Remote Traffic Microwave Sensors Research Articles

A Novel Hybrid Model for Predicting Traffic Flow via Improved Ensemble Learning Combined with Deep Belief Networks

The intelligent transportation system (ITS) plays an irreplaceable role in alleviating urban traffic congestion and realizing sustainable urban development. Accurate and efficient short-term traffic state forecasting is a significant issue in ITS. This study proposes a novel hybrid model (ELM-IBF) to predict the traffic state on urban expressways by taking advantage of both deep learning models and ensemble learning framework. First, a developed bagging framework is introduced to combine several deep belief networks (DBNs) that are utilized to capture the complicated temporal characteristic of traffic flow. Then, a novel combination method named improved Bayesian fusion (IBF) is proposed to replace the averaging method in the bagging framework since it can better fuse the prediction results of the component DBNs by assigning the reasonable weights to DBNs at each prediction time interval. Finally, the proposed hybrid model is validated with ground-truth traffic flow data captured by the remote traffic microwave sensors installed on the multiple road sections of 2nd Ring Road in Beijing. The experimental results illustrate that the ELM-IBF method can effectively capture sharp fluctuations in the traffic flow. Compared with several benchmark models (e.g., artificial neural network, long short-term memory neural network, and DBN), the ELM-IBF model reveals better performance in forecasting single-step-ahead traffic volume and speed. Additionally, it is proved that the ELM-IBF model is capable of providing stable and high-quality results in multistep-ahead traffic flow prediction.

Exploration and evaluation of crowdsourced probe-based Waze traffic speed

ABSTRACT Real-time traffic information such as traffic speed is essential to a variety of practical applications. Because of the high installation and maintenance cost of convention data collecting methods, transportation engineers have sought alternative data sources to monitor traffic. Probe-based traffic data, such as Waze traffic data, could serve as alternative data sources in traffic management, but this source has not been thoroughly explored nor evaluated. Using the 10.8 mile stretch of I-40 in Knoxville, Tennessee, we compared the speed measurements from both Waze and Remote Traffic Microwave Sensors (RTMS) over two months and explored the characteristics of Waze traffic speed data. These are the main findings: 1) These two datasets showed a similar pattern with slight differences. Waze speeds tend to be higher than RTMS speeds for high speed, while Waze speeds are more likely to be similar or even lower than RTMS speeds for low speed; 2) several factors affecting the speed differences between RTMS speeds and Waze speeds were identified, such as Waze speed value, time of day (peak hour vs. non-peak hour), AADT (Annual Average Daily Traffic), and segment length; and 3) Waze reported the same speed for several successive reporting periods if the real-time speed is not available. The effective Waze sampling period is about two to four minutes. Waze speeds had more real-time speed observations during congested times, indicating that Waze speeds are more reliable for congested scenarios. The findings may lead to a better understanding of this source of data and any resulting analysis.

Lane-Level Traffic Speed Forecasting: A Novel Mixed Deep Learning Model

Lane-level traffic state prediction is one of the most essential issues in the connected automated vehicle highway systems. Accurate and timely traffic state prediction of the lane sections can assist the connected automated vehicles in planning the optimal route and making lane selection. In this article, we tackle the problem of forecasting lane-level short-term traffic speed and propose a novel mixed deep learning (MDL) model by coordinating the convolutional long short-term memory (Conv-LSTM) layers, convolutional layers, and a dense layer in an end-to-end structure. The introduction of the Conv-LSTM neural network enables the proposed MDL model to better capture the spatio-temporal characteristics and correlations of the dynamic lane-based traffic flow synchronously. To improve the efficiency of the proposed model, a feature correlation analysis method based on the maximum information coefficient is presented to measure the relevance between the historical traffic flows and the traffic speeds to be forecasted. Validated by the ground-truth traffic flow data collected by the remote traffic microwave sensors installed on the expressways in Beijing, the MDL model is capable of capturing the fluctuation of the lane-level traffic speeds at different types of lanes effectively during the whole day. Furthermore, the results confirm that the MDL model achieves better predictive performance than several state-of-the-art benchmark models in terms of prediction accuracy and space-time distributions. Our code and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/lwqs93/MDL</uri> .

Data Fusion for Multi-Source Sensors Using GA-PSO-BP Neural Network

The development of real-time road condition systems will better monitor road network operation status. However, the weak point of all these systems is their need for comprehensive and reliable data. For traffic data acquisition, two sources are currently available: 1) floating vehicles and 2) remote traffic microwave sensors (RTMS). The former consists of the use of mobile probe vehicles as mobile sensors, and the latter consists of a set of fixed point detectors installed in the roads. First, the structure of a three-layer BP neural network is designed to achieve the fusion of the floating car data (FCD) and the fixed detector data (FDD) efficiently. Second, in order to improve the accuracy of traffic speed estimation, a multi-source data fusion model that combines information from floating vehicles and microwave sensors, and that, by using GA-PSO-BP neural network is proposed. The proposed model has combined GA and PSO ingeniously. The hybrid model can not only overcome the difficulties of the traditional fusion model of its estimation inaccuracy, but also compensate the insufficiency of the traditional BP algorithm. Finally, this system has been tested and implemented on actual roads, and the simulation results show the accuracy of data has reached 98%.

A Hybrid Model for Lane-Level Traffic Flow Forecasting Based on Complete Ensemble Empirical Mode Decomposition and Extreme Gradient Boosting

Accurate and efficient lane-level traffic flow prediction is a challenging issue in the framework of the connected automated vehicle highway system. However, most existing traffic flow forecasting methods concentrate on mining the spatio-temporal characteristics of the traffic flow rather than increasing predictability of traffic flow. In this paper, we propose a novel hybrid model (CEEMDAN-XGBoost) for lane-level traffic flow prediction based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and extreme gradient boosting (XGBoost). The CEEMDAN method is introduced to decompose the raw traffic flow data into several intrinsic mode function components and one residual component. Then, the XGBoost methods are trained and make predictions on the decomposed components respectively. The final prediction results are obtained by integrating the prediction outputs of the XGBoost methods. For illustrative purposes, the ground-truth lane-level traffic flow data captured by remote traffic microwave sensors installed on the 3 rd Ring Road of Beijing are utilized to evaluate the effectiveness of the CEEMDAN-XGBoost model. The experimental results confirm that the CEEMDAN-XGBoost model is capable of fitting the complex volatility of traffic flow efficiently at different types of lane sections. Moreover, the proposed model outperforms the state-of-the-art models (e.g., artificial neural networks and long short-term memory neural network) and other XGBoost-based models in terms of prediction accuracy and stability.

Short-term prediction of lane-level traffic speeds: A fusion deep learning model

Accurate and robust short-term traffic prediction is an important part of advanced traveler information systems. With the development of intelligent navigation and autonomous driving, it is necessary to explore the lane-level predictions of traffic speeds. However, most existing traffic prediction models concentrate on forecasting the traffic flow characteristics of the entire road sections rather than those of certain lanes. This paper proposes a fusion deep learning (FDL) model to predict lane-level traffic speed. First, the entropy-based grey relation analysis is introduced to choose lane sections that are strongly correlated with the lane section to be predicted. Second, a two-layer deep learning framework is established by combining the long short-term memory (LSTM) neural network and the gated recurrent unit (GRU) neural network. Third, the ground-truth data of several lane sections captured by remote traffic microwave sensors (RTMS) on the 2nd Ring Road of Beijing are utilized to examine the FDL model and compare it with several benchmark models. The experimental result indicates that in addition to capturing the fluctuations of traffic speed at the lane level, the FDL model has better performance than the benchmark models in terms of prediction accuracy and stability.

A Kriging based spatiotemporal approach for traffic volume data imputation.

Along with the rapid development of Intelligent Transportation Systems, traffic data collection technologies have progressed fast. The emergence of innovative data collection technologies such as remote traffic microwave sensor, Bluetooth sensor, GPS-based floating car method, and automated license plate recognition, has significantly increased the variety and volume of traffic data. Despite the development of these technologies, the missing data issue is still a problem that poses great challenge for data based applications such as traffic forecasting, real-time incident detection, dynamic route guidance, and massive evacuation optimization. A thorough literature review suggests most current imputation models either focus on the temporal nature of the traffic data and fail to consider the spatial information of neighboring locations or assume the data follow a certain distribution. These two issues reduce the imputation accuracy and limit the use of the corresponding imputation methods respectively. As a result, this paper presents a Kriging based data imputation approach that is able to fully utilize the spatiotemporal correlation in the traffic data and that does not assume the data follow any distribution. A set of scenarios with different missing rates are used to evaluate the performance of the proposed method. The performance of the proposed method was compared with that of two other widely used methods, historical average and K-nearest neighborhood. Comparison results indicate that the proposed method has the highest imputation accuracy and is more flexible compared to other methods.

Estimating traffic conditions from smart work zone systems

ABSTRACTThis article evaluates the effectiveness of sensor network systems for work zone traffic estimation. The comparative analysis is performed on a work zone modeled in microsimulation and calibrated with field data from an Illinois work zone. Realistic error models are used to generate noisy measurements corresponding to Doppler radar sensors, remote traffic microwave sensors (RTMSs), and low energy radars. The velocity, queue length, and travel time are estimated with three algorithms based on (i) interpolation, (ii) spatio-temporal smoothing, and (iii) a flow model–based Kalman filter. A total of 396 sensor and algorithm configurations are evaluated and the accuracy of the resulting traffic estimates is compared to the true traffic state from the microsimulation. The nonlinear Kalman filter provides up to 30% error reduction over other velocity estimators when the RTMS sensor spacing exceeds two miles, and generally offers the best performance for queue and travel time estimation.

Spatial Copula Model for Imputing Traffic Flow Data from Remote Microwave Sensors.

Issues of missing data have become increasingly serious with the rapid increase in usage of traffic sensors. Analyses of the Beijing ring expressway have showed that up to 50% of microwave sensors pose missing values. The imputation of missing traffic data must be urgently solved although a precise solution that cannot be easily achieved due to the significant number of missing portions. In this study, copula-based models are proposed for the spatial interpolation of traffic flow from remote traffic microwave sensors. Most existing interpolation methods only rely on covariance functions to depict spatial correlation and are unsuitable for coping with anomalies due to Gaussian consumption. Copula theory overcomes this issue and provides a connection between the correlation function and the marginal distribution function of traffic flow. To validate copula-based models, a comparison with three kriging methods is conducted. Results indicate that copula-based models outperform kriging methods, especially on roads with irregular traffic patterns. Copula-based models demonstrate significant potential to impute missing data in large-scale transportation networks.

An Improved Fuzzy Neural Network for Traffic Speed Prediction Considering Periodic Characteristic

This paper proposes a new method in construction fuzzy neural network to forecast travel speed for multi-step ahead based on 2-min travel speed data collected from three remote traffic microwave sensors located on a southbound segment of a fourth ring road in Beijing City. The first-order Takagi–Sugeno system is used to complete the fuzzy inference. To train the evolving fuzzy neural network (EFNN), two learning processes are proposed. First, a $K$ -means method is employed to partition input samples into different clusters and a Gaussian fuzzy membership function is designed for each cluster to measure the membership degree of samples to the cluster centers. As the number of input samples increases, the cluster centers are modified and membership functions are also updated. Second, a weighted recursive least squares estimator is used to optimize the parameters of the linear functions in the Takagi–Sugeno type fuzzy rules. Furthermore, a trigonometric regression function is introduced to capture the periodic component in the raw speed data. Specifically, the predicted performance between the proposed model and six traditional models are compared, which are artificial neural network, support vector machine, autoregressive integrated moving average model, and vector autoregressive model. The results suggest that the prediction performances of EFNN are better than those of traditional models due to their strong learning ability. As the prediction time step increases, the EFNN model can consider the periodic pattern and demonstrate advantages over other models with smaller predicted errors and slow raising rate of errors.

Practical approach to determining traffic congestion propagation boundary due to traffic incidents

A practical approach for predicting the congestion boundary due to traffic incidents was proposed. Based on the kinematic wave theory and Van Aerde single-regime flow model, a model for estimating the congestion propagation speed for the basic road segment was developed. Historical traffic flow data were used to analyze the time variant characteristics of the urban traffic flow for each road type. Then, the saturation flow rate was used for analyzing the impact of the traffic incident on the traversing traffic flow at the congestion area. The base congestion propagation speed for each road type was calculated based on field data, which were provided by the remote traffic microwave sensors (RTMS), floating car data (FCD) system and screen line survey. According to a comparative analysis of the congestion propagation speed, it is found that the expressway, major arterial, minor arterial and collector are decreasingly influenced by the traffic incident. Subsequently, the impact of turning movements at intersections on the congestion propagation was considered. The turning ratio was adopted to represent the impact of turning movements, and afterward the corresponding propagation pattern at intersections was analyzed. Finally, an implementation system was designed on a geographic information system (GIS) platform to display the characteristics of the congestion propagation over the network. The validation results show that the proposed approach is able to capture the congestion propagation properties in the actual road network.

Analysis of Speed Differences in Data from Remote Traffic Microwave Sensors and Floating Car Data Systems on Expressways

The remote traffic microwave sensor (RTMS) and the floating car data (FCD) system are two important sources of traffic data; both provide key speed information. However, these two data processes gather data differently. The RTMS detects spot speeds at specific cross sections. The FCD system collects travel speed along a segment of a road link. Although the difference between time mean speed (TMS) and space mean speed (SMS) has been discussed for decades, the speed differences between RTMS and FCD have been underestimated in many engineering applications. This study examined the speed differences between the RTMS and FCD data on expressways in Beijing. First, the differences between the two data collections over 5 days were analyzed. The correlation between the difference and the value of the speeds was investigated. The relationships between TMS and SMS in existing studies were then compared with the relationship derived from the field data. It was found that the existing relationships between TMS and SMS were not valid for representing the relationship between the RTMS and FCD speeds. The flow–speed relationship from each data group was then investigated by using the Van Aerde traffic flow model; it was found that free-flow speed and speed at capacity determined on the basis of the RTMS data were significantly overestimated. It was inaccurate to apply the RTMS speed to the analysis of fundamental traffic flow diagrams. Finally, the repeatability and stability of the relationship between these two data groups were validated.

Simulation-based Variable Speed Limit Systems Modelling: An Overview and A Case Study on Istanbul Freeways

Abstract: Modern transportation systems aim at maximizing the use of available resources in a sustainable manner to deliver efficient and safe movement of traffic. Variable Speed Limit (VSL) system is one of the techniques adopted in order to improve mobility. In this study, we analyse this system using simulation techniques on a 5.2 kilometre section of Istanbul Freeway D100. Being one of the most congested cities in the world, Istanbul freeways provide an excellent opportunity to test the potential benefits of VSL systems. Latest advancements along with comprehensive literature of this field based on simulation are included in this study. Microscopic traffic simulation software VISSIM is used along with MATLAB to implement VSL algorithm based on volume, occupancy and average speed. Remote Traffic Microwave Sensor (RTMS) data is provided by Istanbul municipality which is used to calibrate VISSIM.Scenarios with and without VSL system were simulated for morning hours. It is concluded that driver compliance to VSLs is an important factor for better results. Although 100% driver Compliance Level (CL) for VSL results in significantly higher improvement in performance compared to lower compliance, it is not a practical approach therefore results at 75% and 50% CL has been discussed in this study. Evaluation of network performance is done in terms of Total Travel Time (TTT) in network along with volume, speed and occupancy. Results show reduction in TTT and occupancy level along with improvement in average speed and volume. Fuel consumption and emissions is also found to be reduced in the network indicating sustainable and environmental friendly mobility.

Application of an Intelligent Transportation System in a Travel Time Information System: Safety Assessment and Management

The research presented here evaluated road safety on the road sections included in the Intelligent Traffic Control System of the Podhale Region (ISSRRP) in Poland. This travel time information system consists of a remote traffic microwave sensor, cameras, as well as automatic plate number recognition on national roads with variable message signs and a mobile app to suggest alternative routes in the regional road network. The study analyzed changes in safety caused by transferring traffic volume from national to regional rural and suburban road networks. The assessment of the safety performance was performed with an empirical Bayes study, with periods of three years before and after the implementation of ISSRRP. No changes were identified in the safety performance of the national road network after to the introduction of ISSRRP. However, when the overall network is considered, a potential increase in the number of crashes may be expected, depending on the volume of traffic transferred from national to regional roads, and rural or suburban areas. Therefore, a new approach for system management was proposed, taking into account not only improvement in traffic flow, but also safety performance.

Framework model for time‐variant propagation speed and congestion boundary by incident on expressways

For the purpose of accurately capturing the evolution characteristics of the congestion on urban expressways under traffic incidents, this study developed a framework model for the time-variant propagation speed and congestion boundary based on shockwave model. An initial analysis demonstrated that the traffic demand and facility supply determine the propagation speed and boundary. The outflow at the incident section was considered, which is affected by the number of closed lanes, the proportion of buses, and the number of lane-changing vehicles. Additionally, the background demand varies with the time of day and the location due to a high density of ramps. The entry and exit flows of on-ramps and off-ramps under the traffic incident were shown to have a considerable impact on the congestion propagation. Consequently, the framework model was developed and parameters were estimated based on the field data of ring-road expressways in Beijing. For practical purpose, the data inputs were provided by the floating car system and remote traffic microwave sensor system. Three incidents on expressways were adopted to evaluate the capability of the model. Results showed that the proposed model is able to practically model the time-variant characteristics of the propagation speed and congestion boundary of traffic incidents.

Short-term prediction of border crossing time and traffic volume for commercial trucks: A case study for the Ambassador Bridge

Short-term forecasting of traffic characteristics, such as traffic flow, speed, travel time, and queue length, has gained considerable attention from transportation researchers and practitioners over past three decades. While past studies primarily focused on traffic characteristics on freeways or urban arterials this study places particular emphasis on modeling the crossing time over one of the busiest US–Canada bridges, the Ambassador Bridge. Using a month-long volume data from Remote Traffic Microwave Sensors and a yearlong Global Positioning System data for crossing time two sets of ANN models are designed, trained, and validated to perform short-term predictions of (1) the volume of trucks crossing the Ambassador Bridge and (2) the time it takes for the trucks to cross the bridge from one side to the other. The prediction of crossing time is contingent on truck volume on the bridge and therefore separate ANN models were trained to predict the volume. A multilayer feedforward neural network with backpropagation approach was used to train the ANN models. Predicted crossing times from the ANNs have a high correlation with the observed values. Evaluation indicators further confirmed the high forecasting capability of the trained ANN models. The ANN models from this study could be used for short-term forecasting of crossing time that would support operations of ITS technologies.

Empirical Evaluation of the Accuracy of Technologies for Measuring Average Speed in Real Time

A federal mandate challenges states to acquire and to disseminate reliable travel time–speed information with limited sensor infrastructure and resources; the mandate also opens the opportunity to look beyond traditional sensor technologies. Some of these new and promising travel data technologies include various deployments and combinations of GPS, probe vehicles, cellular devices, Bluetooth devices, radio frequency identification, automated license plate recognition (LPR), and even social media. To take on this challenge, the objective of this study was to provide several key considerations for evaluation of travel speed data for general cases. The key items included obtaining reliable ground truth data, transforming and comparing data sets, and evaluating data accuracy. Along with the explanation of these considerations, the results of a case study are provided to help illuminate the issues. The case study, which was performed in the vicinity of downtown Nashville, Tennessee, along Interstate 40 and Interstate 65 evaluated real-time travel time–speed data from Bluetooth sensors, from probes supplied by two major vendors, and from remote traffic microwave sensors. These data were compared with ground truth data from an LPR-based vehicle tracking system as well as video footage collected simultaneously. The paper discusses the reliability of ground truth, the advantages and shortcomings of different technologies, the evaluation of data accuracy methodologies, and future research directions.

Short-Term Speed Prediction Using Remote Microwave Sensor Data: Machine Learning versus Statistical Model

Recently, a number of short-term speed prediction approaches have been developed, in which most algorithms are based on machine learning and statistical theory. This paper examined the multistep ahead prediction performance of eight different models using the 2-minute travel speed data collected from three Remote Traffic Microwave Sensors located on a southbound segment of 4th ring road in Beijing City. Specifically, we consider five machine learning methods: Back Propagation Neural Network (BPNN), nonlinear autoregressive model with exogenous inputs neural network (NARXNN), support vector machine with radial basis function as kernel function (SVM-RBF), Support Vector Machine with Linear Function (SVM-LIN), and Multilinear Regression (MLR) as candidate. Three statistical models are also selected: Autoregressive Integrated Moving Average (ARIMA), Vector Autoregression (VAR), and Space-Time (ST) model. From the prediction results, we find the following meaningful results: (1) the prediction accuracy of speed deteriorates as the prediction time steps increase for all models; (2) the BPNN, NARXNN, and SVM-RBF can clearly outperform two traditional statistical models: ARIMA and VAR; (3) the prediction performance of ANN is superior to that of SVM and MLR; (4) as time step increases, the ST model can consistently provide the lowest MAE comparing with ARIMA and VAR.

Traffic Speed Time Series Short Term Forecasting Using Aggregated Model

This paper integrated superiority from time series model and least square support vector machine regression model with data aggregation for traffic speed short term forecasting. Based on the results of traffic data variations analysis, the practicability that speed data can be aggregated to several periods was confirmed, and aggregated model can be developed to forecast the speed with auto regression (AR) model and support vector machine regression (SVR). Then the speed data in case study were integrated to 4 periods at the location of Remote Traffic Microwave Sensors (RTMS) 2047 on 2nd Ring Road Expressway in Beijing. Arguments with coefficients from AR models then act as the independent variables of LSSVR in aggregated model. Short term traffic speed was predicted by aggregated model, and the results indicated that taking advantages of time periods variation rule inside the aggregated model would help save the model running time cost under the premise of accuracy with better prediction ability than LSSVR in certain conditions.

Analysis of Congestion Phenomena on the One Lane Dropped Motorway Merge without Ramp-metering in İstanbul

Motorway merges are typically congestion areas because of irregularities on lanes between upstream and downstream directions. At motorway merges, it is obvious that when the upstream and/or on-ramp flow is greater than the downstream (bottleneck) capacity, congestion arises. Therefore, queue will form and grow in relation with the demand and bottleneck capacity. The aim of this paper is to analyze the effect of mainstream and on-ramp flows on the congestion phenomena. As there is no ramp-metering application in Istanbul, on-ramp flow has an excessive effect on the congestion. In this study, macroscopic merge behavior is analyzed at one crucial motorway merge in Istanbul. Traffic data is obtained by Remote Traffic Microwave Sensors (RTMS) operated by the Municipality of Istanbul. RTMS data consists of volume, speed, occupancy and heavy vehicle counts per lane while minimum data collection interval is 2minutes. Examined motorway merge section, main stream and on-ramp flows are observed by separate RTMS. Whole year weekday data of 2012 is used for analysis. It is seen that mainstream flow rate changes from 3360 pcph to 6210 pcph before congestion depends on the on-ramp flow rate that varies from 1755 pcph to 3060 pcph. In addition, on-ramp ratio is found between 0.23 and 0.43 which cause congestion on this motorway merge.