Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Istanbul Ticaret Uni...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

Travel time prediction in public transportation

Authors: Boylu, Betül; Boyacı, Ali;

Travel time prediction in public transportation

Abstract

Günümüzde toplu ulaşımda, otobüsün ulaşım süresinin tahmini, bilgiye kolayca erişebilen ve günlük aktivitelerini planladıkları gibi yolculuklarını da planlamak isteyen yolcular için oldukça önemlidir. Büyük şehirlerde otobüslerin varış süresi bazı öngörülemeyen dış faktörler nedeniyle çeşitlilik göstermektedir. Bu nedenle bu çalışma, GPS cihazları ile toplanan veriyi kullanarak, güçlü ancak sade bir Makine Öğrenmesi tekniği sunmaktadır. Teknik, geçmiş veriden öğrenerek ve hava durumu, yoğun saatler, haftanın yoğun günleri ve yıllın yoğun günleri gibi etkenleri göz önünde bulundurarak her durak aralığı için gelecek verisini tahmin eden Çoklu Doğrusal Regrasyon algoritmasını kullanmaktadır. Tekniği doğrulamak amacı ile bir simulasyon modeli oluşturulmuştur. Simulasyon modeli geçmiş verinin ortalaması ve gerçek veri ile kıyaslanarak modelin doğruluğu ölçülmüştür. Sonuçlar tahmin tekniğinin ortalama modeline göre daha iyi performans gösterdiğini ve gerçek veriye en yakın tahmini yaptığını göstermiştir.

Today, travel time prediction is essential for passengers who can easily access information and want to be able to plan their journeys as well as their daily activities. Travel time varies due to some unpredictable external factors especially in big cities. Therefore this paper proposes a powerful but simple Machine Learning (ML) model by using data collected by GPS devices. The model uses a Multiple Linear Regression algorithm that learns from historic data and predicts future data for each bus stop interval by considering external factors such as; weather condition, peak hours, busy week days and busy days of year. A simulation model was developed to validate the model. Then the simulation model was compared to average of historic data and real data. Results show that the prediction model outperforms the average model and calculates closest travel times to the real data.

Country
Turkey
Related Organizations
Keywords

multiple linear regression, Travel time prediction, Çoklu doğrusal regrasyon, Ulaşım süresi tahmini

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green