Urban Adaptive Travel Hotspot Detection and Area Division Method
-
摘要: 针对固定带宽热点识别在多密度出行数据中的适应性不足，以及传统区域划分方法引发的空间异质性表达失真问题，本文提出了1种面向城市交通的自适应热点探测与动态区域划分方法。构建自适应出行密度估计模型，通过先导估计确定全局初始带宽，结合最大似然估计标定敏感性参数，并引入局部带宽修正系数和动态带宽调整机制，实现研究带宽的自动调节。开发多级热点识别技术，采用移动窗口极值检测与自然断裂分级相结合策略，构建出行热点评价体系。以热点为控制点生成泰森多边形作为基本分析单元，保持空间异质性特征，结合出行热度、莫兰指数等五类指标评估区域划分效果。以哈尔滨主城区出租车轨迹数据为样本进行实证，结果显示：较固定带宽方法，本方法热点识别数量提升2.1~6.7倍，区域热度差异标准差达572.8；面要素内点数据平均中心与重心距离为137.8 m，较传统栅格方法减少15.1%~74.3%，验证了区域划分的均质性优势；块金基台比降低至0.135，单元内部变异度减少39.6%，表明其能有效保留数据聚集特征并降低可塑性面积单元问题影响；自适应方法在研究区域内共得到了1 719个出行热点，在哈尔滨西站等区域精准定位路网交叉口热点，边界清晰且地理语义明确。研究结果为多密度出行数据分析提供了自适应框架，可支持出租车调度、需求预测等应用场景。Abstract: To address the limitations of fixed bandwidth hotspot detection in multi-density travel data and the spatial heterogeneity distortion from traditional zoning methods, this study proposes an adaptive hotspot detection and dy-namic regional division method for urban transportation. An adaptive travel density estimation model is developed. A global initial bandwidth is determined via pilot estimation, and sensitivity parameters are calibrated using maxi-mum likelihood estimation. Local bandwidth correction factors and a dynamic bandwidth adjustment mechanism en-able automatic research bandwidth regulation. A multilevel hotspot identification technology is developed, combin-ing moving window extreme value detection with natural breaks classification to form a travel hotspot evaluation system. Furthermore, Voronoi polygons are generated using the hotspots as control points to serve as basic analysis units while preserving spatial heterogeneity characteristics. The effectiveness of regional division is evaluated using 5 indicators, including travel heat, Moran's index, and others. Empirical analysis using Harbin's main urban area taxi trajectory data shows that, compared with fixed bandwidth methods, the proposed method increases identified hotspots by 2.1 to 6.7 times. The standard deviation of regional travel heat differences is 572.8. The average dis-tance between point data centroids within areal elements and the geometric center is 137.8 m, a 15.1% to 74.3% re-duction from traditional grid methods, verifying the homogeneity advantage of the regional division. The nugget to sill ratio drops to 0.135, and internal unit variation decreases by 39.6%, indicating the method effectively retains da-ta aggregation characteristics and reduces the modifiable areal unit problem's impact. The adaptive method identifies 1, 719 travel hotspots in the study area and accurately locates road intersection hotspots in areas like Harbin West Station, with clear boundaries and explicit geographical semantics. The results provide an adaptive framework for multi-density travel data analysis, supporting applications such as taxi dispatching and demand forecasting.
-
Key words:
- urban transportation /
- hotspot detection /
- kernel density /
- regional division /
- multi-density data
-
图 6 不同区域划分方案案例分析对比
Figure 6. Case studies and comparisons of different regional division schemes
图 7 局部高出行密度区域基本单元划分与分级
Figure 7. Classification and classification of basic units in local high-density areas
图 8 局部低出行密度区域基本单元划分与分级
Figure 8. Classification and classification of basic units in local low-density areas
表 1 哈尔滨出租车数据描述
Table 1. Travel hotspots of Harbin at different grades
等级 自适应带宽 较大带宽 中等带宽 较小带宽 热点数量 占比/% 热点数量 占比/% 热点数量 占比/% 热点数量 占比/% Ⅰ 564 32.81 176 69.02 602 72.53 8 234 77.16 Ⅱ 568 33.04 45 17.65 163 19.64 1 861 17.44 Ⅲ 406 23.61 26 10.20 53 6.39 489 4.58 Ⅳ 147 8.55 7 2.75 11 1.33 86 0.81 Ⅴ 34 1.98 1 0.39 1 0.12 1 0.01 
下载: 导出CSV
表 2 全局莫兰指数
Table 2. Results of Global Moran's I
区域划分方案 Moran's I 均值 方差 Z值 P值 自适应热点区域 0.338 765 -0.000 582 0.000 015 88.987 517 0.000 1 10 m热点区域 0.411 725 -0.000 094 0.000 001 475.990 751 0.000 1 300 m热点区域 0.635 711 -0.001 206 0.000 105 62.228 267 0.000 1 600 m热点区域 0.517 628 -0.000 013 0.000 201 41.356 752 0.000 1 200 m栅格 0.916 463 -0.000 008 0.000 004 452.466 257 0.000 1 300 m栅格 0.893 831 -0.000 033 0.000 016 221.343 284 0.000 1 600 m栅格 0.759 127 -0.000 285 0.000 144 63.177 174 0.000 1 1000 m栅格 0.753 746 -0.000 779 0.000 397 37.869 035 0.000 1
下载: 导出CSV
表 3 不同区域划分方案下的热度与匀质性比较
Table 3. Comparison of heat and homogeneity under different division schemes
区域划分方案 区域数量 热度最小值 热度最大值 热度平均值 区域热度差异 平均距离/m 块金基台比 自适应热点区域 1 719 0 5 554.7 409.8 572.8 137.8 0.135 10 m热点区域 10 671 0 81.0 2.8 3.9 198.1 0.282 300 m热点区域 830 0 24.1 1.44 2.6 206.4 0.194 600 m热点区域 255 0 107.5 5.9 6.5 337.2 0.217 200 m栅格 37 310 0 1 479.4 70.5 118.2 162.3 0.236 300 m栅格 16 714 0 1 904.7 106.7 176.1 226.9 0.209 600 m栅格 4 209 0 3 948.1 179.2 211.9 384.9 0.224 1000 m栅格 1 476 0 4 812.3 477.3 247.1 536.1 0.308
下载: 导出CSV
-
[1] 李之红, 申天宇, 文琰杰, 等. 基于混合机器学习框架的网约车订单需求预测与异常点识别[J]. 交通信息与安全, 2023, 41(3): 157-165, 174. doi: 10.3963/jjssn.1674-4861.2023.03.017LI Z H, SHEN T Y, WEN Y J, et al. Order demand prediction and anomaly-point identification for online car-hailing orders based on hybrid machine learning framework[J]. Journal of Transport Information and Safety, 2023, 41(3): 157-165, 174. (in Chinese) doi: 10.3963/jjssn.1674-4861.2023.03.017 [2] LIANG X, BAKER J, DELLAPOSTA D, et al. Is your neighbor your friend? Scan methods for spatial social network hotspot detection[J]. Transactions in GIS, 2023, 27(3): 607-625. doi: 10.1111/tgis.13050 [3] ZHENG H, GAO S, CAI C, et al. A rapid density method for taxi passengers hot spot recognition and visualization based on DBSCAN+[J]. Scientific Reports, 2021, 11(1): 1-13. doi: 10.1038/s41598-020-79139-8 [4] 龙雪琴, 周萌, 赵欢, 等. 基于网络核密度的网约车上下客热点识别[J]. 交通运输系统工程与信息, 2021, 21(3): 86-93.LONG X Q, ZHOU M, ZHAO H, et al. Passengers' hot spots identification of online car-hailing based on network kernel density[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 86-93. (in Chinese) [5] ZHANG G, XU J. Multi-GPU-Parallel and tile-based kernel density estimation for large-scale spatial point pattern analysis[J]. ISPRS International Journal of Geo-Information, 2023, 12(2): 1-20. [6] OU Y, KIM E, LIU X, et al. Delineating functional regions from road networks: the case of South Korea[J]. Environment and Planning B: Urban Analytics and City Science, 2023, 50(6): 1677-1694. doi: 10.1177/23998083231172198 [7] ZHANG K, LIU Z, ZHENG L. Short-term prediction of passenger demand in multi-zone level: temporal convolutional neural network with multi-Task learning[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(4): 1480-1490. doi: 10.1109/TITS.2019.2909571 [8] COMBER A, HARRIS P, BRATKOVA K, et al. Handling the MAUP: methods for identifying appropriate scales of aggregation based on measures on spatial and non-spatial variance[J]. AGILE: GIScience Series, 2022, 30(3): 1-5. [9] GAO Y, LIAO Y. Urban tourism traffic analysis zone division based on floating car data[J]. Promet-Traffic&Transportation, 2023, 35(3): 395-406. [10] LI C, ZHENG L, JIA N. Network-wide ride-sourcing passenger demand origin-destination matrix prediction with a generative adversarial network[J]. Transportmetrica A: Transport Science, 2022, 20(1): 1-28. [11] YANG B, TIAN Y, WANG J, et al. How to improve urban transportation planning in big data era? A practice in the study of traffic analysis zone delineation[J]. Transport Policy, 2022, 127: 1-14. doi: 10.1016/j.tranpol.2022.08.002 [12] 薛晴婉, 瞿麦青, 彭怀军, 等. 基于多目标蚁群算法的共享单车调度优化方法[J]. 交通信息与安全, 2024, 42(2): 124-135. doi: 10.3963/jssn.1674-4861.2024.02.013XUE Q W, QU M Q, PENG H J, et al. A scheduling optimization method of shared bicycles based on a multi-objective ant colony algorithm[J]. Journal of Transport Information and Safety, 2024, 42(2): 124-135. (in Chinese) doi: 10.3963/jssn.1674-4861.2024.02.013 [13] LUO H, CAI J, ZHANG K, et al. A multi-task deep learning model for short-term taxi demand forecasting considering spatiotemporal dependences[J]. Journal of Traffic and Transportation Engineering(English Edition), 2021, 8(1): 83-94. doi: 10.1016/j.jtte.2019.07.002 [14] 陈启香, 吕斌, 李显林. 站域建成环境对出租车-地铁组合出行的非线性影响[J]. 交通运输工程学报, 2024, 24(5): 285-300.CHEN Q X, LYU B, LI X L. Nonlinear effect of station-area built environment on taxi-metro combined travel[J]. Journal of Traffic and Transportation Engineering, 2024, 24(5): 285-300. (in Chinese) [15] CESARIO E, UCHUBILO P I, VINCI A, et al. Multi-density urban hotspots detection in smart cities: a data-driven approach and experiments[J]. Pervasive and Mobile Computing, 2022, 86(1): 1-13. [16] 王梓蒙, 刘艳芳, 罗璇, 等. 基于多源数据的城市活力与建成环境非线性关系研究——以双休日武汉市主城区为例[J]. 地理科学进展, 2023, 42(4): 716-729. (in Chinese)WANG Z M, LIU Y F, LUO X, et al. Nonlinear relationship between urban vitality and the built environment based on multi-source data: a case study of the main urban area of Wuhan city at the weekend[J]. Progress in Geography, 2023, 42(4): 716-729. (in Chinese) [17] TANG J, HU J, WANG Y, et al. Estimating hotspots using a Gaussian mixture model from large-scale taxi GPS trace data[J]. Transportation Safety and Environment, 2019, 1(2): 145-153. doi: 10.1093/tse/tdz006 [18] ZHANG G, ZHU A X, HUANG Q. A GPU-accelerated adaptive kernel density estimation approach for efficient point pattern analysis on spatial big data[J]. International Journal of Geographical Information Science, 2017, 31(10): 2068-2097. doi: 10.1080/13658816.2017.1324975 [19] JAVANMARD R, LEE J, KIM J, et al. The impacts of the modifiable areal unit problem(MAUP)on social equity analysis of public transit reliability[J]. Journal of Transport Geography, 2023, 106(1): 1-13. [20] 刘瑜, 汪珂丽, 邢潇月, 等. 地理分析中的空间效应[J]. 地理学报, 2023, 78(3): 517-531.LIU Y, WANG K L, XING X Y, et al. On spatial effects in geographical analysis[J]. Acta Geographica Sinica, 2023, 78(3): 517-531. (in Chinese) [21] 全威, 孙超. 基于热点探测的城市区域公交可达性研究[J]. 交通运输系统工程与信息, 2020, 20(2): 231-236.QUAN W, SUN C. Bus accessibility in urban areas based on hot spot detection[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(2): 231-236. (in Chinese) [22] YAN Y, QUAN W, WANG H. A data-driven adaptive geospatial hotspot detection approach in smart cities[J]. Transactions in GIS, 2024, 28(2): 303-325. doi: 10.1111/tgis.13137 [23] 葛浩菁, 吕远, 焦朋朋. 基于信令数据的中型城市通勤公交站点优化方法[J]. 交通信息与安全, 2024, 42(1): 142-149. doi: 10.3963/jssn.1674-4861.2024.01.016GE H J, LYU Y, JIAO P P. Deployment of bus stop for commuters in medium-sized cities based on signaling data[J]. Journal of Transport Information and Safety, 2024, 42(1): 142-149. (in Chinese) doi: 10.3963/jssn.1674-4861.2024.01.016 -
点击查看大图
图(8) / 表(3)
计量
- 文章访问数: 38
- HTML全文浏览量: 22
- PDF下载量: 4
- 被引次数: 0