Using recurrent spatio-temporal profiles in GPS panel data for enhancing imputation of activity type

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

1 Citation (Scopus)

Abstract

Imputation of activity type from GPS traces has been considered of high importance in the domain of activity-travel behavior analysis. To increase the accuracy of activity type inference, recent studies have become increasingly dependent on the extensive use of personal location data, which are typically collected during the recruitment process or as part of auxiliary prompted recall sessions. Such data are however typically missing for increasingly more popular big datasets that tend to be aggregate in nature. To improve activity type imputation for such datasets, this paper proposes an enhanced approach for activity type identification from GPS measurements using recurrent profiles of individuals. It has been inspired by the fact that GPS-based data collection has shifted from single day to multi-day or multi-week data collection efforts, particularly for big data. The method derives from GPS panel data the frequency of activities by each predefined activity category. Results show that the temporal data play a much more important role than the spatial data in predicting activity types, supporting the relevance of the suggested approach for multi-day data. Considering the recurrent profiles of each activity, a model, which incorporates spatial and temporal variables and the frequency of activity locations, yields the best overall imputation accuracy of 67.4%.

Original languageEnglish
Title of host publicationBig Data for Regional Science
Place of PublicationLondon
PublisherTaylor and Francis Ltd.
Chapter10
Pages121-130
Number of pages10
ISBN (Electronic)9781351983266
ISBN (Print)9781138282186
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Imputation
Panel data
Data collection
Travel behavior
Behavior analysis
Inference

Cite this

@inbook{a784fe81d8414e6da57ba87ff04a61f2,
title = "Using recurrent spatio-temporal profiles in GPS panel data for enhancing imputation of activity type",
abstract = "Imputation of activity type from GPS traces has been considered of high importance in the domain of activity-travel behavior analysis. To increase the accuracy of activity type inference, recent studies have become increasingly dependent on the extensive use of personal location data, which are typically collected during the recruitment process or as part of auxiliary prompted recall sessions. Such data are however typically missing for increasingly more popular big datasets that tend to be aggregate in nature. To improve activity type imputation for such datasets, this paper proposes an enhanced approach for activity type identification from GPS measurements using recurrent profiles of individuals. It has been inspired by the fact that GPS-based data collection has shifted from single day to multi-day or multi-week data collection efforts, particularly for big data. The method derives from GPS panel data the frequency of activities by each predefined activity category. Results show that the temporal data play a much more important role than the spatial data in predicting activity types, supporting the relevance of the suggested approach for multi-day data. Considering the recurrent profiles of each activity, a model, which incorporates spatial and temporal variables and the frequency of activity locations, yields the best overall imputation accuracy of 67.4{\%}.",
author = "Tao Feng and Timmermans, {Harry J.P.}",
year = "2017",
month = "1",
day = "1",
doi = "10.4324/9781315270838",
language = "English",
isbn = "9781138282186",
pages = "121--130",
booktitle = "Big Data for Regional Science",
publisher = "Taylor and Francis Ltd.",
address = "United Kingdom",

}

Using recurrent spatio-temporal profiles in GPS panel data for enhancing imputation of activity type. / Feng, Tao; Timmermans, Harry J.P.

Big Data for Regional Science. London : Taylor and Francis Ltd., 2017. p. 121-130.

Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

TY - CHAP

T1 - Using recurrent spatio-temporal profiles in GPS panel data for enhancing imputation of activity type

AU - Feng, Tao

AU - Timmermans, Harry J.P.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Imputation of activity type from GPS traces has been considered of high importance in the domain of activity-travel behavior analysis. To increase the accuracy of activity type inference, recent studies have become increasingly dependent on the extensive use of personal location data, which are typically collected during the recruitment process or as part of auxiliary prompted recall sessions. Such data are however typically missing for increasingly more popular big datasets that tend to be aggregate in nature. To improve activity type imputation for such datasets, this paper proposes an enhanced approach for activity type identification from GPS measurements using recurrent profiles of individuals. It has been inspired by the fact that GPS-based data collection has shifted from single day to multi-day or multi-week data collection efforts, particularly for big data. The method derives from GPS panel data the frequency of activities by each predefined activity category. Results show that the temporal data play a much more important role than the spatial data in predicting activity types, supporting the relevance of the suggested approach for multi-day data. Considering the recurrent profiles of each activity, a model, which incorporates spatial and temporal variables and the frequency of activity locations, yields the best overall imputation accuracy of 67.4%.

AB - Imputation of activity type from GPS traces has been considered of high importance in the domain of activity-travel behavior analysis. To increase the accuracy of activity type inference, recent studies have become increasingly dependent on the extensive use of personal location data, which are typically collected during the recruitment process or as part of auxiliary prompted recall sessions. Such data are however typically missing for increasingly more popular big datasets that tend to be aggregate in nature. To improve activity type imputation for such datasets, this paper proposes an enhanced approach for activity type identification from GPS measurements using recurrent profiles of individuals. It has been inspired by the fact that GPS-based data collection has shifted from single day to multi-day or multi-week data collection efforts, particularly for big data. The method derives from GPS panel data the frequency of activities by each predefined activity category. Results show that the temporal data play a much more important role than the spatial data in predicting activity types, supporting the relevance of the suggested approach for multi-day data. Considering the recurrent profiles of each activity, a model, which incorporates spatial and temporal variables and the frequency of activity locations, yields the best overall imputation accuracy of 67.4%.

UR - http://www.scopus.com/inward/record.url?scp=85050282716&partnerID=8YFLogxK

U2 - 10.4324/9781315270838

DO - 10.4324/9781315270838

M3 - Chapter

AN - SCOPUS:85050282716

SN - 9781138282186

SP - 121

EP - 130

BT - Big Data for Regional Science

PB - Taylor and Francis Ltd.

CY - London

ER -