scholarly journals Ensemble Learning for Short-Term Traffic Prediction Based on Gradient Boosting Machine

2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Senyan Yang ◽  
Jianping Wu ◽  
Yiman Du ◽  
Yingqi He ◽  
Xu Chen
Keyword(s):  
Ensemble Learning ◽  
Traffic Volume ◽  
Prediction Performance ◽  
Traffic Prediction ◽  
Gradient Boosting ◽  
Relative Importance ◽  
Volume Data ◽  
Short Term ◽  
Traffic Condition ◽  
Input Variables

Short-term traffic prediction is vital for intelligent traffic systems and influenced by neighboring traffic condition. Gradient boosting decision trees (GBDT), an ensemble learning method, is proposed to make short-term traffic prediction based on the traffic volume data collected by loop detectors on the freeway. Each new simple decision tree is sequentially added and trained with the error of the previous whole ensemble model at each iteration. The relative importance of variables can be quantified in the training process of GBDT, indicating the interaction between input variables and response. The influence of neighboring traffic condition on prediction performance is identified through combining the traffic volume data collected by different upstream and downstream detectors as the input, which can also improve prediction performance. The relative importance of input variables for 15 GBDT models is different, and the impact of upstream traffic condition is not balanced with that of downstream. The prediction accuracy of GBDT is generally higher than SVM and BPNN for different steps ahead, and the accuracy of multi-step-ahead models is lower than 1-step-ahead models. For 1-step-ahead models, the prediction errors of GBDT are smaller than SVM and BPNN for both peak and nonpeak hours.

Optimization of Dynamic Neural Network Performance for Short-Term Traffic Prediction

2003 ◽  
Vol 1836 (1) ◽  
pp. 45-56 ◽  
Author(s):  
Sherif Ishak ◽  
Prashanth Kotha ◽  
Ciprian Alecsandru
Keyword(s):  
Neural Networks ◽  
Network Performance ◽  
Information Dissemination ◽  
Target Location ◽  
Prediction Performance ◽  
Time Factor ◽  
Traffic Prediction ◽  
Short Term ◽  
Traffic Condition ◽  
Dynamic Neural Networks

An approach is presented for optimizing short-term traffic-prediction performance by using multiple topologies of dynamic neural networks and various network-related and traffic-related settings. The conducted study emphasized the potential benefit of optimizing the prediction performance by deploying multimodel approaches under parameters and traffic-condition settings. Emphasis was placed on the application of temporal-processing topologies in short-term speed predictions in the range of 5-min to 20-min horizons. Three network topologies were used: Jordan–Elman networks, partially recurrent networks, and time-lagged feedforward networks. The input patterns were constructed from data collected at the target location and at upstream and downstream locations. However, various combinations were also considered. To encourage the networks to associate with historical information on recurrent conditions, a time factor was attached to the input patterns to introduce time-recognition capabilities, in addition to information encoded in the recent past data. The optimal prediction settings (type of topology and input settings) were determined so that performance was maximized under different traffic conditions at the target and adjacent locations. The optimized performance of the dynamic neural networks was compared to that of a statistical nonlinear time series approach, which was outperformed in most cases. The study showed that no single topology consistently outperformed the others for all prediction horizons considered. However, the results showed that the significance of introducing the time factor was more pronounced under longer prediction horizons. A comparative evaluation of performance of optimal and nonoptimal settings showed substantial improvement in most cases. The applied procedure can also be used to identify the prediction reliability of information-dissemination systems.

Short-term traffic volume prediction by ensemble learning in concept drifting environments

2019 ◽  
Vol 164 ◽  
pp. 213-225 ◽  
Author(s):  
Jianhua Xiao ◽  
Zhu Xiao ◽  
Dong Wang ◽  
Jing Bai ◽  
Vincent Havyarimana ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Traffic Volume ◽  
Short Term

SHORT TERM TRAFFIC FLOW PREDICTION IN HETEROGENEOUS CONDITION USING ARTIFICIAL NEURAL NETWORK

Transport ◽  
2013 ◽  
Vol 30 (4) ◽  
pp. 397-405 ◽  
Author(s):  
Kranti Kumar ◽  
Manoranjan Parida ◽  
Vinod Kumar Katiyar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Traffic Flow ◽  
Traffic Congestion ◽  
Traffic Volume ◽  
Flow Data ◽  
Highway Traffic ◽  
Short Term ◽  
Artificial Neural ◽  
Input Variables

Traffic congestion is one of the main problems related to transportation in developed as well as developing countries. Traffic control systems are based on the idea to avoid traffic instabilities and to homogenize traffic flow in such a way that risk of accidents is minimized and traffic flow is maximized. There is a need to predict traffic flow data for advanced traffic management and traffic information systems, which aim to influence traveller behaviour, reducing traffic congestion and improving mobility. This study applies Artificial Neural Network for short term prediction of traffic volume using past traffic data. Besides traffic volume, speed and density, the model incorporates both time and the day of the week as input variables. Model has been validated using actual rural highway traffic flow data collected through field studies. Artificial Neural Network has produced good results in this study even though speeds of each category of vehicles were considered separately as input variables.

scholarly journals Short-Term Traffic Volume Forecasting with Asymmetric Loss Based on Enhanced KNN Method

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Zhiyuan Wang ◽  
Shouwen Ji ◽  
Bowen Yu
Keyword(s):  
Euclidean Distance ◽  
Intelligent Transportation System ◽  
Nearest Neighbor ◽  
Mean Squared Error ◽  
Essential Elements ◽  
Traffic Volume ◽  
K Nearest Neighbor ◽  
Short Term ◽  
Traffic Condition ◽  
Asymmetric Loss

Short-term traffic volume forecasting is one of the most essential elements in Intelligent Transportation System (ITS) by providing prediction of traffic condition for traffic management and control applications. Among previous substantial forecasting approaches, K nearest neighbor (KNN) is a nonparametric and data-driven method popular for conciseness, interpretability, and real-time performance. However, in previous related researches, the limitations of Euclidean distance and forecasting with asymmetric loss have rarely been focused on. This research aims to fill up these gaps. This paper reconstructs Euclidean distance to overcome its limitation and proposes a KNN forecasting algorithm with asymmetric loss. Correspondingly, an asymmetric loss index, Imbalanced Mean Squared Error (IMSE), has also been proposed to test the effectiveness of newly designed algorithm. Moreover, the effect of Loess technique and suitable parameter value of dynamic KNN method have also been tested. In contrast to the traditional KNN algorithm, the proposed algorithm reduces the IMSE index by more than 10%, which shows its effectiveness when the cost of forecasting residual direction is notably different. This research expands the applicability of KNN method in short-term traffic volume forecasting and provides an available approach to forecast with asymmetric loss.

scholarly journals Context-specific volume–delay curves by combining crowd-sourced traffic data with automated traffic counters: A case study for London

2020 ◽  
Vol 1 ◽  
Author(s):  
Gerard Casey ◽  
Bingyu Zhao ◽  
Krishna Kumar ◽  
Kenichi Soga
Keyword(s):  
Traffic Congestion ◽  
Specific Volume ◽  
Traffic Volume ◽  
Ease Of Use ◽  
General Nature ◽  
Volume Data ◽  
Traffic Condition ◽  
Delay Function ◽  
Traffic Speed ◽  
Context Specific

Abstract Traffic congestion across the world has reached chronic levels. Despite many technological disruptions, one of the most fundamental and widely used functions within traffic modeling, the volume–delay function has seen little in the way of change since it was developed in the 1960s. Traditionally macroscopic methods have been employed to relate traffic volume to vehicular journey time. The general nature of these functions enables their ease of use and gives widespread applicability. However, they lack the ability to consider individual road characteristics (i.e., geometry, presence of traffic furniture, road quality, and surrounding environment). This research investigates the feasibility to reconstruct the model using two different data sources, namely the traffic speed from Google Maps’ Directions Application Programming Interface (API) and traffic volume data from automated traffic counters (ATC). Google’s traffic speed data are crowd-sourced from the smartphone Global Positioning System (GPS) of road users, able to reflect real-time, context-specific traffic condition of a road. On the other hand, the ATCs enable the harvesting of the vehicle volume data over equally fine temporal resolutions (hourly or less). By combining them for different road types in London, new context-specific volume–delay functions can be generated. This method shows promise in selected locations with the generation of robust functions. In other locations, it highlights the need to better understand other influencing factors, such as the presence of on-road parking or weather events.

scholarly journals A Gradient Boosting Crash Prediction Approach for Highway-Rail Grade Crossing Crash Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Pan Lu ◽  
Zijian Zheng ◽  
Yihao Ren ◽  
Xiaoyi Zhou ◽  
Amin Keramati ◽  
...  
Keyword(s):  
The United States ◽  
Traffic Volume ◽  
Prediction Performance ◽  
Data Availability ◽  
Gradient Boosting ◽  
Gradient Descent Algorithm ◽  
Grade Crossing ◽  
Crash Likelihood ◽  
Prediction Approach ◽  
Gb Model

Highway-rail grade crossing (HRGC) crashes continue to be the major contributors to rail causalities in the United States and have been intensively researched in the past. Data-mining models focus on prediction while dominant general linear models focus on model and data fitness. Decision makers and traffic engineers rely on prediction models to examine at-grade crash frequency and make safety improvement. The gradient boosting (GB) model has gained popularity in many research areas. In this study, to fully understand the model performance on HRGC accident prediction performance, the GB model with functional gradient descent algorithm is selected to analyze crashes at highway-rail grade crossings (HRGCs) and to identify contributor factors. Moreover, contributors’ importance and partial-dependent relations are generated to further understand the relationship of identified contributors and HRGC crash likelihood to concur “black box” issues that most machine learning methods face. Furthermore, to fully demonstrate the model’s prediction performance, a comprehensive model prediction power assessment based on six measurements is conducted, and the prediction performance of the GB model is verified and compared with a decision tree model as a reference due to their popularity and comparable data availability. It is demonstrated that the GB model produces better prediction accuracy and reveals nonlinear relationships among contributors and crash likelihood. In general, HRGC crash likelihood is significantly impacted by several traffic exposure factors: highway traffic volume, railway traffic volume, and train travel speed and others.

A Deep Learning Model for Off-Ramp Hourly Traffic Volume Estimation

2021 ◽  
pp. 036119812110271
Author(s):  
Amir Nohekhan ◽  
Sara Zahedian ◽  
Ali Haghani
Keyword(s):  
Deep Learning ◽  
Transportation Network ◽  
Flow Characteristics ◽  
Learning Model ◽  
Traffic Volume ◽  
Volume Estimation ◽  
Primary Data ◽  
Volume Data ◽  
Traffic Condition ◽  
Deep Learning Model

This paper addresses estimation of traffic volume of freeway off-ramps. Freeways are the transportation network’s main corridors, serving a large portion of the traffic volume. This traffic passes into the lower-level roads through off-ramps. Therefore, the traffic condition of the off-ramps is an essential factor affecting the operation of the transportation network. The continuous collection of volume data is impractical, and transportation authorities install vehicle detectors permanently on only a few off-ramps and temporarily (e.g., a week) on some others. Thus, traffic volume is the most challenging to estimate among various traffic measures. Moreover, the existing literature on volume estimation is mainly concerned with evaluating traffic on the main road segments. However, the distinct characteristics of the connection links, such as off-ramps, demands specified modeling. This study estimates the hourly traffic volume of off-ramps using a deep learning model. It evaluates the advantages of inputting the connected lower-level road features to the model, and explores various detector installation strategies on the model training process. The primary data sources are volume counts, probe speeds, and road segment infrastructure characteristics. The model results indicate that the incorporation of traffic flow characteristics and infrastructure attributes of the lower-level road connected to the freeway significantly improves the accuracy of estimation off-ramp traffic volume. Further, analysis illustrated that the model trained with data from temporarily installed detectors on all interchanges outperformed models trained with permanently installed detectors on 90% of the interchanges, indicating the model’s ability in extracting temporal correlations significantly more than spatial correlations.

Sign in / Sign up

Export Citation Format

Share Document