kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
”Text me when you are home”: A Comparison of the Quality and Usability of Cellular Data to Traditional Travel Surveys
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Transport planning.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Effectively modeling travel demand is essential for evaluating transportation policies, improving the transportation system and contributing to sustainable mobility. Traditionally, information about travel demand is gathered through travel surveys, questionnaires about an individual’s travel behavior during one or more days. This approach has seen dwindling response rates in recent years, along with high costs and associated biases. As an alternative, travel demand can be measured passively using mobile signaling data due to the proliferation and high penetration of mobile device usage. In this report, mobile signaling data processed by a third party and labeled with transportation mode using an eXtreme Gradient Boost Classifier trained through supervised learning using manually labeled data is evaluated as a potential replacement or complement to traditional travel surveying using questionnaires through a case study in Ale municipality, Sweden. The novel data source is validated quantitatively and qualitatively regarding the number of trips recorded, detected transportation mode, gender, age and time attributes. It is found that the number of trips is accurate in the mobile signaling data. And although the inferred transportation modes are found to be less accurate than the number of trips, information about modes is considered accurate enough for practical transportation planning purposes. Lastly, the gender attribute in the mobile signaling data most likely describes gender-differentiated travel better than the traditional travel survey, although this finding needs to be reaffirmed with further research, while the corresponding findings for the age attribute are inconclusive. As the evaluated data source offers an improved spatial and temporal resolution, novel use cases are made possible, such as evaluation of new infrastructure, more accurate predictions of travel demand and augmentation with census data to describe socio-demographic effects on travel behavior. More efforts should be put into producing an unsupervised mode inference model which would alleviate any quality problems associated with resource constraints in the data processing.

 

Place, publisher, year, edition, pages
2024.
Series
TRITA-ABE-MBT ; 24559
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-349592OAI: oai:DiVA.org:kth-349592DiVA, id: diva2:1880755
External cooperation
Sweco
Supervisors
Examiners
Available from: 2024-07-02 Created: 2024-07-02

Open Access in DiVA

fulltext(1702 kB)106 downloads
File information
File name FULLTEXT01.pdfFile size 1702 kBChecksum SHA-512
c26b6735f8681d83e3bded7dc48dafcef70c2ce4b3898d28ad64e57d29df057994a4238a7862ea0c2b5b9dfc345c521b38cf7489a842378387bfe5952ac344e5
Type fulltextMimetype application/pdf

By organisation
Transport planning
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 106 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 444 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf