基于马尔科夫链的轻轨乘客轨迹预测新算法 |
| |
引用本文: | 彭舰,孙海,陈瑜,仝博,黄飞虎. 基于马尔科夫链的轻轨乘客轨迹预测新算法[J]. 电子科技大学学报(自然科学版), 2018, 47(5): 720-725. DOI: 10.3969/j.issn.1001-0548.2018.05.013 |
| |
作者姓名: | 彭舰 孙海 陈瑜 仝博 黄飞虎 |
| |
作者单位: | 四川大学计算机学院 成都 610065 |
| |
基金项目: | 国家自然科学基金U1333113四川省科技支撑计划2014GZ0111 |
| |
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。
|
关 键 词: | 贝叶斯分类 马尔科夫链 轻轨预测 出行轨迹 |
收稿时间: | 2017-01-18 |
Novel Algorithm of Light Rail Passenger Trajectory Prediction Based on Markov Chain |
| |
Affiliation: | College of Computer Science, Sichuan University Chengdu 610065 |
| |
Abstract: | 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. |
| |
Keywords: | |
|
| 点击此处可从《电子科技大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《电子科技大学学报(自然科学版)》下载全文 |