从空间时间序列数据中识别逻辑设施

IF 7.1 1区 地球科学 Q1 ENVIRONMENTAL STUDIES Computers Environment and Urban Systems Pub Date : 2024-09-12 DOI:10.1016/j.compenvurbsys.2024.102182
Dirk J. De Beer , Johan W. Joubert
{"title":"从空间时间序列数据中识别逻辑设施","authors":"Dirk J. De Beer ,&nbsp;Johan W. Joubert","doi":"10.1016/j.compenvurbsys.2024.102182","DOIUrl":null,"url":null,"abstract":"<div><p>Vehicle telemetry data is becoming more ubiquitous with increasingly sensorised vehicles, but making sense of the vehicles' purpose remains challenging without additional context. Clustering the vehicle activity data and identifying the underlying facilities where the activities occur reveals much insight, particularly for logistics planning. Unfortunately, current research typically only looks at a single point in time. This paper contributes by matching geospatial patterns, each representing a facility where trucks perform activities over multiple periods. The contribution is a necessary first step in studying how urban freight movement and its underlying inter-firm networks of connectivity change over time. We demonstrate how to overcome three challenges. Firstly, the complexity of identifying facilities from non-regular geometric polygons. Secondly, the challenge associated with the scale of comparing more than 200,000 facilities on a month-to-month basis over a multi-year period. Finally, overcoming the computational challenge of the workflow and getting the required performance on a consumer-grade laptop. The paper evaluates various machine learning algorithms, highlighting a SVM that outperforms more popular deep learning and neural network alternatives, with a mean average accuracy of 96.9 %.</p></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"114 ","pages":"Article 102182"},"PeriodicalIF":7.1000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Logistic facility identification from spatial time series data\",\"authors\":\"Dirk J. De Beer ,&nbsp;Johan W. Joubert\",\"doi\":\"10.1016/j.compenvurbsys.2024.102182\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Vehicle telemetry data is becoming more ubiquitous with increasingly sensorised vehicles, but making sense of the vehicles' purpose remains challenging without additional context. Clustering the vehicle activity data and identifying the underlying facilities where the activities occur reveals much insight, particularly for logistics planning. Unfortunately, current research typically only looks at a single point in time. This paper contributes by matching geospatial patterns, each representing a facility where trucks perform activities over multiple periods. The contribution is a necessary first step in studying how urban freight movement and its underlying inter-firm networks of connectivity change over time. We demonstrate how to overcome three challenges. Firstly, the complexity of identifying facilities from non-regular geometric polygons. Secondly, the challenge associated with the scale of comparing more than 200,000 facilities on a month-to-month basis over a multi-year period. Finally, overcoming the computational challenge of the workflow and getting the required performance on a consumer-grade laptop. The paper evaluates various machine learning algorithms, highlighting a SVM that outperforms more popular deep learning and neural network alternatives, with a mean average accuracy of 96.9 %.</p></div>\",\"PeriodicalId\":48241,\"journal\":{\"name\":\"Computers Environment and Urban Systems\",\"volume\":\"114 \",\"pages\":\"Article 102182\"},\"PeriodicalIF\":7.1000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers Environment and Urban Systems\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S019897152400111X\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL STUDIES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers Environment and Urban Systems","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S019897152400111X","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
引用次数: 0

摘要

随着车辆传感器化程度的不断提高,车辆遥测数据变得越来越普遍,但如果没有更多的背景信息,要了解车辆的用途仍然具有挑战性。对车辆活动数据进行聚类,并确定活动发生的底层设施,可以为物流规划提供更多启示。遗憾的是,目前的研究通常只关注单个时间点。本文的贡献在于匹配地理空间模式,每个模式都代表卡车在多个时间段内开展活动的设施。这是研究城市货运及其背后的企业间连通网络如何随时间变化的必要的第一步。我们展示了如何克服三个挑战。首先,从非规则几何多边形中识别设施的复杂性。其次,与在多年时间内逐月比较 20 多万个设施的规模相关的挑战。最后,克服工作流程的计算挑战,在消费级笔记本电脑上获得所需的性能。论文对各种机器学习算法进行了评估,其中 SVM 的平均准确率高达 96.9%,优于更常用的深度学习和神经网络算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Logistic facility identification from spatial time series data

Vehicle telemetry data is becoming more ubiquitous with increasingly sensorised vehicles, but making sense of the vehicles' purpose remains challenging without additional context. Clustering the vehicle activity data and identifying the underlying facilities where the activities occur reveals much insight, particularly for logistics planning. Unfortunately, current research typically only looks at a single point in time. This paper contributes by matching geospatial patterns, each representing a facility where trucks perform activities over multiple periods. The contribution is a necessary first step in studying how urban freight movement and its underlying inter-firm networks of connectivity change over time. We demonstrate how to overcome three challenges. Firstly, the complexity of identifying facilities from non-regular geometric polygons. Secondly, the challenge associated with the scale of comparing more than 200,000 facilities on a month-to-month basis over a multi-year period. Finally, overcoming the computational challenge of the workflow and getting the required performance on a consumer-grade laptop. The paper evaluates various machine learning algorithms, highlighting a SVM that outperforms more popular deep learning and neural network alternatives, with a mean average accuracy of 96.9 %.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
13.30
自引率
7.40%
发文量
111
审稿时长
32 days
期刊介绍: Computers, Environment and Urban Systemsis an interdisciplinary journal publishing cutting-edge and innovative computer-based research on environmental and urban systems, that privileges the geospatial perspective. The journal welcomes original high quality scholarship of a theoretical, applied or technological nature, and provides a stimulating presentation of perspectives, research developments, overviews of important new technologies and uses of major computational, information-based, and visualization innovations. Applied and theoretical contributions demonstrate the scope of computer-based analysis fostering a better understanding of environmental and urban systems, their spatial scope and their dynamics.
期刊最新文献
Estimating the density of urban trees in 1890s Leeds and Edinburgh using object detection on historical maps The role of data resolution in analyzing urban form and PM2.5 concentration Causal discovery and analysis of global city carbon emissions based on data-driven and hybrid intelligence Editorial Board Exploring the built environment impacts on Online Car-hailing waiting time: An empirical study in Beijing
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1