Identifying atypical travel patterns for improved medium-term mobility prediction

Roland Herberth, Leonhard Menz, Sidney Korper, Chunbo Luo, Frank Gauterin, Ansgar Gerlicher, Qi Wang

Research output: Contribution to journalArticle

10 Downloads (Pure)

Abstract

During the last decades, concepts of Intelligent Transportation Systems (ITS) were continuously adapted and improved based on new insights into human travel behavior. Drivers for improvements are the quantity and quality of available mobility data, which increased significantly in recent years. Based on travel behavior, literature proposes a large number of different solutions for next step or future location prediction. However a holistic spatio-temporal prediction, which could further improve the quality of ITS, creates a more complex task. The prediction of medium-term mobility for one to seven days is challenging in particular for atypical travel behavior, since the weekdays' order delivers no reliable indication for the next day's travel behavior. With our contribution, we explore the benefits of various prediction approaches for medium-term mobility prediction and combine them dynamically to predict individual mobility behavior for a period of one week. The derived framework utilizes an exhaustive search approach to benefit from a machine learning based clustering method on location data. In conjunction with an Artificial Neural Network, the prediction framework is robust against prediction errors created by atypical behavior. With two data sets consisting of smartphone and vehicle data, we demonstrate the framework's real-world applicability. We show that clustering an individual's historical movement data can improve the prediction accuracy of different prediction methods that will be explained in detail and illustrate the interrelation of entropy and prediction accuracy.
Original languageEnglish
JournalIEEE Transactions on Intelligent Transportation Systems
Early online date23 Oct 2019
DOIs
Publication statusE-pub ahead of print - 23 Oct 2019

Fingerprint

Smartphones
Learning systems
Entropy
Neural networks

Keywords

  • Spatio-temporal
  • Medium-term mobility prediction
  • Pattern mining
  • Atypical travel pattern
  • Intelligent transportation system

Cite this

Herberth, Roland ; Menz, Leonhard ; Korper, Sidney ; Luo, Chunbo ; Gauterin, Frank ; Gerlicher, Ansgar ; Wang, Qi. / Identifying atypical travel patterns for improved medium-term mobility prediction. In: IEEE Transactions on Intelligent Transportation Systems. 2019.
@article{a748204a41aa4c959ae6c0f9fc5d1567,
title = "Identifying atypical travel patterns for improved medium-term mobility prediction",
abstract = "During the last decades, concepts of Intelligent Transportation Systems (ITS) were continuously adapted and improved based on new insights into human travel behavior. Drivers for improvements are the quantity and quality of available mobility data, which increased significantly in recent years. Based on travel behavior, literature proposes a large number of different solutions for next step or future location prediction. However a holistic spatio-temporal prediction, which could further improve the quality of ITS, creates a more complex task. The prediction of medium-term mobility for one to seven days is challenging in particular for atypical travel behavior, since the weekdays' order delivers no reliable indication for the next day's travel behavior. With our contribution, we explore the benefits of various prediction approaches for medium-term mobility prediction and combine them dynamically to predict individual mobility behavior for a period of one week. The derived framework utilizes an exhaustive search approach to benefit from a machine learning based clustering method on location data. In conjunction with an Artificial Neural Network, the prediction framework is robust against prediction errors created by atypical behavior. With two data sets consisting of smartphone and vehicle data, we demonstrate the framework's real-world applicability. We show that clustering an individual's historical movement data can improve the prediction accuracy of different prediction methods that will be explained in detail and illustrate the interrelation of entropy and prediction accuracy.",
keywords = "Spatio-temporal, Medium-term mobility prediction, Pattern mining, Atypical travel pattern, Intelligent transportation system",
author = "Roland Herberth and Leonhard Menz and Sidney Korper and Chunbo Luo and Frank Gauterin and Ansgar Gerlicher and Qi Wang",
year = "2019",
month = "10",
day = "23",
doi = "10.1109/TITS.2019.2947347",
language = "English",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "IEEE",

}

Identifying atypical travel patterns for improved medium-term mobility prediction. / Herberth, Roland; Menz, Leonhard; Korper, Sidney; Luo, Chunbo; Gauterin, Frank; Gerlicher, Ansgar; Wang, Qi.

In: IEEE Transactions on Intelligent Transportation Systems, 23.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identifying atypical travel patterns for improved medium-term mobility prediction

AU - Herberth, Roland

AU - Menz, Leonhard

AU - Korper, Sidney

AU - Luo, Chunbo

AU - Gauterin, Frank

AU - Gerlicher, Ansgar

AU - Wang, Qi

PY - 2019/10/23

Y1 - 2019/10/23

N2 - During the last decades, concepts of Intelligent Transportation Systems (ITS) were continuously adapted and improved based on new insights into human travel behavior. Drivers for improvements are the quantity and quality of available mobility data, which increased significantly in recent years. Based on travel behavior, literature proposes a large number of different solutions for next step or future location prediction. However a holistic spatio-temporal prediction, which could further improve the quality of ITS, creates a more complex task. The prediction of medium-term mobility for one to seven days is challenging in particular for atypical travel behavior, since the weekdays' order delivers no reliable indication for the next day's travel behavior. With our contribution, we explore the benefits of various prediction approaches for medium-term mobility prediction and combine them dynamically to predict individual mobility behavior for a period of one week. The derived framework utilizes an exhaustive search approach to benefit from a machine learning based clustering method on location data. In conjunction with an Artificial Neural Network, the prediction framework is robust against prediction errors created by atypical behavior. With two data sets consisting of smartphone and vehicle data, we demonstrate the framework's real-world applicability. We show that clustering an individual's historical movement data can improve the prediction accuracy of different prediction methods that will be explained in detail and illustrate the interrelation of entropy and prediction accuracy.

AB - During the last decades, concepts of Intelligent Transportation Systems (ITS) were continuously adapted and improved based on new insights into human travel behavior. Drivers for improvements are the quantity and quality of available mobility data, which increased significantly in recent years. Based on travel behavior, literature proposes a large number of different solutions for next step or future location prediction. However a holistic spatio-temporal prediction, which could further improve the quality of ITS, creates a more complex task. The prediction of medium-term mobility for one to seven days is challenging in particular for atypical travel behavior, since the weekdays' order delivers no reliable indication for the next day's travel behavior. With our contribution, we explore the benefits of various prediction approaches for medium-term mobility prediction and combine them dynamically to predict individual mobility behavior for a period of one week. The derived framework utilizes an exhaustive search approach to benefit from a machine learning based clustering method on location data. In conjunction with an Artificial Neural Network, the prediction framework is robust against prediction errors created by atypical behavior. With two data sets consisting of smartphone and vehicle data, we demonstrate the framework's real-world applicability. We show that clustering an individual's historical movement data can improve the prediction accuracy of different prediction methods that will be explained in detail and illustrate the interrelation of entropy and prediction accuracy.

KW - Spatio-temporal

KW - Medium-term mobility prediction

KW - Pattern mining

KW - Atypical travel pattern

KW - Intelligent transportation system

U2 - 10.1109/TITS.2019.2947347

DO - 10.1109/TITS.2019.2947347

M3 - Article

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

ER -