针对公交车行程时间预测存在数据稀疏、数据缺失及更新间隔长等问题,提出了一种基于相似路段划分并融合多线路信息的卡尔曼滤波算法。该算法对每条路段的属性特征和空间结构特征进行归一化处理,利用属性特征和空间结构的相似性及POI(Poi...针对公交车行程时间预测存在数据稀疏、数据缺失及更新间隔长等问题,提出了一种基于相似路段划分并融合多线路信息的卡尔曼滤波算法。该算法对每条路段的属性特征和空间结构特征进行归一化处理,利用属性特征和空间结构的相似性及POI(Point of Interest)对交通影响的变化动态地划分相似路段;然后融合相似路段与目标路段上的多条公交线路的数据信息,用相似路段的数据丰富实验数据;最后结合卡尔曼滤波算法动态性高、实时性强等特点建立模型,从而实现短时预测,并对信息进行修正。选取沈阳市162线路和299线路作为实验线路,各划取一段相似路段进行基础数据采集并进行实验。通过相似路段上的信息来推断数据稀疏或缺失路段的信息,能够缩短数据更新间隔并提高算法预测的实时性及精准性,尤其在早高峰时段,提出的算法模型的绝对平均百分误差达到13.2%,能达到实时查询的性能需求。展开更多
[Objective] This study was to construct VPDN-based 3G wireless meteorological information transmission system, in order to achieve the backup transmission of real-time meteorological services in all levels of meteorol...[Objective] This study was to construct VPDN-based 3G wireless meteorological information transmission system, in order to achieve the backup transmission of real-time meteorological services in all levels of meteorological stations. [Method] The current situations and business requirements of municipal meteorological networks are analyzed, putting forward the idea of backup routes that using VPDN-based 3G wireless meteorological information transmission system as the ground transmission line. And the network structure, operation mode and the system implementation are described in detail. [Result] VPDN-based 3G wireless meteorological information transmission system realizes the backup of ground line. Compared with the Modem dial-up, it is more stable and with faster transferring speed. With the rapid development of communication technology and computer technology, the information transmission system will be more efficient and stable, and will play a greater role in meteorological information transmission. [Conclusion] With the continuous development of modern meteorology, various types of meteorological data increase, presenting higher demand for the meteorological information transmission system. The established VPND-based 3G wireless meteorological information transmission system of this study provides a solution for backup transmission of real-time meteorological services.展开更多
文摘针对公交车行程时间预测存在数据稀疏、数据缺失及更新间隔长等问题,提出了一种基于相似路段划分并融合多线路信息的卡尔曼滤波算法。该算法对每条路段的属性特征和空间结构特征进行归一化处理,利用属性特征和空间结构的相似性及POI(Point of Interest)对交通影响的变化动态地划分相似路段;然后融合相似路段与目标路段上的多条公交线路的数据信息,用相似路段的数据丰富实验数据;最后结合卡尔曼滤波算法动态性高、实时性强等特点建立模型,从而实现短时预测,并对信息进行修正。选取沈阳市162线路和299线路作为实验线路,各划取一段相似路段进行基础数据采集并进行实验。通过相似路段上的信息来推断数据稀疏或缺失路段的信息,能够缩短数据更新间隔并提高算法预测的实时性及精准性,尤其在早高峰时段,提出的算法模型的绝对平均百分误差达到13.2%,能达到实时查询的性能需求。
文摘[Objective] This study was to construct VPDN-based 3G wireless meteorological information transmission system, in order to achieve the backup transmission of real-time meteorological services in all levels of meteorological stations. [Method] The current situations and business requirements of municipal meteorological networks are analyzed, putting forward the idea of backup routes that using VPDN-based 3G wireless meteorological information transmission system as the ground transmission line. And the network structure, operation mode and the system implementation are described in detail. [Result] VPDN-based 3G wireless meteorological information transmission system realizes the backup of ground line. Compared with the Modem dial-up, it is more stable and with faster transferring speed. With the rapid development of communication technology and computer technology, the information transmission system will be more efficient and stable, and will play a greater role in meteorological information transmission. [Conclusion] With the continuous development of modern meteorology, various types of meteorological data increase, presenting higher demand for the meteorological information transmission system. The established VPND-based 3G wireless meteorological information transmission system of this study provides a solution for backup transmission of real-time meteorological services.