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
Similarity and Interchangeability of Flow and Speed Data for Transport Network Day-Type Clustering and Prediction
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Transport planning.ORCID iD: 0000-0002-8499-0843
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Transport planning.ORCID iD: 0000-0003-1514-6777
Linköping university.
KTH, School of Architecture and the Built Environment (ABE), Civil and Architectural Engineering, Transport planning.ORCID iD: 0000-0002-4106-3126
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Prediction of future traffic states is an essential part of traffic management and intelligent transportation systems. Previous work has shown that spatio-temporal clustering of traffic data such as flows or speeds into network day-types improves both the performance and the robustness of traffic predictions. Since some data types may not be available at a network-wide level, or only for certain periods, this paper investigates how similar such representative day-types are if based on different data types. The similarity of day-type clusters is evaluated with qualitative calendar visualization and two quantitative metrics, the Adjusted Mutual Information (AMI) which considers day-to-cluster assignments, and a new proposed Centroids Similarity Score (CSS) which compares centroids. The paper also explores the impact on flow and speed prediction performance of substituting one data type for the other in the clustering or classification phases. Using microwave sensor data from the Stockholm motorway network, our findings show that clusterings based on flows and speeds and across a range of clustering methods have reasonably high similarity. CSS is found to be a more relevant similarity indicator than AMI in the prediction application context. By capturing more relevant traffic state information, flow-based clustering and classification are robust for both flow and speed predictions, while speed-based clustering significantly degrades flow prediction performance.

Keywords [en]
clustering, pattern recognition, machine-learning, day type, intelligent transportation systems, traffic prediction, short-term prediction, speed-flow relationship
National Category
Transport Systems and Logistics
Research subject
Transport Science; Transport Science, Transport Systems
Identifiers
URN: urn:nbn:se:kth:diva-304731OAI: oai:DiVA.org:kth-304731DiVA, id: diva2:1610245
Note

QC 20211116

Available from: 2021-11-10 Created: 2021-11-10 Last updated: 2022-06-25Bibliographically approved
In thesis
1. Enhancing Short-Term Traffic Prediction for Large-Scale Transport Networks by Spatio-Temporal Clustering
Open this publication in new window or tab >>Enhancing Short-Term Traffic Prediction for Large-Scale Transport Networks by Spatio-Temporal Clustering
2021 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Congestion in large cities is responsible for extra travel time, noise, air pollution, CO2 emissions, and more. Transport is one of the main recognized contributors to global warming and climate change, which is getting increasing attention from authorities and societies around the world. Better utilization of existing resources by Intelligent Transport Systems (ITS) and digital technologies are recognized by the European Commission as technologies with enormous potential to lower the negative impacts associated with high traffic volumes in urban areas.

The main focus of this work is on short-term traffic prediction, which is an essential tool in ITS. In combination with providing information, it enables proactive decisions to decrease severity of congestion that occurs regularly or is caused by incidents. The main contribution of this work is to develop a methodological framework and prove its enhancing effects on short-term prediction in the context of large-scale transport networks. It is expected to contribute to more robust and accurate predictions of ITS in traffic management centers.

Traffic patterns in large-scale networks, including urban streets, can be heterogeneous during the day and from day-to-day. This work investigates spatio-temporal clustering of heterogeneous data sets to smaller, more homogeneous data sub-sets. This is expected to produce more robust, accurate, scalable, and cost-effective prediction models. 

This thesis is the collection of five papers that contribute to enhancing short-term traffic prediction in this context. The clustering is recognized to boost prediction performance in Papers II, III, IV, and V. Paper II considers network partitioning and the last three papers study day clustering. The prediction models used across included papers are naive historical mean prediction models and more advanced prediction models such as probabilistic principal component analysis (PPCA) and exponential smoothing. Paper I considers and facilitates floating car data (FCD) as a cost-effective opportunistic source of speed and travel time data with extensive network coverage.

Common practice in determining the number of clusters is to rely on internal evaluation indices, and these are very efficient but isolated from application. Paper IV tests this practice by also considering performance in short-term prediction application. Our results show that relying on these indices can lead to a loss of prediction accuracy of about 20% depending on the considered prediction model. Dimensionality reduction has a minimal effect on the resulting prediction performance, but clustering needs 20 times less computational time and only 0.1% of the original information.

Finally, in Paper V, we look at similarities of representative day clusters recognized by speed and flows. Furthermore, the interchangeability of speed day-type centroids for flow when predicting speeds has proven to be robust, which is not a case for predicting flows by speed day-type centroids and observations.

Abstract [sv]

Trängsel i storstäderna leder till extra restid, buller, luftföroreningar, koldioxidutsläpp med mera. Transporter är en av de främsta erkända bidragsgivarna till global uppvärmning och klimatförändringar, som får allt större uppmärksamhet från myndigheter och samhällen runt om i världen. Bättre utnyttjande av befintliga resurser genom intelligenta transportsystem (ITS) och digital teknik identifieras av Europeiska kommissionen som teknik med en enorm potential att minska ovanstående negativa effekter kopplade till stora trafikvolymer i stadsområden.

Huvudfokus i detta arbete ligger påkortsiktiga trafikprognoser, som är ett viktigt verktyg inom ITS. I kombination med informationsförsörjning möjliggör de proaktiva beslut för att minska omfattningen av trafikstockningar som uppstår regelbundet eller orsakas av incidenter. Det viktigaste bidraget i detta arbete är att utveckla ett metodologiskt ramverk och bevisa dess förbättrande effekter påkortsiktiga prognoser för storskaliga transportnät. Det förväntas bidra till mer robusta och exakta prognoser av ITS i trafikledningscentraler.

Trafikmönster i storskaliga nät, inklusive stadsgator, kan vara heterogena under dagen och från dag till dag. I detta arbete undersöks rumslig och temporal klustring av heterogena datamängder till mindre, mer homogena datamängder. Detta förväntas ge mer robusta, exakta, skalbara och kostnadseffektiva prognosmodeller.

Avhandlingen är en samling av fem artiklar som bidrar till att förbättra kortsiktiga trafikprognoser i detta sammanhang. Klustring påvisas öka prediktionsprestandan i artiklar II, III, IV och V. I artikel II beaktas nätverksuppdelning och i de tre sista dokumenten klusterbildning. De prediktionsmodeller som används i de inkluderade artiklarna är naiva historiska medelvärdesprediktionsmodeller och mer avancerade parametriska prediktionsmodeller, t.ex. probabilistisk principalkomponentanalys (PPCA) och exponentiell utjämning. I artikel I beaktas och utnyttjas probfordonsdata (FCD) som en kostnadseffektiv opportunistisk källa till hastighets- och restidsdata med omfattande nätverkstäckning.

Den vedertagna metoden för att bestämma antalet kluster är att förlita sig påinterna utvärderingsindex, och dessa är mycket effektiva men isolerade från tillämpningen. I uppsats IV testas denna praxis genom att även beakta prestandan i en tillämpning för korttidsprognoser. Våra resultat visar att om man förlitar sig pådessa index kan det leda till en förlust av prediktionsprestanda påcirka 20% beroende påvilken prognosmodell som används. Dimensionalitetsminskning har en minimal effekt påden resulterande prediktionsprestandan, men klusterbildning kräver 20 gånger mindre beräkningstid och endast 0,1% av den ursprungliga informationen.

Slutligen undersöker vi i artikel V likheterna mellan representativa dagskluster som bildas genom hastighet respektive flöden. Dessutom visar sig utbytbarheten av dagstypcentroider från hastigheter till flöden robust vid prediktion av hastigheter , vilket inte är fallet när det gäller prediktion av flöden.

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2021. p. 58
Series
TRITA-ABE-DLT ; 2143
Keywords
short-term prediction, clustering, spatio-temporal clustering, day-types, speed-flow relationship, large-scale
National Category
Transport Systems and Logistics
Research subject
Transport Science, Transport Systems
Identifiers
urn:nbn:se:kth:diva-304732 (URN)978-91-8040-071-8 (ISBN)
Public defence
2021-12-09, F3, Lindstedsvägen 26, KTH Campus, Zoom: https://kth-se.zoom.us/j/66844011086, Stockholm, 13:00 (English)
Opponent
Supervisors
Available from: 2021-11-15 Created: 2021-11-10 Last updated: 2022-09-19Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records

Cebecauer, MatejBurghout, WilcoJenelius, Erik

Search in DiVA

By author/editor
Cebecauer, MatejBurghout, WilcoJenelius, Erik
By organisation
Transport planning
Transport Systems and Logistics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 230 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