functions of city regions from large-scale taxi behaviors. Pervasive Computing and Communications Workshops, 2011: 384-388. doi: 10.1109/PERCOMW.2011.5766912
[17]	Cranshaw J, Schwartz R, Hong J I.The livehoods project: utilizing social media to understand the dynamics of a city. ICWSM, 2012.
[18]	Gaubatz P. Changing Beijing. Geographical Review, 1995: 79-96. doi: 10.2307/215557
[19]	Kling F, Pozdnoukhov A.When a city tells a story: Urban topic analysis. Advances in Geographic Information Systems, 2012: 482-485. doi: 10.1145/2424321.2424395
[20]	Pozdnoukhov A, Kaiser C.Space-time dynamics of topics in streaming text. Location-based Social Networks, 2011: 1-8. doi: 10.1145/2063212.2063223
[21]	Yin Z, Cao L, Han J, et al.Geographical topic discovery and comparison. World Wide Web, 2011: 247-256. doi: 10.1145/1963405.1963443
[22]	Liu Y, Wang F, Xiao Y, et al.Urban land uses and traffic 'source-sink areas': Evidence from GPS-enabled taxi data in Shanghai. Landscape and Urban Planning, 2012, 106(1): 73-87. doi: 10.1016/j.landurbplan.2012.02.012
[23]	Pulliam H R.Sources, sinks, and population regulation. The American Naturalist, 1988, 132(5): 652-661. doi: 10.1086/284880
[24]	Yuan J, Zheng Y, Xie X.Discovering regions of different functions in a city using human mobility and POIs. Knowledge Discovery and Data Mining, 2012: 186-194.
[25]	Dong Xiaojing, Yu Zhiwei, Fu Weiwei.Data processing and analyzing system for bus IC card based on GIS. Geospatial Information, 2009, 7(5): 124-126. doi: 10.3969/j.issn.1672-4623.2009.05.039
	[董晓晶, 余志伟, 伏伟伟. 基于GIS的公交IC卡数据处理及分析系统. 地理空间信息, 2009, 7(5): 124-126.] doi: 10.3969/j.issn.1672-4623.2009.05.039
[26]	Gao Lianxiong, Wu Jianping.An algorithm for mining passenger flow information from smart card data. Journal of Beijing University of Posts and Telecommunications, 2011, 34(3): 94-97. doi: 10.3969/j.issn.1007-5321.2011.03.021
	[高联雄, 吴建平. 从智能卡数据挖掘客流信息的算法. 北京邮电大学学报, 2011, 34(3): 94-97.] doi: 10.3969/j.issn.1007-5321.2011.03.021
[27]	Long Ying, Zhang Yu, Cui Chengyin.Identifying commuting pattern of Beijing using bus smart card data. Acta Geographica Sinica, 2012, 67(10): 1339-1352.
	[龙瀛, 张宇, 崔承印. 利用公交刷卡数据分析北京职住关系和通勤出行. 地理学报, 2012, 67(10): 1339-1352.]
[28]	Ni Zhongyun, Lei Fanggui, Yang Wunian.Application of google earth in Chengdu functional zoning. Scientific and Technological Management of Land and Resources, 2007, 24(4): 121-124. doi: 10.3969/j.issn.1009-4210.2007.04.027
	[倪忠云, 雷方贵, 杨武年. Google Earth在成都市功能分区研究中的应用. 国土资源科技管理, 2007, 24(4): 121-124.] doi: 10.3969/j.issn.1009-4210.2007.04.027
[29]	Yu Xiang.Discovering zones of different functions using bus smart card data and points of interest: A case study of Beijing [D]. Hangzhou: Zhejiang University, 2014.
	[于翔. 基于城市公交刷卡数据和兴趣点的城市功能区识别研究[D]. 杭州: 浙江大学, 2014.]
[30]	Zhang Yu, Hu Xinhua.A detection method of expressway traffic congestion with probe car data. Journal of Transport Information & Safety, 2012, 30(6): 87-89. doi: 10.3963/j.issn1674-4861.2012.06.018
	[章玉, 胡兴华. 基于IC卡数据的居民公交乘车距离研究. 交通信息与安全, 2012, 30(6): 87-89.] doi: 10.3963/j.issn1674-4861.2012.06.018
[31]	Liu Y, Liu X, Gao S.Social sensing: A new approach to understanding our socioeconomic environments. Annals of the Association of American Geographers, 2015, 105(3): 1-19. doi: 10.1080/00045608.2015.1018773
[32]	Blei D M, Ng A Y, Jordan M I.Latent dirichlet allocation. The Journal of Machine Learning Research, 2003, 3: 993-1022. doi: 10.1109/MLSP.2011.6064562
[33]	Wei X, Croft W B.LDA-based document models for ad-hoc retrieval. Research and Development in Information Retrieval, 2006: 178-185. doi: 10.1145/1148170.1148204
[34]	Li Wenbo, Sun Le, Zhang Dakun.Text classification based on labeled-LDA model. Chinese Journal of Computers, 2008, 31(4): 620-627. doi: 10.3321/j.issn:0254-4164.2008.04.008
	[李文波, 孙乐, 张大鲲. 基于Labeled-LDA模型的文本分类新算法. 计算机学报, 2008, 31(4):620-627.] doi: 10.3321/j.issn:0254-4164.2008.04.008
[35]	Karlsson C.Clusters, functional regions and cluster policies. IBS and CESIS Electronic Working Paper Series, 2007, 84:1-24.
[36]	Mimno D M A. Topic models conditioned on arbitrary features with dirichlet-multinomial regression. ArXiv Preprint ArXiv,1206.3278, 2012.
[37]

数据	年份	数量	详细说明
广州市区划图	2014年		选取广州市白云区,海珠区,黄浦区,越秀区,荔湾区以及天河区为研究对象
道路网络数据	2014年	1028条	选取高速公路,快速路,国道,省道,城市主干道及城市次干道的道路功能等级为道路分割对象
兴趣点数据	2014年	182504个	研究对象范围内的所有兴趣点
浮动车轨迹数据	2013年	2万辆(1.315亿条)	选取研究对象范围内的所有GPS点并提取其OD点对进行分析
居民出行调查问卷	2013年	1152份	调查问卷的对象,时间,主题

对照区域	中国进出口商品交易会展馆(广交会展馆)
对照图
识别结果	识别图中A区域(深红色)为文化区与现状图A区域相一致
对照区域	五山区是高校(老教学区)云集地,包含华南理工,华南农业,华南师范,暨南大学等均在此有校区,是广州市的科教文化区
对照图
识别结果	B区域在百度地图中为科教区与识别图中的B区域(粉色)相互对应
对照区域	亚洲单体建筑面积最大的现代化纺织品批发市场----广州国际轻纺城
对照图
识别结果	百度地图中的F区域即用红色圈标出的区域和识别图中的F区域相一致

Discovering urban functional regions using latent semantic information: Spatiotemporal data mining of floating cars GPS data of Guangzhou

RichHTML

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

Figures/Tables 10

References 37

Related Articles 15

Metrics

Comments

[1]	CHEN Xiang, SUN Wu, SHEN Zitong, ZHU Linlin, ZHANG Jiabin, XU Wei. Characteristics of ventilation channel and ventilation efficiency assessment: A case study of main built-up area in Guangzhou [J]. Acta Geographica Sinica, 2021, 76(3): 694-712.
[2]	PENG Shiyao, CHEN Shaokuan, XU Qi, NIU Jiaqi. Spatial characteristics of land use based on POI and urban rail transit passenger flow [J]. Acta Geographica Sinica, 2021, 76(2): 459-470.
[3]	AN Ning,FENG Qiuyi,ZHU Hong. The spatial imagination of Guangzhou's African community: Analysis based on newspaper discourses [J]. Acta Geographica Sinica, 2019, 74(8): 1650-1662.
[4]	TU Jianjun,TANG Siqi,ZHANG Qian,WU Yue,LUO Yunchao. Spatial heterogeneity of the effects of mountainous city patternon catering industry location [J]. Acta Geographica Sinica, 2019, 74(6): 1163-1177.
[5]	Rongping LIN, Suhong ZHOU, Xiaopei YAN. Intergenerational differences of spatio-temporal characteristics and influencing factors of home-work location changes since 1978: Empirical analysis based on the micro-survey in Guangzhou, China [J]. Acta Geographica Sinica, 2019, 74(4): 753-769.
[6]	XU Zhihua,LIU Kaizhi. State rescaling of the urban development in Hong Kong after the reunification: A case study of the planning process of the Hong Kong section of the Guangzhou-Shenzhen-Hong Kong Express Rail Link [J]. Acta Geographica Sinica, 2019, 74(2): 253-265.
[7]	YANG Ying,LIN Lin,ZHONG Zhiping,OU Yingying,XU Qian,MENG Meiyun,HAO Shan. Comprehensive evaluation and spatial differentiation of community resilience in Guangzhou based on response of the city to public health hazards [J]. Acta Geographica Sinica, 2019, 74(2): 266-284.
[8]	WU Rong,HUANG Xu,LIU Ye,LI Zhigang. Place attachment of urbanites in Guangzhou: Measurement and mechanism [J]. Acta Geographica Sinica, 2019, 74(2): 379-393.
[9]	YANG Wenyue,CAO Xiaoshu. The influence mechanism of travel-related CO₂ emissions from the perspective of residential self-selection: A case study of Guangzhou [J]. Acta Geographica Sinica, 2018, 73(2): 346-361.
[10]	CHEN Chun,YUAN Zhenjie,ZHU Hong. Floating children in Guangzhou: The construction of "home" in the context of urbanization [J]. Acta Geographica Sinica, 2018, 73(12): 2440-2451.
[11]	Suhong ZHOU, Jiangyu SONG, Guangwen SONG. Examining the dual-levels impact of neighbourhood and individual variables on car use on weekdays in Guangzhou [J]. Acta Geographica Sinica, 2017, 72(8): 1444-1457.
[12]	Zhangzhi TAN, Shaoyin LI, Xia LI, Xiaoping LIU, Yimin CHEN, Weixian LI. Spatio-temporal effects of urban rail transit on complex land-use change [J]. Acta Geographica Sinica, 2017, 72(5): 850-862.
[13]	Chenhao FU, Suhong ZHOU, Xiaopei YAN, Lin LIU, Weishan CHEN. Spatio-temporal characteristics and influencing factors of consumer behavior in retailing centers: A case study of Guangzhou in Guangdong Province [J]. Acta Geographica Sinica, 2017, 72(4): 603-617.
[14]	Wei TAO, Shaoxu WANG, Hong ZHU. Scavengers' bodily practices and spatial construction in Guangzhou [J]. Acta Geographica Sinica, 2017, 72(12): 2199-2213.
[15]	Haiyan TAO, Zhongzhe PAN, Maolin PAN, Li ZHUO, Yong XU, Miao LU. Mixing spatial-temporal transmission patterns of metropolis dengue fever: A case study of Guangzhou, China [J]. Acta Geographica Sinica, 2016, 71(9): 1653-1662.