摘要
利用重庆轻轨的乘客刷卡数据,分析了乘客出行特征,并提出了一种基于马尔科夫链的乘客轨迹预测算法。该算法首先利用贝叶斯分类器对乘客下次出行轨迹进行分类;然后,根据乘客最近一次出行轨迹与其常住地的关系,预测其下次出行轨迹。在真实轻轨交通数据集上的实验结果表明,该算法对乘客出行轨迹的预测效果优于LTMT、RNN和2-MC;同时,该算法基于大数据处理框架Spark进行编码,减少了运行时间。
By utilizing the smart card data from Chongqing light rail system,the travel characteristics of light rail passengers are analyzed and a trajectory prediction algorithm based on Markov chain is proposed.In the algorithm,the next travel trajectory of a passenger is classified by Bayesian classification and then predicted according to the relationship between the passenger’s last travel trajectory and her/his residence.Experimental results based on real datasets show that the algorithm outperforms LTMT,RNN and 2-MC on predicting passenger’s next travel trajectory.Meanwhile,the algorithm is coded on Spark,a big data processing framework,which reduces its runtime.
作者
彭舰
孙海
陈瑜
仝博
黄飞虎
PENG Jian;SUN Hai;CHEN Yu;TONG Bo;HUANG Fei-hu(College of Computer Science,Sichuan University Chengdu 610065)
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
2018年第5期720-725,共6页
Journal of University of Electronic Science and Technology of China
基金
国家自然科学基金(U1333113)
四川省科技支撑计划(2014GZ0111)
关键词
贝叶斯分类
马尔科夫链
轻轨预测
出行轨迹
Bayesian classification
Markov chain
trajectory prediction
travel trajectory
