An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

Prediction of Traffic Volume of Motor Vehicles Based on Mobile Phone Signaling Technology

Urban traffic volume detection is an essential part of trafficplanning in terms of urban planning in China. To improve the statisticsefficiency of road traffic volume, this thesis proposes a method for predictingmotor vehicle traffic volume on urban roads in small and medium-sizedcities during the traffic peak hour by using mobile signal technology. Themethod is verified through simulation experiments, and the limitations andthe improvement methods are discussed. This research can be divided intothree parts: Firstly, the traffic patterns of small and medium-sized cities areobtained through a questionnaire survey. A total of 19745 residents weresurveyed in Luohe, a medium-sized city in China and five travel modes oflocal people were obtained. Secondly, after the characteristics of residents’rest and working time are investigated, a method is proposed in this studyfor the distribution of urban residential and working places based on mobilephone signaling technology. Finally, methods for predicting traffic volume ofthese travel modes are proposed after the characteristics of these travel modesand methods for the distribution of urban residential and working placesare analyzed. Based on the actual traffic volume data observed at offlineintersections, the project team takes Luohe city as the research object and itverifies the accuracy of the prediction method by comparing the predictiondata. The prediction simulation results of traffic volume show that the averageerror rate of traffic volume is unstable. The error rate ranges from 10% to 30%.In this thesis, simulation experiments and field investigations are adopted toanalyze why these errors occur.

Integrated Application of Statistical Method Used in Predicting the Lanes＇ Traffic Volume of Non-detector Intersections

Based on the relationships between the lanes of signal-controlled intersections, we utilize the integration method of cluster analysis and stepwise regression and the integration method of cluster analysis and the principal component analysis method to predict the lanes＇ traffic volume of non-detector isolated controlled intersections. The results are examined by the real-time lanes＇ traffic volume data of the road network of Nanjing City. The problem of the lanes＇ traffic volume prediction of non-detector isolated signal-controlled intersections was resolved which can be widely used in urban traffic flow guidance and urban traffic control in cities.

Influence of Traffic Volume on Fugitive Road Dust Emissions in Beijing, China

Eighty sites were set up to monitor road dust fall and 80 locations were selected to sample silt loading in April, August, and November 2007 and January 2008 in the Beijing metropolitan area. Fugitive road dust emission strengths were calculated using the AP-42 emission factor model. Silt loading on Beijing urban roads was typically less than 1.0 g/m^2, the PM10 emission strength was typically less than 100 kg/km·day, and road dust fall was typically less than 40 t/km^2·30day. The relationships between traffic volume, silt loading, fugitive road dust emission strength and road dust fall were studied in the Beijing metropolitan area. The results indicate that silt loading and emission factors are negatively correlated with traffic volume, but the PM10 emission rate and road dust-fall are positively correlated with traffic volume.

A Hybrid Geostatistical Method for Estimating Citywide Traffic Volumes - A Case Study of Edmonton, Canada

Traffic volume information has long played an important role in many transportation related works,such as traffic operations,roadway design,air quality control,and policy making.However,monitoring traffic volumes over a large spatial area is not an easy task due to the significant amount of time and manpower required to collect such large-scale datasets.In this study,a hybrid geostatistical approach,named Network Regression Kriging,has been developed to estimate urban traffic volumes by incorporating auxiliary variables such as road type,speed limit,and network accessibility.Since standard kriging is based on Euclidean distances,this study implements road network distances to improve traffic volumes estimations.A case study using 10-year of traffic volume data collected within the city of Edmonton was conducted to demonstrate the robustness of the model developed herein.Results suggest that the proposed hybrid model significantly outperforms the standard kriging method in terms of accuracy by 4.0%overall,especially for a large-scale network.It was also found that the necessary stationarity assumption for kriging did not hold true for a large network whereby separate estimations for each road type performed significantly better than a general estimation for the overall network by 4.12%.

Long-term Traffic Volume Prediction Based on K-means Gaussian Interval Type-2 Fuzzy Sets

This paper uses Gaussian interval type-2 fuzzy se theory on historical traffic volume data processing to obtain a 24-hour prediction of traffic volume with high precision. A K-means clustering method is used in this paper to get 5 minutes traffic volume variation as input data for the Gaussian interval type-2 fuzzy sets which can reflect the distribution of historical traffic volume in one statistical period. Moreover, the cluster with the largest collection of data obtained by K-means clustering method is calculated to get the key parameters of type-2 fuzzy sets, mean and standard deviation of the Gaussian membership function.Using the range of data as the input of Gaussian interval type-2 fuzzy sets leads to the range of traffic volume forecasting output with the ability of describing the possible range of the traffic volume as well as the traffic volume prediction data with high accuracy. The simulation results show that the average relative error is reduced to 8% based on the combined K-means Gaussian interval type-2 fuzzy sets forecasting method. The fluctuation range in terms of an upper and a lower forecasting traffic volume completely envelopes the actual traffic volume and reproduces the fluctuation range of traffic flow.

Air Traffic Volume and Air Traffic Control Human Errors

Navigable airspaces are becoming more crowded with increasing air traffic, and the number of accidents caused by human errors is increasing. The main objective of this paper is to evaluate the relationship between air traffic volume and human error in air traffic control (ATC). First, the paper identifies categories and elements of ATC human error through a review of existing literature, and a study through interviews and surveys of ATC safety experts. And then the paper presents the results of an experiment conducted on 52 air traffic controllers sampled from the Korean ATC organization to find out if there is any relationship between traffic volume and air traffic controller human errors. An analysis of the experiment clearly showed that several types of ATC human error are influenced by traffic volume. We hope that the paper will make its contribution to aviation safety by providing a realistic basis for securing proper manpower and facility in accordance with the level of air traffic volume.

Prediction of Railway Passenger Traffic Volume

The current situation of the railway passenger traffic (RPT) and the traffic marketing is analyzed. The grey model theory is adopted to establish a prediction model for the railway passenger traffic volume (RPTV).The RPTV from 2001 to 2005 is predicted with the proposed model, and a few suggestions are put forward.

Transit Bus and Pedestrian Safety Analysis in the Context of Operator Improvements and Traffic Volume Assessment

Pedestrian safety related to public bus transit is an integral part of promoting sustainability especially in the urban setting. This concept has received significant attention within the last decade as transit agencies strive to make their systems more sustainable and safer at the same time. This study examined pedestrian collisions related to public transit buses in Philadelphia over a three-year study period from 2008 to 2011. The objective is to perform a detailed analysis on crash records, which provides the foundation on statistics for bus-pedestrian collision to allow for future studies in modeling work in this field. Results of this research provided insights on bus-pedestrian collisions in terms of bus maneuver, cause of crash, impact point of bus, and relation to hourly traffic volume. A strong correlation was found between traffic volume and bus-pedestrian collision rate in terms of hours of the day. For any given hour, an increase in collision frequency was found if the traffic volume exceeds a threshold of 5% of its average annual daily traffic. This serves as an indicator of locations that pedestrians are vulnerable at. Analyses were conducted to the fullest extent allowable by the limited dataset. This study presents findings that can be future developed and investigated in future studies. Additionally, countermeasures are recommended in each section that presents a critical area to address.

Comparison between Neural Network and Adaptive Neuro-Fuzzy Inference System for Forecasting Chaotic Traffic Volumes

This paper applies both the neural network and adaptive neuro-fuzzy inference system for forecasting short-term chaotic traffic volumes and compares the results. The architecture of the neural network consists of the input vector, one hidden layer and output layer. Bayesian regularization is employed to obtain the effective number of neurons in the hidden layer. The input variables and target of the adaptive neuro-fuzzy inference system are the same as those of the neural network. The data clustering technique is used to group data points so that the membership functions will be more tailored to the input data, which in turn greatly reduces the number of fuzzy rules. Numerical results indicate that these two models have almost the same accuracy, while the adaptive neuro-fuzzy inference system takes more time to train. It is also shown that although the effective number of neurons in the hidden layer is less than half the number of the input elements, the neural network can have satisfactory performance.

Analysis and modeling of highway truck traffic volume variations during severe winter weather conditions in Canada

This paper investigates the impact of cold and snow on daily and hourly truck traffic volume on a primary highway in Alberta, Canada. This research is based on a detailed case study of 5 years of weigh-in-motion data recorded continuously at Leduc site on Highway 2A. Influence of the winter conditions on truck type distribution is examined by classifying trucks into single-unit trucks, single-trailer, and multi-trailer units. It is evident from the study that proportion of the three truck classes in the total truck traffic remained essentially stable over the study period （2005-2009）. Dummy-variable regression models are used to relate daily and hourly truck traffic volume with snowfall and categorized cold as independent variables. The statistical significance of all the independent variables used in the model is established by conducting tests such as R2, F test, incremental F test, and t test. The study results suggested that the truck volume is not significantly affected by the normal snowfall or the typical cold temperatures, i.e., average daily snowfall about less than 15 cm or temperatures higher than -25 ℃ are not likely to affect the truck traffic patterns. It is believed that the findings of this study can benefit highway agencies in developing programs and policies for efficient monitoring of truck traffic throughout the year and snow removal during the winter season in Canada.

A Light Weight Traffic Volume Prediction Approach Based on Finite Traffic Volume Data

As one of the key technologies of intelligent transportation systems, short-term traffic volume prediction plays an increasingly important role in solving urban traffic problems. In the last decade, many approaches were proposed for the traffic volume prediction from different perspectives. However, most of these approaches are based on a large amount of historical data. When there are only finite collected traffic data, they cannot be well trained, so the prediction accuracy of these approaches will be poor. In this paper, a tensor model is proposed to capture the change patterns of continuous traffic volumes. From collected traffic volume data, the element data are extracted to update the corresponding elements of the tensor model. Then, a tucker decomposition and gradient descent based algorithm is employed to impute the missing elements of the tensor model. After missing element imputation, the tensor model can be directly applied to the short-term traffic volume prediction through searching the corresponding elements of the model and the storage cost of the model is low. Our model is evaluated on real traffic volume data from PeMS dataset, which indicates that our model has higher traffic volume prediction accuracy than other approaches in the situation of finite traffic volume data.

Assessing the visualization of space and traffic volume using GIS-based processing and visibility parameters of space syntax

Streets and physical layouts can be inherent in a sustainable city by emphasizing the use of space with planned strategies by promoting the movement of people and social behaviors for enhancing an economic structure.An analysis of the space layout is beneficial for defining the urban areas that can affect street behavior.A GIS incorporated with a space syntax can help to propagate the effectiveness of a spatial analysis in a study on urban spaces.The integration of the computational pieces of both a GIS analytical tool and space syntax parameters will stimulate research oriented urban systems and spatial morphologies combined with a spatial database.However,the development of livability can be affected by a set of parameters that define the used space.Thus,this paper was aimed at examining the space syntax parameters for space visualization to evaluate street behavior using the GIS processing and space syntax methods.In this study,a spatial analysis was used to generate spatial information on traffic volume,while a space syntax was used to test the street behavior.Also,a predictive analysis was conducted to identify the correlation between traffic behavior and a set of parameters.The results showed that integration and direct visibility were significant to the traffic volume.Most of the streets that were linked to the commercial area showed high integration and direct visibility,which increased by more than half,compared with the unlinked areas.Based on the statistical analysis,both parameters recorded aprobability of less than 5%.The results showed that any space designed with a continuous,direct and clear traffic volume will lead to increased integration and direct visibility,thus influencing a natural vehicle movement.

An estimation of vehicle kilometer traveled and on-road emissions using the traffic volume and travel speed on road links in Incheon City

The objective of this study is to estimate the vehicle kilometer traveled（VKT） and on-road emissions using the traffic volume in urban. We estimated two VKT; one is based on registered vehicles and the other is based on traffic volumes. VKT for registered vehicles was 2.11 times greater than that of the applied traffic volumes because each VKT estimation method is different. Therefore, we had to define the inner VKT is moved VKT inner in urban to compare two values. Also, we focused on freight modes because these are discharged much air pollutant emissions. From analysis results, we found middle and large trucks registered in other regions traveled to target city in order to carry freight, target city has included many industrial and logistics areas. Freight is transferred through the harbors,large logistics centers, or via locations before being moved to the final destination. During this process, most freight is moved by middle and large trucks, and trailers rather than small trucks for freight import and export. Therefore, these trucks from other areas are inflow more than registered vehicles. Most emissions from diesel trucks had been overestimated in comparison to VKT from applied traffic volumes in target city. From these findings, VKT is essential based on traffic volume and travel speed on road links in order to estimate accurately the emissions of diesel trucks in target city. Our findings support the estimation of the effect of on-road emissions on urban air quality in Korea.

Estimating traffic volume on Wyoming low volume roads using linear and logistic regression methods

Traffic volume is an important parameter in most transportation planning applications. Low volume roads make up about 69% of road miles in the United States. Estimating traffic on the low volume roads is a cost-effective alternative to taking traffic counts. This is because traditional traffic counts are expensive and impractical for low priority roads. The purpose of this paper is to present the development of two alternative means of cost- effectively estimating traffic volumes for low volume roads in Wyoming and to make recommendations for their implementation. The study methodology involves reviewing existing studies, identifying data sources, and carrying out the model development. The utility of the models developed were then verified by comparing actual traffic volumes to those predicted by the model. The study resulted in two regression models that are inexpensive and easy to implement. The first regression model was a linear regression model that utilized pavement type, access to highways, predominant land use types, and population to estimate traffic volume. In verifying the model, an R^2 value of 0.64 and a root mean square error of 73.4% were obtained. The second model was a logistic regression model that identified the level of traffic on roads using five thresholds or levels. The logistic regression model was verified by estimating traffic volume thresholds and determining the percentage of roads that were accurately classified as belonging to the given thresholds. For the five thresholds, the percentage of roads classified correctly ranged from 79% to 88%. In conclusion, the verification of the models indicated both model types to be useful for accurate and cost-effective estimation of traffic volumes for low volume Wyoming roads. The models developed were recommended for use in traffic volume estimations for low volume roads in pavement management and environmental impact assessment studies.

Use of Hi-resolution data for evaluating accuracy of traffic volume counts collected by microwave sensors

Over the past few years, the Utah Department of Transportation has developed the signal performance metrics （SPMs） system to evaluate the performance of signalized in- tersections dynamically. This system currently provides data summaries for several per- formance measures, one of them being turning movement counts collected by microwave sensors. As this system became public, there was a need to evaluate the accuracy of the data placed on the SPMs. A large-scale data collection was carried out to meet this need. Vehicles in the Hi-resolution data from microwave sensors were matched with the vehicles by ground-truth volume count data. Matching vehicles from the microwave sensor data and the ground-truth data manually collected required significant effort, A spreadsheet- based data analysis procedure was developed to carry out the task. A mixed model analysis of variance was used to analyze the effects of the factors considered on turning volume count accuracy. The analysis found that approach volume level and number of approach lanes would have significant effect on the accuracy of turning volume counts but the location of the sensors did not significantly affect the accuracy of turning volume counts. In addition, it was found that the location of lanes in relation to the sensor did not significantly affect the accuracy of lane-by-lane volume counts. This indicated that accu- racy analysis could be performed by using total approach volumes without comparing specific turning counts, that is, left-turn, through and right-turn movements. In general, the accuracy of approach volume counts collected by microwave sensors were within the margin of error that traffic engineers could accept. The procedure taken to perform the analysis and a summary of accuracy of volume counts for the factor combinations considered are presented in this paper.

Fatigue monitoring and analysis of orthotropic steel deck considering traffic volume and ambient temperature

Fatigue has gradually become a serious issue for orthotropic steel deck used for long-span bridges. Two fatigue effects, namely number of stress cycles and equivalent stress amplitude, were introduced as investigated parameters in this paper. Investigation was focused on their relationships with traffic volume and ambient temperature by using 7-months fatigue monitoring data of an actual bridge. A fatigue analytical model considering temperature-induced changes in material property of asphalt pavement was established for verifying these relationships. The analysis results revealed that the number of stress cycles and equivalent stress amplitude showed a linear correlation with the traffic volume and ambient temperature, respectively, and that the rib-to-deck welded joint was much more sensitive to the traffic volume and ambient temperature than the rib-to-rib welded joint. The applicability of the code-recommended model for fatigue vehicle loading was also discussed, which revealed that the deterministic vehicle loading model requires improvement to account for significant randomness of the actual traffic conditions.

Research on a forecasting model of tourism traffic volume in theme parks in China

In this study,a model based on multiple regression analysis is developed to forecast the tourism traffic volume of theme parks.First,the macro,meso and micro factors affecting traffic passenger volume are analysed.Second,SPSS software is used for multivariate regression analysis on data for 10 theme parks from 2014.A tourism traffic volume forecasting model is then proposed.Finally,related data for 2015 is used to validate the model,with results showing a prediction error of 14.1%.All results show that the model has a high predictive ability.

Effects of odd-even traffic restriction on travel speed and traffic volume:Evidence from Beijing Olympic Games

This paper reports the effects of using an ＂odd and even＂ traffic restriction policy in Beijing during the 2008 Olympic Games. Based on data from 529 traffic detectors on the expressway network and some main arterials in Beijing, China, a comparative analysis has been carried out on the following parameters： the total traffic volume within the expressway network, the total traffic volume on different ring expressways, the traffic volume and speed of a freeway segment, and an arterial street before and after the implementation of the traffic restriction policy. The results show that during the traffic restriction period, although more than 50% of vehicles were forbidden to travel in Beijing, the traffic volume was only reduced by 20%-40% while the travel speed had been increased by 10%-20%. This suggests that such traffic restriction policy may be an effective shortterm management measure in dealing with increased transportation demand and congestion during major events, such as the Olympic Games. Results also indicate that vehicle travel demand does not decrease with the same proportion as the total vehicles forbidden, at least for the expressway and main arterials in a city.

Network traffic classification:Techniques,datasets,and challenges

In network traffic classification,it is important to understand the correlation between network traffic and its causal application,protocol,or service group,for example,in facilitating lawful interception,ensuring the quality of service,preventing application choke points,and facilitating malicious behavior identification.In this paper,we review existing network classification techniques,such as port-based identification and those based on deep packet inspection,statistical features in conjunction with machine learning,and deep learning algorithms.We also explain the implementations,advantages,and limitations associated with these techniques.Our review also extends to publicly available datasets used in the literature.Finally,we discuss existing and emerging challenges,as well as future research directions.