Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Inferring passenger types from commuter eigentravel matrices

Inferring passenger types from commuter eigentravel matrices A sufficient knowledge of the demographics of a commuting public is essential in formulating and implementing more targeted transportation policies. Here, a procedure is demonstrated that classifies passengers (Adult, Child/Student, and Senior Citizen) based on their three-month travel patterns. The method proceeds by constructing distinct commuter matrices, we refer to as eigentravel matrices, that capture a commuter's characteristic travel routine. Comparing various classification models, we show that the gradient boosting method gives the best prediction with 76% accuracy, 81% better than the minimum model accuracy (42%) computed using proportional chance criterion. The models are verified and validated; consequently, the procedure demonstrated should serve as a benchmark for problems of this type. The generally intuitive pattern of the demographic classification also points to a possible universal ‘travelprint’ of commuters, and can inspire development of unsupervised machine learning methods for automated fare collection systems that do not provide additional demographic detail. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Transportmetrica B: Transport Dynamics Taylor & Francis

Inferring passenger types from commuter eigentravel matrices

Inferring passenger types from commuter eigentravel matrices

Transportmetrica B: Transport Dynamics , Volume 6 (3): 21 – Jul 3, 2018

Abstract

A sufficient knowledge of the demographics of a commuting public is essential in formulating and implementing more targeted transportation policies. Here, a procedure is demonstrated that classifies passengers (Adult, Child/Student, and Senior Citizen) based on their three-month travel patterns. The method proceeds by constructing distinct commuter matrices, we refer to as eigentravel matrices, that capture a commuter's characteristic travel routine. Comparing various classification models, we show that the gradient boosting method gives the best prediction with 76% accuracy, 81% better than the minimum model accuracy (42%) computed using proportional chance criterion. The models are verified and validated; consequently, the procedure demonstrated should serve as a benchmark for problems of this type. The generally intuitive pattern of the demographic classification also points to a possible universal ‘travelprint’ of commuters, and can inspire development of unsupervised machine learning methods for automated fare collection systems that do not provide additional demographic detail.

Loading next page...
 
/lp/taylor-francis/inferring-passenger-types-from-commuter-eigentravel-matrices-kBrAlkJFPm

References (64)

Publisher
Taylor & Francis
Copyright
© 2017 Hong Kong Society for Transportation Studies Limited
ISSN
2168-0582
eISSN
2168-0566
DOI
10.1080/21680566.2017.1291377
Publisher site
See Article on Publisher Site

Abstract

A sufficient knowledge of the demographics of a commuting public is essential in formulating and implementing more targeted transportation policies. Here, a procedure is demonstrated that classifies passengers (Adult, Child/Student, and Senior Citizen) based on their three-month travel patterns. The method proceeds by constructing distinct commuter matrices, we refer to as eigentravel matrices, that capture a commuter's characteristic travel routine. Comparing various classification models, we show that the gradient boosting method gives the best prediction with 76% accuracy, 81% better than the minimum model accuracy (42%) computed using proportional chance criterion. The models are verified and validated; consequently, the procedure demonstrated should serve as a benchmark for problems of this type. The generally intuitive pattern of the demographic classification also points to a possible universal ‘travelprint’ of commuters, and can inspire development of unsupervised machine learning methods for automated fare collection systems that do not provide additional demographic detail.

Journal

Transportmetrica B: Transport DynamicsTaylor & Francis

Published: Jul 3, 2018

Keywords: Human mobility; travel pattern recognition; activity pattern recognition; automated fare collection system; sociodemographics; classification; machine learning

There are no references for this article.