李帆, 夏吉喆, 黄赵, 李晓明, 李清泉. 顾及停留位置特征提取的个人位置预测方法[J]. 武汉大学学报 ( 信息科学版), 2020, 45(12): 1970-1980. DOI: 10.13203/j.whugis20200068
引用本文: 李帆, 夏吉喆, 黄赵, 李晓明, 李清泉. 顾及停留位置特征提取的个人位置预测方法[J]. 武汉大学学报 ( 信息科学版), 2020, 45(12): 1970-1980. DOI: 10.13203/j.whugis20200068
LI Fan, XIA Jizhe, HUANG Zhao, LI Xiaoming, LI Qingquan. Predicting Personal Next Location Based on Stay Point Feature Extraction[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1970-1980. DOI: 10.13203/j.whugis20200068
Citation: LI Fan, XIA Jizhe, HUANG Zhao, LI Xiaoming, LI Qingquan. Predicting Personal Next Location Based on Stay Point Feature Extraction[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1970-1980. DOI: 10.13203/j.whugis20200068

顾及停留位置特征提取的个人位置预测方法

Predicting Personal Next Location Based on Stay Point Feature Extraction

  • 摘要: 预测居民的未来活动位置与轨迹,为传染病防控、交通疏导、公共安全等城市智慧管理和服务提供主要决策依据。当前的个人位置预测方法往往基于个体的历史轨迹规律模式挖掘与建模进行位置预测,对于个体在不同停留位置的特征信息挖掘不够充分。为此,提出一种顾及停留位置特征提取的个人位置预测模型。首先,模型基于轨迹数据构建历史轨迹链路,采用位置发现规则将轨迹链路转化为停留位置链路,对停留位置进行空间聚类以构建聚类链路;其次,对不同的停留位置进行特征信息(进入/离开时间、天气状况、土地利用)提取,并提取聚类链路的空间特征;最后,将带有特征信息的链路代入长短期记忆神经网络进行定制集成,并实现个人位置的预测。实验结果表明,基于深圳市志愿者用户23天300余万个轨迹位置数据,本模型用户位置预测的F值在不同时间步长参数下均优于变阶马尔可夫模型(约5.5%增益)和传统N阶马尔可夫模型(约7%增益),引入停留位置特征的模型性能增益约为6.6%。

     

    Abstract: Predicting the future activity location and trajectory of residents can provide essential information for smart urban management such as epidemic control, traffic facilitation, public security, etc. However, the current personal location prediction methods generally focus on the mining of individual's historical travel patterns, and seldom consider the feature of different travel stay points. This paper aims to propose a location prediction model utilizing stay point feature extraction. The model firstly constructs the historical trajectory links based on trajectory data, performs the location discovery rules to transform historical trajectory links into stay point links and clusters the stay points to form clustering links. Secondly, the model extracts the feature information (entry time, departure time, weather and land use) from different stay points and extracts the space feature from clustering links. Finally, the cluster links with feature information is introduced into long short-term memory (LSTM) network for customization to implement the personal location prediction capability. By using a 23-day trajectory location data of more than 3 million volunteer users in Shenzhen city, China. The results show that the location prediction F-score of our proposed model is better than variable order Markov model (about 5.5% performance gains) and the traditional N-order Markov model (about 7% performance gains). The model also introduces approximately 6.6% performance gains by utilizing the temporal and weather features of stay points. The model shows the capability of utilizing travel stay point feature for personal next location prediction.

     

/

返回文章
返回