Recommendation of feeder bus routes using neural network embedding-based optimization

C. Park, Jungpyo Lee, So Young Sohn

Research output: Contribution to journalArticle

Abstract

Despite the existence of vast bus and subway networks, the demand for taxis in the morning commute hours is substantial in metropolitan areas. This kind of morning traffic can be resolved by means of feeder buses connecting residential areas with popular transit points. To assist the design of feeder bus routes, this study proposes an optimization approach based on road2vec, which is applied to real-time taxi GPS data. Road2vec is a neural network-based embedding methodology that extracts road name vectors considering the movement patterns of vehicles. Subsequently, the k-means clustering analysis is applied to those vectors to identify the major taxi transit clusters during the commute hours. For each cluster, we suggest a feeder bus route that can best reflect the taxi trajectory patterns. To find intermediate stops between the departure and origin of a feeder bus route, we solve an integer programming to maximize the cosine similarity between the origin road vector and the departure road vector subtracted by the road vectors of intermediate stops. The suggested routes based on our method differ from the existing routes in that they have a tendency to pass through residential areas, transit stations, and schools. In addition, the result suggests that the model developed in this study finds bus routes that could be suitable for feeder buses by accommodating areas where the demand for taxis is high in the morning. Our road2vec approach is expected to contribute to a reduction in traffic during rush hours.

Original languageEnglish
Pages (from-to)329-341
Number of pages13
JournalTransportation Research Part A: Policy and Practice
Volume126
DOIs
Publication statusPublished - 2019 Aug

Fingerprint

neural network
road
Neural networks
residential area
traffic
demand
agglomeration area
programming
Subways
Integer programming
Bus
methodology
Global positioning system
school
Trajectories
Roads

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Transportation
  • Management Science and Operations Research

Cite this

@article{9e0a7ca38dfd41a7bf5742c4d59e7428,
title = "Recommendation of feeder bus routes using neural network embedding-based optimization",
abstract = "Despite the existence of vast bus and subway networks, the demand for taxis in the morning commute hours is substantial in metropolitan areas. This kind of morning traffic can be resolved by means of feeder buses connecting residential areas with popular transit points. To assist the design of feeder bus routes, this study proposes an optimization approach based on road2vec, which is applied to real-time taxi GPS data. Road2vec is a neural network-based embedding methodology that extracts road name vectors considering the movement patterns of vehicles. Subsequently, the k-means clustering analysis is applied to those vectors to identify the major taxi transit clusters during the commute hours. For each cluster, we suggest a feeder bus route that can best reflect the taxi trajectory patterns. To find intermediate stops between the departure and origin of a feeder bus route, we solve an integer programming to maximize the cosine similarity between the origin road vector and the departure road vector subtracted by the road vectors of intermediate stops. The suggested routes based on our method differ from the existing routes in that they have a tendency to pass through residential areas, transit stations, and schools. In addition, the result suggests that the model developed in this study finds bus routes that could be suitable for feeder buses by accommodating areas where the demand for taxis is high in the morning. Our road2vec approach is expected to contribute to a reduction in traffic during rush hours.",
author = "C. Park and Jungpyo Lee and Sohn, {So Young}",
year = "2019",
month = "8",
doi = "10.1016/j.tra.2019.05.005",
language = "English",
volume = "126",
pages = "329--341",
journal = "Transportation Research, Part A: Policy and Practice",
issn = "0965-8564",
publisher = "Elsevier Limited",

}

Recommendation of feeder bus routes using neural network embedding-based optimization. / Park, C.; Lee, Jungpyo; Sohn, So Young.

In: Transportation Research Part A: Policy and Practice, Vol. 126, 08.2019, p. 329-341.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Recommendation of feeder bus routes using neural network embedding-based optimization

AU - Park, C.

AU - Lee, Jungpyo

AU - Sohn, So Young

PY - 2019/8

Y1 - 2019/8

N2 - Despite the existence of vast bus and subway networks, the demand for taxis in the morning commute hours is substantial in metropolitan areas. This kind of morning traffic can be resolved by means of feeder buses connecting residential areas with popular transit points. To assist the design of feeder bus routes, this study proposes an optimization approach based on road2vec, which is applied to real-time taxi GPS data. Road2vec is a neural network-based embedding methodology that extracts road name vectors considering the movement patterns of vehicles. Subsequently, the k-means clustering analysis is applied to those vectors to identify the major taxi transit clusters during the commute hours. For each cluster, we suggest a feeder bus route that can best reflect the taxi trajectory patterns. To find intermediate stops between the departure and origin of a feeder bus route, we solve an integer programming to maximize the cosine similarity between the origin road vector and the departure road vector subtracted by the road vectors of intermediate stops. The suggested routes based on our method differ from the existing routes in that they have a tendency to pass through residential areas, transit stations, and schools. In addition, the result suggests that the model developed in this study finds bus routes that could be suitable for feeder buses by accommodating areas where the demand for taxis is high in the morning. Our road2vec approach is expected to contribute to a reduction in traffic during rush hours.

AB - Despite the existence of vast bus and subway networks, the demand for taxis in the morning commute hours is substantial in metropolitan areas. This kind of morning traffic can be resolved by means of feeder buses connecting residential areas with popular transit points. To assist the design of feeder bus routes, this study proposes an optimization approach based on road2vec, which is applied to real-time taxi GPS data. Road2vec is a neural network-based embedding methodology that extracts road name vectors considering the movement patterns of vehicles. Subsequently, the k-means clustering analysis is applied to those vectors to identify the major taxi transit clusters during the commute hours. For each cluster, we suggest a feeder bus route that can best reflect the taxi trajectory patterns. To find intermediate stops between the departure and origin of a feeder bus route, we solve an integer programming to maximize the cosine similarity between the origin road vector and the departure road vector subtracted by the road vectors of intermediate stops. The suggested routes based on our method differ from the existing routes in that they have a tendency to pass through residential areas, transit stations, and schools. In addition, the result suggests that the model developed in this study finds bus routes that could be suitable for feeder buses by accommodating areas where the demand for taxis is high in the morning. Our road2vec approach is expected to contribute to a reduction in traffic during rush hours.

UR - http://www.scopus.com/inward/record.url?scp=85068419446&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068419446&partnerID=8YFLogxK

U2 - 10.1016/j.tra.2019.05.005

DO - 10.1016/j.tra.2019.05.005

M3 - Article

AN - SCOPUS:85068419446

VL - 126

SP - 329

EP - 341

JO - Transportation Research, Part A: Policy and Practice

JF - Transportation Research, Part A: Policy and Practice

SN - 0965-8564

ER -