arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2407.07030cs.AI
收藏

特定道路的轨迹数据挖掘与行程旅行时间预测

Trajectory Data Mining and Trip Travel Time Prediction on Specific Roads

Data Science Consultant(数据科学顾问);Datamatics Technologies(Datamatics技术公司);Department of CS&IT Women University of AJ&K(CS&IT系妇女大学AJ&K分校);Classified institute(保密机构);Department of Computer Science(计算机科学系);Kohsar University(Kohsar大学);Disruptive Innovation Laboratory(颠覆性创新实验室);PIEAS

Muhammad Awais Amin, Jawad-Ur-Rehman Chughtai, Waqar Ahmad, Waqas Haider Bangyal, Irfan Ul Haq

AI总结:

针对巴基斯坦本土道路缺乏适配旅行时间预测研究的问题,设计轨迹挖掘流水线并采用多种前沿神经网络模型,实现了伊斯兰堡地区常用路线较低误差的行程时间预测。

摘要:

预测行程旅行时间对路线规划与导航应用至关重要。现有研究大多基于国际数据,并不适用于巴基斯坦的道路状况。我们设计了一套完整的从传感器数据中挖掘轨迹的流水线。基于该数据,我们采用了包括浅层人工神经网络、深度多层感知器以及长短期记忆网络(LSTM)在内的前沿方法,探究常走路线的旅行时间预测问题。实验结果显示,在巴基斯坦伊斯兰堡地区的六条最常用路线上,对于时长10分钟至60分钟的行程,平均预测误差在30秒到1.2分钟之间。

英文摘要:

Predicting a trip's travel time is essential for route planning and navigation applications. The majority of research is based on international data that does not apply to Pakistan's road conditions. We designed a complete pipeline for mining trajectories from sensors data. On this data, we employed state-of-the-art approaches, including a shallow artificial neural network, a deep multi-layered perceptron, and a long-short-term memory, to explore the issue of travel time prediction on frequent routes. The experimental results demonstrate an average prediction error ranging from 30 seconds to 1.2 minutes on trips lasting 10 minutes to 60 minutes on six most frequent routes in regions of Islamabad, Pakistan.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑