클라우드 경로탐색을 이용한 미래 교통정보 예측 방법

In offer of the traffic information to the drivers, it is the big factor that decides quality of the traffic information whether the traffic information and conformity with the real condition experienced by a drivers. The OD time is useful information because the drivers can know the time of arrival to the destination. However only using the real-time traffic information, it is different from the time of arrival to display at origin and the time of arrival at destination because it can’t consider the change of traffic condition when they arrive at the destination. So it is generally to raise the benefit of the drivers with the traffic information prediction that can decrease the difference. But now (in particularly the prediction) in evaluating the quality of the traffic information, there are methods to evaluate the traffic jam but not any effective methods to evaluate the traffic information with link travel time. This article suggests the method of evaluating the quality of the prediction with the RMSE in addition to the standard deviation and considers the quality of the traffic information prediction that can offer useful information to the drivers.

Information and communication technologies have improved the quality of Intelligent Transportation Systems (ITS). The real-time traffic information has traditionally been collected via stationary vehicle detectors or GPS-based probe cars. Compared to the traditional ways, estimating traffic information from Cellular Floating Vehicle Data (CFVD) is more cost-effective, and easier to acquire. In this paper, this study proposes a novel approach to evaluate the relation of call arrival, handover, traffic flow, and traffic density. Moreover, the traffic speed is estimated by the proposed approach according to CFVD. Through the analytical analysis, this study analyzes the effects of traffic information (e.g. traffic flow and vehicle speed) and communication behaviors (e.g. call arrival rate and call holding time) on handovers and call arrivals. In the simulation, this study compares the estimated traffic information with the real traffic information. The experiment results show that the accuracy of traffic speed estimation is 89.75%. Therefore, the proposed approach can be used to estimate traffic speed from CFVD for ITS.

The amount of traffic on the Internet has been increasing both in quantity and in fluctuation as the devices connected to the Internet and the services on the Internet become popular. Predictive Traffic Engineering (TE) is one approach to accommodating fluctuating traffic without causing congestion. Prediction accuracy is important for predictive TE. Real-world information is useful for the prediction of future traffic. Although the real-world information may contribute to the accurate prediction of future traffic, it is difficult to model the relation between these two types of data. Therefore, we propose a prediction method inspired by the cognitive process of the human brain, which makes decisions from uncertain information. Our method defines multiple states based on the monitored information including both traffic and real-world information and subsequently learns the future traffic corresponding to each state. Then, our method predicts future traffic by deciding the current state from the traffic and real-world information by using a process inspired by the cognitive process of the human brain. Finally, our method allocates resources based on the future traffic corresponding to the states of which the confidence levels are high. We evaluated our method by simulation. The results demonstrate that our method avoids congestion without requiring a large amount of additional resources; the amount of resources required to avoid congestion is reduced by 25 % compared with the predictive TE using only past traffic information.

Providing reliable predictive traffic information is a crucial element for successful operation of intelligent transportation systems. However, there are difficulties in providing accurate predictions mainly because of limitations in processing data associated with existing traffic surveillance systems and the lack of suitable prediction techniques. This study examines different aggregation intervals to characterize various levels of traffic dynamic representations and to investigate their effects on prediction accuracy. The relationship between data aggregation and predictability is explored by predicting travel times obtained from the inductive signature-based vehicle reidentification system on the I-405 freeway detector test bed in Irvine, California. For travel time prediction, this study employs three techniques: adaptive exponential smoothing, adaptive autoregressive model using Kalman filtering, and recurrent neural network with genetically optimized parameters. Finally, findings are discussed on s...

Location based services (LBS) are capturing global spotlights increasingly, in which users tend to pick up navigation service as their favorites. This paper examines the dynamic routing problems based on real-time traffic information in LBS. At first, the overall structure of dynamic navigation system is illustrated, which is composed of four ingredients: traffic data collection, digital road map, static routing and dynamic re-routing. Traffic data collection is the task of traffic information center (TIC), where various sources of data are fused into link travel times that are used as criteria to choose candidates in path determining. Digital road map includes digital road network and historical traffic data, where the topology relationship of road network is elementarily explored and the method to represent statistical traffic data is referred to. Routing with historical traffic data and dynamic re-routing with live traffic data are two main functions of dynamic navigation service. The flow of dynamic re-routing algorithm is exhibited. Lastly, a first-in-first-out (FIFO) time-depend shortest path algorithm is discussed for dynamic routing, which adopts the adaptive A^* algorithm based on binary heap priority queue and RB-tree.

Accurate on-road vehicle speed prediction is important for many intelligent vehicular and transportation applications. It is also challenging because the individual vehicle speed is affected by many factors, e.g., traffic speed, vehicle type, and driver's behavior, in either deterministic or stochastic ways. This paper proposes a novel vehicle speed prediction method in the context of vehicular networks, where the real-time traffic information is accessible. Traffic speeds of following road segments are first predicted by Neural Networks (NNs) based on historical traffic data. Hidden Markov models (HMMs) are trained by the Baum-Welch algorithm with historical traffic and vehicle data to present the statistical relationship between vehicle speed and traffic speed. The forward-backward algorithm is applied on HMMs to extract vehicle's speed on each road segment along the driving route. Simulation is set up on the SUMO microscopic traffic simulator with the application of a real Luxembourg highway network and traffic count data. The vehicle speed prediction result shows that our proposed method outperforms other ones in terms of prediction accuracy.

Adaptive real-time energy management control strategy based on fuzzy inference system for plug-in hybrid electric vehicles

For providing drivers with robust traffic information and Optimizing the energy management of Hybrid Electric Vehicles (HEVs), it is important to predict traffic information accurately with past traffic information. As acquisition of the traffic information have been easier by the development of Intelligent Transportation System (ITS), active study on traffic prediction is currently underway. Multi-Layer Perceptron (MLP) model have been widely utilized for predicting traffic information since it is appropriate to represent the non-linear characteristics inherent in traffic prediction. However, the MLP model doesn't reflect local dependencies of traffic data and is prone to noise in traffic data. Convolutional Neural Networks (CNN) based model, on the other hand, can capture the local dependencies of traffic data and is less prone to disturbance in data. In this paper, we use temporal data and speed data collected on main roads in Seoul, South Korea to construct traffic prediction models. The speed data which are collected by every 5 minutes are provided by Ministry of Land, Infrastructure and Transport in South Korea. We construct the CNN based model and two MLP models which predict traffic speed and compare performance of the prediction models in this paper. The comparison results show that the CNN based model's prediction performance is higher than the prediction performance of the other two MLP models.

We analyze how traffic congestion affects the usage of cruise control in real-traffic situations. Usually, a negative relationship is assumed, but empirical evidence in naturalistic settings is rare. We make use of a large sample of truck drivers ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$N$</tex-math></inline-formula> = 562) in Germany. We take advantage of the volatile traffic density imposed by the first implementation of COVID-19-related measures in Germany and analyze truck drivers resulting application of cruise control using random effects models. We match official traffic density information and the share of cruise control usage as recorded by the telematics information of each truck per day. We find that on average traffic density does have the expected effect: more traffic leads to a lower usage of cruise control. However, we find great heterogeneity among drivers and a strong tendency to react nonlinear to changes in traffic density. Additionally, comparing traffic types, heavy-goods vehicle traffic density has a stronger impact on drivers' usage of cruise control than private traffic density. Again, not all drivers react similarly: we investigate eight different reaction patterns to varying types of congestion. Our results show that even in a favorable environment such as low traffic congestion, the use of cruise control cannot be taken for granted: about 25%–34% of the drivers (depending on traffic type) do not respond to changes in traffic density at all. Our results may help to inform models of traffic flow and traffic automation and may serve as a premise for more realistic assumptions about human behavior in traffic.

On stochastic transport network, travelers tend to reserve travel time budget (TTB) for every alternative route, to assure their on-time arrive with a predefined confidence level. This paper incorporates the concept of TTB into a deterministic nonlinear dynamic system, to model the day-to-day evolution process of travelers' risk-taking route choices on stochastic degradable road network. This paper also introduces consistent traffic information prediction, which can be provided by Advanced Traveler Information Systems (ATIS), into the dynamic system to investigate its influence on travelers' route choice behaviors and the corresponding day-to-day network flow evolutions. Illustrative examples are presented to demonstrate that, the consistent predictive traffic information can help to stabilize day-to-day network flow fluctuations, while travelers' extreme risk-averse route choice behaviors, on the other hand, would cause greater network flow fluctuations.

Traffic speed estimation based on normal location updates and call arrivals from cellular networks

The accurate short-term traffic flow prediction can provide timely and accurate traffic condition information which can help one to make travel decision and mitigate the traffic jam. Deep learning (DL) provides a new paradigm for the analysis of big data generated by the urban daily traffic. In this paper, we propose a novel end-to-end deep learning architecture which consists of two modules. We combine convolution and LSTM to form a Conv-LSTM module which can extract the spatial-temporal information of the traffic flow information. Furthermore, a Bi-directional LSTM module is also adopted to analyze historical traffic flow data of the prediction point to get the traffic flow periodicity feature. The experimental results on the real dataset show that the proposed approach can achieve a better prediction accuracy compared with the existing approaches.

Traffic information prediction is one of the most essential studies for traffic research, operation and management. The successful prediction of traffic speed is increasingly significant for the benefits of both road users and traffic authorities. However, accurate prediction is challenging, due to the stochastic feature of traffic flow and shallow model structure. Furthermore, environmental factors, such as rainfall influence, should also be incorporated to improve accuracy. Inspired by deep learning, this paper investigates the performance of deep belief network (DBN) and long short‐term memory (LSTM) to conduct short‐term traffic speed prediction with the consideration of rainfall impact as a non‐traffic input. The deep learning models have the ability to learn complex features of traffic flow pattern under various rainfall conditions. To validate the performance of rainfall‐integrated DBN and LSTM, the traffic detector data from an arterial in Beijing are utilised for model training and testing. The experiment results indicate that with the combination input of speed and additional rainfall data, deep learning models have better prediction accuracy over other existing models, and also yields improvements over the models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time‐series characteristics of traffic speed data.

Systeme d'Information Routiere Intelligible aux Usagers (SIRIUS) is the largest urban field operational test of the advanced traveler information and automated traffic management system in Europe. With variable-message signs, SIRIUS has been in operation in the Paris region for 3 years. A preliminary investigation of the effectiveness of the SIRIUS system in traffic management is presented. The extent to which drivers respond to real-time traffic information and the consequential changes in link flow under SIRIUS is also presented. Time-series traffic data were analyzed to measure changes in mean flow rates at a selected link. It was found that variable-message signs influence drivers to choose less congested routes when drivers are provided with real-time traffic information, and that a driver's decision to divert is closely associated with the information pertaining to the level of congestion. In the Paris region, drivers received information on the length of the queue at the time of this study. As congestion becomes heavier, drivers are more likely to respond to variable-message signs. According to the data analysis, a queue length of 3 km seems to be a threshold at which a significant number of drivers choose to use an alternative route.

Building a traffic monitoring system for intelligent transportation systems (ITS) in the developing smart cities has drawn in a mass of consideration in the latest past. Since the majority of cities in the world are observing the increasing number of vehicles on the road, they are tending to accept an intelligent transportation system for resolving tedious issues like traffic density, count of traffic lines and their length, the standard speed of the traffic, and increase in the number of vehicles during weekends or for a particular time span in a day. Smart transportation systems are provided with traffic pictures and recordings by installed cameras on roads or signals. Also, different types of sensor-actuator pairs help check and deal with traffic issues. This paper proposed a method that uses customized convolution neural network (CCNN) on traffic images to classify images as per the traffic density and thereby provide driving assistance. The proposed system in the paper can monitor traffic using videos captured by installed cameras and then classify the current traffic situation into categories of high, medium, and low categories. The aim is to use this as a model to provide traffic density information from various places to expert systems and take other important decisions regarding traffic control. NVIDIA graphics processing unit (GPU) is used to parallelize the training process and implement complex deep neural networks to obtain better accuracy. Performance evaluation of the proposed system is done on a real-time dataset containing recorded footage of traffic from Pune city (India) and recorded footage by highway CCTVs at Seattle, WA, obtained from the Washington State Department of Transport. Experiment results classify traffic density into high, medium, and low based on existing traffic and predict it correctly up to 99.6%. Obtained testing accuracy is much better than the results given by existing algorithms.KeywordsDeep learningIntelligent traffic systemConvolutional neural networkPattern recognitionComputer visionTraffic image analysis