利用神经网络从行程数据和环境信息中预测每小时出发地-目的地矩阵

IF 1.4 4区工程技术 Q2 ENGINEERING, MULTIDISCIPLINARY

Scientia Iranica Pub Date : 2023-07-18 DOI:10.24200/sci.2023.58193.5608

Ehsan Hassanzadeh, Zahra Amini

{"title":"利用神经网络从行程数据和环境信息中预测每小时出发地-目的地矩阵","authors":"Ehsan Hassanzadeh, Zahra Amini","doi":"10.24200/sci.2023.58193.5608","DOIUrl":null,"url":null,"abstract":"61 Predicting Origin-Destination demand has always been a challenging problem in transportation. 62 Conventional demand prediction methods mainly propose procedures for forecasting aggregated temporal 63 Origin-Destination (OD) flows. In other words, they are primarily unable to predict short-term demands. 64 Another limitation of these models is that they do not consider the impact of environmental conditions on 65 trip patterns. Furthermore, OD demand prediction requires two individual steps of modeling: trip 66 generation and trip distribution. This article presents a framework for predicting hourly OD flows using 67 the Neural Network. The proposed method utilizes trip patterns and environmental conditions for 68 predicting demands in single-step modeling. A case study on New York City Green Taxi 2018 trip data is 69 done to evaluate the method, and the results demonstrate that the network has reasonably accurate OD 70 flows predictions.","PeriodicalId":21605,"journal":{"name":"Scientia Iranica","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using Neural Network for Predicting Hourly Origin-Destination Matrices from Trip Data and Environmental Information\",\"authors\":\"Ehsan Hassanzadeh, Zahra Amini\",\"doi\":\"10.24200/sci.2023.58193.5608\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"61 Predicting Origin-Destination demand has always been a challenging problem in transportation. 62 Conventional demand prediction methods mainly propose procedures for forecasting aggregated temporal 63 Origin-Destination (OD) flows. In other words, they are primarily unable to predict short-term demands. 64 Another limitation of these models is that they do not consider the impact of environmental conditions on 65 trip patterns. Furthermore, OD demand prediction requires two individual steps of modeling: trip 66 generation and trip distribution. This article presents a framework for predicting hourly OD flows using 67 the Neural Network. The proposed method utilizes trip patterns and environmental conditions for 68 predicting demands in single-step modeling. A case study on New York City Green Taxi 2018 trip data is 69 done to evaluate the method, and the results demonstrate that the network has reasonably accurate OD 70 flows predictions.\",\"PeriodicalId\":21605,\"journal\":{\"name\":\"Scientia Iranica\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2023-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Scientia Iranica\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.24200/sci.2023.58193.5608\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientia Iranica","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.24200/sci.2023.58193.5608","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

摘要

61 起点-目的地需求预测一直是交通领域的难题。62 传统的需求预测方法主要是提出预测时间性的起点-目的地（OD）总流量的程序。换言之，它们主要无法预测短期需求。64 这些模型的另一个局限是没有考虑环境条件对 65 行程模式的影响。此外，OD 需求预测需要两个单独的建模步骤：66 行程生成和行程分布。本文提出了一个利用 67 神经网络预测每小时 OD 流量的框架。所提出的方法利用了出行模式和环境条件，在单步建模中预测需求。为评估该方法，对纽约市绿色出租车 2018 年的出车数据进行了 69 案例研究，结果表明该网络能合理准确地预测 70 OD 流量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Using Neural Network for Predicting Hourly Origin-Destination Matrices from Trip Data and Environmental Information

61 Predicting Origin-Destination demand has always been a challenging problem in transportation. 62 Conventional demand prediction methods mainly propose procedures for forecasting aggregated temporal 63 Origin-Destination (OD) flows. In other words, they are primarily unable to predict short-term demands. 64 Another limitation of these models is that they do not consider the impact of environmental conditions on 65 trip patterns. Furthermore, OD demand prediction requires two individual steps of modeling: trip 66 generation and trip distribution. This article presents a framework for predicting hourly OD flows using 67 the Neural Network. The proposed method utilizes trip patterns and environmental conditions for 68 predicting demands in single-step modeling. A case study on New York City Green Taxi 2018 trip data is 69 done to evaluate the method, and the results demonstrate that the network has reasonably accurate OD 70 flows predictions.

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

Scientia Iranica 工程技术-工程：综合

CiteScore

2.90

自引率

7.10%

发文量

审稿时长

2 months

期刊介绍： The objectives of Scientia Iranica are two-fold. The first is to provide a forum for the presentation of original works by scientists and engineers from around the world. The second is to open an effective channel to enhance the level of communication between scientists and engineers and the exchange of state-of-the-art research and ideas. The scope of the journal is broad and multidisciplinary in technical sciences and engineering. It encompasses theoretical and experimental research. Specific areas include but not limited to chemistry, chemical engineering, civil engineering, control and computer engineering, electrical engineering, material, manufacturing and industrial management, mathematics, mechanical engineering, nuclear engineering, petroleum engineering, physics, nanotechnology.