Bus Stations Prediction Based on Canopy-K-means from Taxi GPS Data

doi:10.13474/j.cnki.11-2246.2018.0351

Abstract

Abstract:

It is fairly hard to plan the path of public traffic and to determine the traffic site via traditional way. Additionally, by appropriately mining the useful GPS data of taxi, the human activity hotspot can be identified. Thus, mining the GPS data of taxi is helpful for planning bus station. For this reason, A Canopy-K-means method is proposed to predict public traffic stations. Firstly, the hot spots of the tourist destination can be got by applying the Canopy K-means algorithm. Further, comparing the hot spots with the existing bus stations, we analyze the rationality of the existence of the bus station. Then, the temporal and spatial distribution characteristics of passenger flow is studied by mathematical statistics. The GPS trajectory data of 2064 taxis in Wuhan from July 31, 2014 to August 12, 2014 are employing for experimental study and the results show that the proposed method can effectively distinguish the rationality of bus station location and provide auxiliary decision for the departure frequency of buses.

Key words: taxi track data, Canopy-K-means algorithm, bus stations prediction, departure frequency of buses

CLC Number:

LIU Xu, CHEN Yunbo, SHI Kun, HUANG Qiang. Bus Stations Prediction Based on Canopy-K-means from Taxi GPS Data[J]. 测绘通报, 2018, 0(11): 63-68.

References

[1] 李德仁,姚远,邵振峰.智慧城市中的大数据[J].武汉大学学报(信息科学版),2014,39(6):631-640.
[2] 岳邦佳,林爱文,孙铖.基于公共交通系统的城市公园绿地可达性分析——以武汉市中心城区为例[J].测绘与空间地理信息,2016,39(12):60-63,67.
[3] LIU Y, WANG F, XIAO Y, et al. Urban Land Uses and Traffic ‘Source-sink Areas’:Evidence from GPS-enabled Taxi Data in Shanghai[J]. Landscape and Urban Planning, 2012, 106(1):73-87.
[4] 周素红,郝新华,柳林.多中心化下的城市商业中心空间吸引衰减率验证——深圳市浮动车GPS时空数据挖掘[J].地理学报,2014,69(12):1810-1820.
[5] 李晓旭,于亚新,张文超,等.Coteries轨迹模式挖掘及个性化旅游路线推荐[J].软件学报,2018,29(3):587-598.
[6] 谷岩岩,焦利民,董婷,等.基于多源数据的城市功能区识别及相互作用分析[J].武汉大学学报(信息科学版),2018,43(7):1-9.
[7] 周雪梅,彭昌溆,宋兴昊,等.基于前车数据的动态公交车辆到站时间预测模型研究[J].交通与运输(学术版),2011(2):52-56.
[8] 王武. 基于海量GPS数据的公共交通站点及路线优化研究[D].重庆:西南大学,2016.
[9] KOSHY R Z, ARASAN V T. Influence of Bus Stops on Flow Characteristics of Mixed Traffic[J]. Journal of Transportation Engineering, 2005, 131(8):640-643.
[10] 周洋. 基于出租车数据的城市居民活动空间与网络时空特性研究[D].武汉:武汉大学,2016.
[11] 蒋鸿玲,张楠,李克,等.基于MapReduce的出租车停泊点智能推荐算法[J].计算机应用与软件,2016,33(2):254-258.
[12] AVINERI E. The Effect of Reference Point on Stochastic Network Equilibrium[J].Transportation Science,2006,40(4):409-420.
[13] 李晓瑜,俞丽颖,雷航,等.一种K-means改进算法的并行化实现与应用[J].电子科技大学学报,2017,46(1):61-68.
[14] 樊宁.K均值聚类算法在银行客户细分中的研究[J].计算机仿真,2011,28(3):369-372.
[15] 唐炉亮,段倩,阚子涵,等.出租车交接班行为识别与时空分布研究[J].地球信息科学学报,2017,19(2):167-175.
[16] 刘春,黄美娴,林航飞.基于浮动车数据的城市隧道实时路况多元线性回归模拟[J].交通与计算机,2008,26(2):66-69.
[17] YUAN N J, ZHENG Y, ZHANG L, et al. T-finder:A Recommender System for Finding Passengers and Vacant Taxis[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(10):2390-2403.