Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Data-Driven Travel Time Prediction
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Being able to accurately forecast the time of arrival of a vehicle in traffic appeals both to private drivers aiming to keep up with their schedules, and to businesses that need to organize transport logistics. THis thesis is assigned by the Swedish truck manufacturer Scania CV AB, and sets out to use GPS data from Scania's vehicle fleet to train Machine LEarning models to predict the travel times of vehicles between stops. The predictive models implemented train on features engineered from quite simple information from the vehicles, yet reach high predictive accuracy in certain scenarios. Two approaches to predicting travel time are tested, one referred to as the Local Models approach, and the other as the Global Model approach. In the Local Models approach, many separate regressors are trained on geographical subsets of the datra and then comnbined to give global predictions. In the Global Model approach, a single regressor trains on the entire data set. The Global Model approch gives better performance than that of the Local Models in the experiment, but the Local Models approach shows some promising tendencies. It is found that a regressor predicts significantly more accurately when the geographical spread of the data is limited.

Abstract [sv]

Att ge noggranna förutsager om restider för fordon i trafik är av intresse både för privata förare som försöker hinna med sina scheman, och företag som behöver organiska logistik för transporter. Denna rapport görs på uppdrag av svenska lastbilstillverkaren Scania CV AB, och har som mål att använda GPS-data från Scanias fordon till att träna maskininlärningsmodeller för att förutsäga hur lång tid det tar för fordon att resa mellan stopp. De prediktiva modellerna som implementeras använder variabler som konstrueras från relativt enkel information från fordonen, men lyckas ändå nå hög prediktiv prestanda i vissa scenarion. Två olika ansatser prövas för att förutsäga restider, en ansats med lokala modeller, och en ansats med global modell. I ansatsen med lokala modeller tränas flera separata regressorer på geografiska delmängder av datan, vilka sedan kombineras och ger globala förutsägor. I ansatsen med global modell tränas en enda regressor på hela datamängden. Ansatsen med global modell visar sig ha högre prestanda i experimenten, men ansatsen med lokala modeller förevisar ändå vissa lovande tendenser. Resultaten antyder att en regressor ger mycket noggrannare prediktioner när den geografiska spridningen i datan begränsas.

Place, publisher, year, edition, pages
2019. , p. 55
Series
TRITA-EECS-EX ; 2019:493
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-255023OAI: oai:DiVA.org:kth-255023DiVA, id: diva2:1337275
Examiners
Available from: 2019-07-12 Created: 2019-07-12 Last updated: 2019-07-12Bibliographically approved

Open Access in DiVA

fulltext(2713 kB)14 downloads
File information
File name FULLTEXT01.pdfFile size 2713 kBChecksum SHA-512
fd81a9e467e6695056be55be9b8ce4574cb5be3270016941e3a8d82f9882edc14e43b8ece32163b1a247cc0d39341df4cb23b108426f9a89089ef4ee8ab78e05
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 14 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: 101 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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