Cellular Network Based Real-Time Urban Road Traffic State Estimation Framework Using Neural Network Model Estimation

Uncertainty quantification of reservoir performance using machine learning algorithms and structured expert judgment

The road traffic state is usually analyzed from a temporal and macroscopic perspective; however, traffic flow parameters, such as density and spacing, can explain the evolution of traffic states from the microscopic perspective and the spatial distribution of vehicles in lanes. In this paper, we attempt to take both temporal and spatial characteristics into consideration simultaneously, and a parameter is defined as the traffic spatiotemporal state of urban road sections to represent the operational status of road traffic, using advanced prediction techniques to estimate its short-term trends. An estimation method is constructed for the traffic spatiotemporal state considering travel times, speeds, and queuing situations from temporal and spatial perspectives. Then, based on Takens’ theorem and the single variable phase space, the phase space of multiple traffic parameters is reconstructed and the chaotic characteristics are analyzed. Next, an LSTM prediction model is constructed based on the phase space reconstruction of multiple variables, and the traffic parameters are predicted by empirical analysis. The results show the proposed estimation method has a significantly improved accuracy. Finally, combined with RFID data, the traffic spatiotemporal state of the case section is calculated, which provides a theoretical basis and practical reference for road traffic state evaluations.

This paper presents an adaptable roadside vehicle detection and speed estimation system for various traffic conditions on urban roads based on tri-axial anisotropic magnetoresistive sensors and wireless sensor network. The system consists of one master node and two sensor nodes, which are placed along the roadsides and can measure the earth's local magnetic field disturbance caused by passing vehicles. A dynamic threshold detection algorithm is proposed for vehicle detection, especially considering the actual variable traffic condition. The vehicle speed is estimated on the basis of the maximum values and the cross correlation of effective parts extracted from two sensor signals. We have tested the vehicle information at several roads under different traffic conditions. Validation study has revealed a high detection accuracy of 97.92% when using a dynamic threshold compared with 92.3% when using a fixed threshold. And, the average accuracy of speed estimation can reach up to 97.11% on the roads. The proposed algorithm has a significant increase in accuracy, reliability, and practicability compared with the fixed threshold algorithm.

This paper proposes a method for estimating the speed and position of unsampled vehicles using sampled data from connected automated vehicles (CAVs). The determination of vehicle speed and position on the road is a challenging and crucial task, as they can effectively reflect traffic flow characteristics and contribute to traffic state estimation and intersection signal timing optimization. Connected automated vehicles have the capability to upload their own trajectory data while also capturing trajectory data of surrounding vehicles through onboard sensors. Therefore, this paper proposes a novel approach to estimate the speed and position of unsampled vehicles. Firstly, using real vehicle trajectory data, the correlation between the velocity of following vehicles and the velocity of leading vehicles under different densities is analyzed, leading to the development of a velocity estimation model incorporating a speed correction factor. Secondly, the correlation between time headway, the rate of change of following vehicle acceleration, and traffic density is examined. To address the issue of heterogeneous behavior in vehicle following described by the Intelligent Driver Model (IDM), a real-time optimization model for estimating vehicle position by optimizing IDM parameters is proposed. The velocity estimation model and the position estimation model are summarized as two nonlinear optimization problems. Finally, the proposed method is validated using actual vehicle trajectory data. Experimental results demonstrate that when the number of connected automated vehicles (CAVs) is 2, the proposed method reduces the average absolute error by 30.73% and the standard deviation of the average absolute error by 42.8% compared to a linear model-based speed estimation method under different density conditions. Compared to a method that estimates vehicle position by calibrating desired gaps, the proposed method reduces the average absolute error by 38.2% and the standard deviation of the average absolute error by 41.7% under different density conditions. Furthermore, the proposed method exhibits good practicality under different CAV penetration rates.

Artificial neural network modeling of photocatalytic removal of a disperse dye using synthesized of ZnO nanoparticles on montmorillonite

Data-driven analysis of weather impacts on urban traffic conditions at the city level

Evaluating traffic networks is crucial for administration of roadway systems, to better address congestion, safety, and air quality issues around the globe. However, challenges in implementation abound, including major investment costs, large and dynamic data streams and a need for real-time response. Recently developed Global Positioning System (GPS) data loggers are a promising tool for traffic monitoring, thanks to their low cost, ready availability on smartphones, and ability to simultaneously track many travelers and vehicles, relative to expensive, built-in traffic GPS. GPS data from many travelers provides real-time details of traffic conditions and can improve active traffic management using various big-data analytics. We demonstrate how to couple such GPS data to estimate relative roadway speeds in order to improve system management. By analyzing real-time traffic surveillance software with high data coupling and concurrent processing, a new coupling method for real-time traffic evaluation is proposed. Experimental results show efficient coupling of all available GPS data with road condition can improve traffic state estimation accuracy. This new method may increase matching accuracy by more than 1 m in vehicle position. Over 98% of GPS data can be successfully matched to service routes when the low-cost GPS devices are used to detect real-time traffic conditions. The results of traffic network evaluation could well serve as a driving assistant for connected and autonomous vehicles (C/AVs) and other traffic operations.

Road damage indicates a condition where the structural and functional roads are no longer able to provide optimal service to traffic crossing the road. Traffic conditions and the types of vehicles that will cross a road greatly affect the design of construction planning and road pavement made. Asphalt or concrete pavement has frequent damage due to water entering the pavement so that it becomes damaged, this can be seen on Munif Rahman Street, Palu City, Central Sulawesi Province at Sta 0+000 – 2+200. The purpose of this study was to determine the relationship between vehicle speeds caused by various road damage conditions such as potholes, edge cracks, grain release, crests on Road Munif Rahman, Palu City, especially Sta. 0+000 – 2+200. The method used to determine the speed of the vehicle is the Spot Speed, and the Pavement Condition Index (PCI) method to determine the condition of the road pavement. From the results and discussion, some conclusions that can be drawn are the regression equation obtained is y = -0.0029x2 + 0.4101x + 10.841. R2 (R Square) obtained is R² = 0.3789. This means that the relationship between road damage and vehicle speed is 38% (poor), showing the relationship between the level of road damage and vehicle speed, that the lower the PCI value, the slower the vehicle speed as in Sta 1+900 to 2+000 with a PCI value of 13. (very poor) then obtained a vehicle speed of 14.611 km/hour. The results are inversely proportional to the influence of several factors in the research conditions, namely Sta. 1+300 to 1+400 with a PCI value of 33 (medium) then the vehicle speed is 26,800 km/hour, indicating that the lower the PCI value, the faster the vehicle speed, this is influenced by the driver, obstacles, and vehicle disturbances along the way. Munif Rahman street, Palu city.

In this paper, we take the urban road network as the object, a further study on the method of traffic signal self organization under the condition of traffic state identification and local congestion. In the urban road traffic state identification study, according to the need of traffic signal control, respectively from qualitative and quantitative point of view, the urban road traffic state is defined. In order to be able to obtain real-time traffic data as the foundation, design urban road traffic state evaluation index system. Based on the current mainstream micro traffic simulation software VB and VISSIM as the tool to build the experimental platform, and set up the UTC-CI (Urban Traffic Control for Congested Intersections) experimental environment, the above method is verified by simulation. The results show that the traffic state identification method and the related signal control method have the expected effect in reducing congestion duration.

Intelligent transportation systems (ITS) depend on precise vehicle identification and speed estimation to provide real-time traffic monitoring, accident avoidance, and effective traffic flow management. This paper, a novel deep neural network (DNN)-based method for real-time vehicle detection and speed estimate is presented. For accurate vehicle detection, we use cutting-edge object detection models like YOLOv5, and we use computer vision algorithms to determine a vehicle's speed from video frames. The technology operates reliably in a range of environmental circumstances and processes real-time traffic video streams. High detection accuracy (above 95%) and accurate speed estimation with an average error margin of less than 5 km/h are demonstrated by the experimental findings. A scalable and economical architecture for traffic surveillance applications is provided by the suggested approach.

Probe vehicle-based traffic state estimation method with spacing information and conservation law

The paper predicts the shear strength of high-strength steel fiber-reinforced concrete deep beams. It studies the effect of clear span-to-overall depth ratio on shear capacity of steel fiber high-strength deep beams using artificial neural network (ANN8). The three-layered model has eight input nodes which represent width, effective depth, volume fraction, fiber aspect ratio and shear span-to-depth ratio, longitudinal steel, compressive strength of concrete, and clear span-to-overall depth ratio. The model predicts the shear strength of high-strength steel fiber deep beams to be reasonably good when compared with the results of proposed equations by researchers as well as the results obtained by neural network (ANN7) which is developed for seven inputs excluding span-to-depth ratio. The developed neural network ANN8 proves the versatility of artificial neural networks to establish the relations between various parameters affecting complex behavior of steel fiber-reinforced concrete deep beams and costly experimental processes.

Artificial neural network modeling of the water quality index for Kinta River (Malaysia) using water quality variables as predictors

Due to the funds problem, it is impossible to have acceleration sensors installed on bridge's every cable. In order to get each cable's tension, a three-layer BP neural network model is presented and the neural network with a number of measured data is trained. Using this neural network model, the cable tension can be predicted without any acceleration sensor installed. Then, the neural network model is certificated by using the measured data. By comparison with measured data and the predicted data, the predicted cable tensions by the neural network are credible.

Physical properties and coating thickness of the materials are measured using the eddy current principles. Most publications on the eddy current method are directed toward air-core coils operated at high frequency. But low-frequency ferrite-core probes provide the advantage of enhanced signal-to-noise ratio and increased resolution for electronic detection. A ferrite-core probe design has several parameters, which includes the selection of ferrite material and the design of the probe structure and core. In this article a total of five variables, which are most influential on probe performance, were considered. A three-layer back-propagation neural network model is used to correlate these variables to probe performance using the data generated based on experimental observations.