SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS

Estimation of the state of road traffic conditions is gaining increasing attention in recent intelligent transportation systems. Accurate and real-time estimation of traffic condition changes is critical in the management and control of road network systems. Thus, efforts are been made to predict sho...

Full description

Saved in:
Bibliographic Details
Main Authors: Yağmur ÖZİNAL AVŞAR, Ercan AVŞAR
Format: Article
Language:English
Published: Silesian University of Technology 2022-06-01
Series:Scientific Journal of Silesian University of Technology. Series Transport
Subjects:
Online Access:https://sjsutst.polsl.pl/archives/2022/vol115/121_SJSUTST115_2022_OzinalAvsar_Avsar.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846093332176961536
author Yağmur ÖZİNAL AVŞAR
Ercan AVŞAR
author_facet Yağmur ÖZİNAL AVŞAR
Ercan AVŞAR
author_sort Yağmur ÖZİNAL AVŞAR
collection DOAJ
description Estimation of the state of road traffic conditions is gaining increasing attention in recent intelligent transportation systems. Accurate and real-time estimation of traffic condition changes is critical in the management and control of road network systems. Thus, efforts are been made to predict short-term traffic conditions based on measured traffic data such as speed, flow and density. In this work, the state of the traffic is estimated through a three-step process. First, both speed and flow predictions for 15-minute ahead are made for a particular freeway segment. Four different regression models are used for the prediction task, namely, multi-layer perceptron neural networks (MLPNN), support vector regression (SVR), gradient boosted decision trees (GBDT), and k-nearest neighbors (kNN). Next, the breakpoint (BP) flow is calculated using the distribution of these predicted speed and flow values. In the final step, these predictions are classified as belonging to a “stable state” or “metastable state” by using the calculated BP as the threshold between these states. According to the experimental results, the values for MLPNN are the highest for speed (0.8564) and flow (0.9862) predictions. An identical BP, 1050 pc/15min, is calculated for actual data as well as all prediction methods.
format Article
id doaj-art-df471e5fec3d46948a9e53e3b61cc78d
institution Kabale University
issn 0209-3324
2450-1549
language English
publishDate 2022-06-01
publisher Silesian University of Technology
record_format Article
series Scientific Journal of Silesian University of Technology. Series Transport
spelling doaj-art-df471e5fec3d46948a9e53e3b61cc78d2025-01-02T18:09:08ZengSilesian University of TechnologyScientific Journal of Silesian University of Technology. Series Transport0209-33242450-15492022-06-0111511512113410.20858/sjsutst.2022.115.9SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODSYağmur ÖZİNAL AVŞAR0https://orcid.org/0000-0002-8083-6494Ercan AVŞAR1https://orcid.org/0000-0002-1356-2753Faculty of Engineering, Department of Civil Engineering, Dokuz Eylül University, 35390, Buca/İzmir, TurkeyFaculty Engineering, Department of Computer Engineering, Dokuz Eylül University, 35390, Buca/İzmir, TurkeyEstimation of the state of road traffic conditions is gaining increasing attention in recent intelligent transportation systems. Accurate and real-time estimation of traffic condition changes is critical in the management and control of road network systems. Thus, efforts are been made to predict short-term traffic conditions based on measured traffic data such as speed, flow and density. In this work, the state of the traffic is estimated through a three-step process. First, both speed and flow predictions for 15-minute ahead are made for a particular freeway segment. Four different regression models are used for the prediction task, namely, multi-layer perceptron neural networks (MLPNN), support vector regression (SVR), gradient boosted decision trees (GBDT), and k-nearest neighbors (kNN). Next, the breakpoint (BP) flow is calculated using the distribution of these predicted speed and flow values. In the final step, these predictions are classified as belonging to a “stable state” or “metastable state” by using the calculated BP as the threshold between these states. According to the experimental results, the values for MLPNN are the highest for speed (0.8564) and flow (0.9862) predictions. An identical BP, 1050 pc/15min, is calculated for actual data as well as all prediction methods.https://sjsutst.polsl.pl/archives/2022/vol115/121_SJSUTST115_2022_OzinalAvsar_Avsar.pdfbreakpointmachine learningshort-term trafficpredictionspeed-flow relationship
spellingShingle Yağmur ÖZİNAL AVŞAR
Ercan AVŞAR
SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
Scientific Journal of Silesian University of Technology. Series Transport
breakpoint
machine learning
short-term traffic
prediction
speed-flow relationship
title SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
title_full SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
title_fullStr SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
title_full_unstemmed SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
title_short SHORT-TERM TRAFFIC STATE ESTIMATION USING BREAKPOINT FLOW CALCULATION AND MACHINE LEARNING METHODS
title_sort short term traffic state estimation using breakpoint flow calculation and machine learning methods
topic breakpoint
machine learning
short-term traffic
prediction
speed-flow relationship
url https://sjsutst.polsl.pl/archives/2022/vol115/121_SJSUTST115_2022_OzinalAvsar_Avsar.pdf
work_keys_str_mv AT yagmurozinalavsar shorttermtrafficstateestimationusingbreakpointflowcalculationandmachinelearningmethods
AT ercanavsar shorttermtrafficstateestimationusingbreakpointflowcalculationandmachinelearningmethods