JournalTOCs

Journal of Big Data Analytics in Transportation
Number of Followers: 2

Hybrid journal (It can contain Open Access articles)
ISSN (Print) 2523-3556 - ISSN (Online) 2523-3564
Published by Springer-Verlag

[2469 journals]

Driver Behavior Extraction from Videos in Naturalistic Driving Datasets
with 3D ConvNets
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Naturalistic driving data (NDD) is an important source of information to understand crash causation and human factors and to further develop crash avoidance countermeasures. Videos recorded while driving are often included in such datasets. While there is a large amount of video data in NDD, only a small portion of it can be annotated by human coders and used for research. In this paper, we explored a computer vision method to automatically annotate behaviors in videos. More specifically, we developed a 3D ConvNet algorithm to automatically extract cell phone behaviors from videos. The experiments show that our method can extract chunks from videos, most of which (∼ 85%) contain the automatically labeled cell phone behaviors. Importantly, we discuss and evaluate two use cases: (1) using algorithm labels without subsequent human review, and (2) using algorithm labels with subsequent human review. We find that even a 99% accurate algorithm will produce statistics that are appreciably biased towards the null, relative to ground truth, when labels are used without review. Thus, while the algorithm is not accurate enough to support the direct use of its labels in analysis, in conjunction with a human review of the extracted chunks, this approach can find cell phone behaviors much more efficiently than simply viewing a video.
  PubDate: 2022-06-24
Real-Time Detection and Recognition of Railway Traffic Signals Using Deep
Learning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Automated detection and recognition of traffic signals are of great significance in railway systems. Autonomous driving solutions are well established for urban rail transportation systems. Many metro lines in service worldwide have reached the highest grade of automation where the train is automatically operated without any staff on board. However, autonomous driving is still an open challenge for mainline trains, due to the complexity of the mainline environment. In this context, automated recognition of wayside signals can help to minimise the risk of human error owing to low visibility and fatigue. It represents a key step towards the fully autonomous train. In this article we present a deep learning based approach for the above task. The You Only Look Once (YOLOv5) is used for detection and recognition of wayside signals. A heuristic is used to recognise blinking states. We consider FRSign dataset, a large collection of over 100,000 images of traffic signals from some of the trains in French Railways. A distilled and cleaned version of the dataset curated by us is used for training. The trained network has low computational overhead and can recognise traffic signals in real time and under diverse field conditions. It has robust performance even for complex scenes having multiple signals and light sources, and in adverse circumstances such as rain and night environments. The refined version of the dataset is published as open for validation and further research and development.
  PubDate: 2022-06-23
Semi-supervised Mode Classification of Inter-city Trips from Cellular
Network Data
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Good knowledge of travel patterns is essential in transportation planning. Cellular network data as a large-scale passive data source provides billions of daily location updates allowing us to observe human mobility with all travel modes. However, many transport planning applications require an understanding of travel patterns separated by travel mode, requiring the classification of trips by travel mode. Most previous studies have used rule-based or geometric classification, which often fails when the routes for different modes are similar or supervised classification, requiring labelled training trips. Sufficient amounts of labelled training trips are unfortunately often unavailable in practice. We propose semi-supervised classification as a novel approach of classifying large sets of trips extracted from cellular network data in inter-city origin–destination pairs as either using road or rail. Our methods require no labelled trips which is an important advantage as labeled data is often not available in practice. We propose three methods which first label a small share of trips using geometric classification. We then use structures in a large set of unlabelled trips using a supervised classification method (geometric-labelling), iterative semi-supervised training (self-labelling) and by transferring information between origin–destination pairs (continuity-labelling). We apply the semi-supervised classification methods on a dataset of 9545 unlabelled trips in two inter-city origin–destination pairs. We find that the methods can identify structures in the cells used during trips in the unlabelled data corresponding to the available route alternatives. We validate the classification methods using a dataset of 255 manually labelled trips in the two origin–destination pairs. While geometric classification misclassifies 4.2% and 5.6% of the trips in the two origin–destination pairs, all trips can be classified correctly using semi-supervised classification.
  PubDate: 2022-06-10
Understanding the Recovery of On-Demand Mobility Services in the COVID-19
Era
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The COVID-19 pandemic and its related events (e.g., lockdown policies, vaccine distributions) have caused disruptive changes in travel patterns and urban mobility services. Cities need to understand the impacts of these factors on mobility activities for taking effective actions to restore/reform urban transportation systems and prepare for future shocks. In this study, we investigate the correlations between the COVID-19 related factors and the usage of on-demand mobility services (OMS, i.e., street-hailing, ride-hailing, and bike-sharing) through a two-step framework. In the first step, we construct low-dimensional representations, called mobility signals, of multivariate mobility data which provide a temporal understanding of the variation of trips across different modes. Then the Bayesian structural time series model is utilized to estimate the regression coefficients and inclusion probability of different time-varying factors including COVID-19 cases, policies, and vaccination rates in predicting each mobility signal. This framework is adopted in New York City (NYC) and Chicago, two example cities that have been significant affected by COVID-19 disruptions and that have comprehensive on-demand mobility services. The results suggest an asymmetrical influence of COVID-19 related policies to the usage of OMS: the mobility/business restrictions can trigger fast and consistent decrease of ridership, but lifting these restrictions does not result in a fast rebound. Our analyses further uncovers the heterogeneity of spatial impacts of different COVID-19 related policies. A one-year prediction of OMS usage is conducted and the results suggest a highly uncertain future of the ride-hailing and street-hailing services, and relatively stable bike-sharing usage in the near future.
  PubDate: 2022-06-03
Optimization Models for Estimating Transit Network Origin–Destination
Flows with Big Transit Data
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The increasing adoption of automatic vehicle location and automatic passenger count technologies by transit agencies produces passenger boarding and alighting count data on a continuous basis. This data provides new opportunities for origin–destination (O–D) flow estimation. However, the state-of-the-art methodologies generated flows within routes and barely considered linked trips. This paper proposes optimization models to identify transfers and approximate network-level O–D flows by: a quadratic integer program (QIP), a feasible rounding procedure for the quadratic convex programming (QCP) relaxation of the QIP, and an integer program (IP). A case study for Ann Arbor-Ypsilanti area in Michigan suggests that: The IP model outperforms the QCP in terms of accuracy and remains tractable from an efficiency standpoint, contrary to the QIP. Its O–D estimation achieves an R-Squared metric of \(95.57\%\) at the traffic analysis zone level and \(92.39\%\) at the stop level, compared to the ground-truths inferred from the state-of-the-practice trip-chaining methods.
  PubDate: 2021-12-01
  DOI: 10.1007/s42421-021-00050-3
Large-Scale Data-Driven Traffic Sensor Health Monitoring
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Accurate traffic data collection is essential for supporting advanced traffic management system operations. This study investigated a large-scale data-driven sequential traffic sensor health monitoring (TSHM) module that can be used to monitor sensor health conditions over large traffic networks. Our proposed module consists of three sequential steps for detecting different types of abnormal sensor issues. The first step detects sensors with abnormally high missing data rates, while the second step uses clustering anomaly detection to detect sensors reporting abnormal records. The final step introduces a novel Bayesian changepoint modeling technique to detect sensors reporting abnormal traffic data fluctuations by assuming a constant vehicle length distribution based on average effective vehicle length (AEVL). Our proposed method is then compared with two benchmark algorithms to show its efficacy. Results obtained by applying our method to the statewide traffic sensor data of Iowa show it can successfully detect different classes of sensor issues. This demonstrates that sequential TSHM modules can help transportation agencies determine traffic sensors’ exact problems, thereby enabling them to take the required corrective steps.
  PubDate: 2021-09-23
  DOI: 10.1007/s42421-021-00049-w
Correction to: Short‑Term Prediction of Demand for Ride‑Hailing
Services: A Deep Learning Approach
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: A correction to this paper has been published: https://doi.org/10.1007/s42421-021-00046-z
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00046-z
Correction to: Seasonal Disorder in Urban Traffic Patterns: A Low Rank
Analysis
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: A correction to this paper has been published: https://doi.org/10.1007/s42421-021-00045-0
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00045-0
Scalable Framework for Enhancing Raw GPS Trajectory Data: Application to
Trip Analytics for Transportation Planning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Transportation analysts and planners are beginning to leverage GPS trajectory data to draw additional insight into travel behavior and enhance data-driven decision-making capabilities. However, raw trajectory data cannot be utilized directly; they require extensive processing prior to analysis. This paper presents a scalable approach for enhancing raw GPS trajectory data by snapping and routing waypoints along a user-defined target road network that may have discontinuities and missing links, thus enabling trajectory datasets to be used in conjunction with the types of non-routable road networks often employed by transportation agencies. The proposed approach fuses a well-established map matching solution with a custom waypoint conflation procedure, and provides a framework to execute the trajectory processing in parallel to efficiently leverage available computing resources for large GPS datasets. To demonstrate its capability, four months of 2018 trajectory data from Maryland (2.5 billion waypoints from 46 million trips) are processed in this manner and assigned to a Traffic Message Channel road network. The enhanced trajectory data are then used to demonstrate a real-world use case, identifying key travel patterns along the I-270 spur in Maryland—a key commuting corridor currently being considered by the Maryland Department of Transportation for a congestion mitigation investment.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00040-5
Deep LSTM Recurrent Neural Networks for Arterial Traffic Volume Data
Imputation
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This research investigates the performance of deep learning to perform traffic data imputation using Long Short Term Memory (LSTM) Recurrent Neural Network (RNN) layers. Investigation of real-time traffic volume data received from a connected corridor revealed the presence of intermittent data gaps. Such data gaps in data streams could impact applications that utilize connected corridor data. To improve the utility of the connected corridor real-time data streams a deep learning algorithm that can use historic and current high frequency data to learn and provide accurate estimations for imputation is realized. In this study traffic volume data streams are received in 6-min aggregate bins from the corridor detectors. Univariate time series models based on only the given detector and multivariate time series models based on the given detector and a similar detector are trained on LSTM RNN layers using current and historic data. To investigate the performance of these models in imputing missing data gaps two experiments are conducted. The first experiment investigates the performance of models to impute consecutive missing data under typical traffic conditions. Results indicate comparable performance of the multivariate and univariate models for shorter consecutive missing data gap imputations, while for longer consecutive missing data gaps, multivariate outperforms univariate for several cases. The second experiment compared the models performance under atypical traffic conditions. Results indicate improved performance of the multivariate over univariate models, further demonstrating the potential advantages of using recent information from other similar detectors in a multivariate model, under both typical and atypical conditions.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00043-2
A Proactive Approach to Evaluating Intersection Safety Using Hard-Braking
Data
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Typical safety improvements at signalized intersections are identified and prioritized using crash data over 3–5 years. Enhanced probe data that provides date, time, heading, and location of hard-braking events has recently become available to agencies. In a typical month, over six million hard-braking events are logged in the state of Indiana. This study compared rear-end crash data over a period of 4.5 years at 8 signalized intersections with weekday hard-braking data from July 2019. Using Spearman’s rank-order correlation, results indicated a strong correlation between hard-braking events and rear-end crashes occurring more than 400 ft upstream of an intersection. The paper concludes that using a month or two of hard-braking events occurring upstream from the stop bar may be a useful tool to screen potential locations with elevated rear-end crashes. Using these techniques described in this paper, new commercially available hard-braking data sources will provide an opportunity for agencies to follow up with mitigation measures addressing emerging problems much quicker than typical practices that rely on 3–5 years of crash data.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00039-y
Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning
Approach
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract As ride-hailing services become increasingly popular, being able to accurately predict demand for such services can help operators efficiently allocate drivers to customers, and reduce idle time, improve traffic congestion, and enhance the passenger experience. This paper proposes UberNet, a deep learning convolutional neural network for short-time prediction of demand for ride-hailing services. Exploiting traditional time series approaches for this problem is challenging due to strong surges and declines in pickups, as well as spatial concentrations of demand. This leads to pickup patterns that are unevenly distributed over time and space. UberNet employs a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services. Specifically, the proposed model includes two sub-networks that aim to encode the source series of various features and decode the predicting series, respectively. To assess the performance and effectiveness of UberNet, we use 9 months of Uber pickup data in 2014 and 28 spatial and temporal features from New York City. We use a number of features suggested by the transport operations and travel behaviour research areas as being relevant to passenger demand prediction, e.g., weather, temporal factors, socioeconomic and demographics characteristics, as well as travel-to-work, built environment and social factors such as crime level, within a multivariate framework, that leads to operational and policy insights for multiple communities: the ride-hailing operator, passengers, third-part location-based service providers and revenue opportunities to drivers, and transport operators such as road traffic authorities, and public transport agencies. By comparing the performance of UberNet with several other approaches, we show that the prediction quality of the model is highly competitive. Further, Ubernet’s prediction performance is better when using economic, social and built environment features. This suggests that Ubernet is more naturally suited to including complex motivators of travel behavior in making real-time demand predictions for ride-hailing services.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00041-4
Inferring Twitters’ Socio-demographics to Correct Sampling Bias of
Social Media Data for Augmenting Travel Behavior Analysis
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Many studies demonstrated that social media data, especially Twitter data, have significant potentials to develop models for estimating travel demand, managing operation, and conducting long-term planning purposes. However, it is well known that research with social media data is facing a looming challenge in sampling bias. The Twitter user’s population has huge discrepancies compared with the overall population. Therefore, social media data, when it is directly used for travel behavior analysis, contains biases and errors to some degree. The objective of this study is to correct sampling bias of Twitter data for travel behavior analysis by inferring Twitter users’ socio-demographics. This study first links travelers’ Twitter account with their Facebook account, and verifies their socio-demographics by Facebook data, assuming that one’s Facebook information is real. Second, several models are proposed for predicting socio-demographics, including gender, age, ethnicity, and education levels. Afterward, this paper resamples social media data and compares it to the 2009 California Household Travel Survey data. The resampled data show comparable characteristics to the survey data. This research shed light on tackling sampling bias issues when social media data are incorporated for augmenting travel behavior analysis and urban planning.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00037-0
Real-Time Traffic Counter Using Mobile Devices
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Automatic traffic counting and classification (ATCC) is a salient step in many applications such as accessing the contribution of traffic to air pollution for clean air strategies and computing the passenger car unit (PCU) for urban road infrastructure planning and management. This work focuses on developing an ATCC system that is low cost, privacy-preserving, and auditable using state-of-the-art AI technology on mobile phones. The camera unit and the GPU compute available within a mobile phone are used to capture the video feed and run the required analytics for detection, tracking and counting in real time. On the target device, we have been able to achieve 12 FPS. On the test data composed of four videos, the solution achieved a counting precision and recall of 0.96 ± 0.02 and 0.86 ± 0.03, respectively.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00044-1
Deep Learning Techniques for Vehicle Trajectory Extraction in Mixed
Traffic
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract Vehicle trajectories provide very useful empirical data for studying traffic phenomena such as vehicle following behavior, lane changing behavior, traffic oscillations, capacity drop, safety analysis, etc. However, there are a very limited number of studies on extracting trajectory data from mixed traffic and for congested conditions. This paper presents a deep learning-based framework to extract vehicle trajectories in mixed traffic under both free-flow and congested conditions. The popular YOLOv3 deep learning architecture is used and trained on a hybrid dataset generated from two different sets of frames with different scales and orientations. The anchor boxes for vehicle detection and classification are customized to improve accuracy and efficiency. The SORT algorithm is used to track the identified vehicles and the extracted trajectory data are benchmarked with a popular trajectory extraction portal that showed that the proposed model performs well for trajectory extraction. The paper also presents a methodology based on numerical integration techniques to impute missing trajectory data. Finally, the trajectory data obtained from the adjacent road sections are aligned and scaled to the real-world coordinates using coordination transformation and error correction methods to make it useful for research purposes. The extracted trajectories show remarkable accuracy with approximately 0.25–0.35 m of precision. It is expected that these trajectories capture traffic and driving behavior phenomena for a better understanding of mixed traffic conditions.
  PubDate: 2021-08-01
  DOI: 10.1007/s42421-021-00042-3
Predicting the Use of Managed Lanes Using Machine Learning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The use of managed lanes (MLs) is currently predicted using discrete choice models. However, recent research discovered that many travelers were not making choices in their use of MLs—they always used one set of lanes and never varied. Therefore, choice models may not be appropriate. This research examined if machine learning could be used to model ML use by travelers. Machine learning techniques were used to classify approximately 125,000 travelers who made approximately 3.5 million trips on the Katy Freeway over a 2-year period. Different machine learning models were able to classify travelers into those who always used MLs, always used toll-free general purpose lanes (GPLs), and those who used both types of lanes (choosers). Travel time savings, total number of trips made, and the start and end location of the trip were key predictors of the user class. Neural networks with LSTM could classify the trips conducted by choosers as ML trips or GPL trips based on the start and end location of the trips and the drivers’ travel history. A comparison with logit models showed that machine learning models performed better in classifying travelers and trips made by choosers. However, trends obtained from both models were same. This research has shown that a multi-level classification of travelers and machine learning techniques were able to predict real-world traveler choice on a ML facility. This may be an important first step in shifting travel models from how we think travelers are behaving to what is actually happening.
  PubDate: 2021-07-14
  DOI: 10.1007/s42421-021-00048-x
Semi-supervised GANs to Infer Travel Modes in GPS Trajectories
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This study experiments with the use of adversarial networks to classify travel mode based on one-dimensional smartphone trajectory data. We use data from a large-scale smartphone travel survey in Montreal, Canada. We convert GPS trajectories into fixed-sized segments with five channels (or variables). We develop different GANs architectures and compare their prediction results with convolutional neural networks (CNNs). The best semi-supervised GANs model led to a prediction accuracy of 83.4%, while the best CNN model was able to achieve the prediction accuracy of 81.3%. The results compare favorably with previous studies, especially when taking the large, real-world nature of the dataset into account. The developed semi-supervised GANs models share the same architectural innovations used in the image recognition literature, that we show can be used in travel information inference from smartphone travel survey data, not only to generate more labeled samples but also to improve the prediction performance of the classifier. Future work will allow exploration of better-performing models either with more channels and/or improved architectures.
  PubDate: 2021-07-10
  DOI: 10.1007/s42421-021-00047-y
Seasonal Disorder in Urban Traffic Patterns: A Low Rank Analysis
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This article proposes several advances to sparse nonnegative matrix factorization (SNMF) as a way to identify large-scale patterns in urban traffic data. The input to our model is traffic counts organized by time and location. Nonnegative matrix factorization additively decomposes this information, organized as a matrix, into a linear sum of temporal signatures. Penalty terms encourage this factorization to concentrate on only a few temporal signatures, with weights which are not too large. Our interest here is to quantify and compare the regularity of traffic behavior, particularly across different broad temporal windows. In addition to the rank and error, we adapt a measure introduced by Hoyer to quantify sparsity in the representation. Combining these, we construct several curves which quantify error as a function of rank (the number of possible signatures) and sparsity; as rank goes up and sparsity goes down, the approximation can be better and the error should decreases. Plots of several such curves corresponding to different time windows leads to a way to compare disorder/order at different time scalewindows. In this paper, we apply our algorithms and procedures to study a taxi traffic dataset from New York City. In this dataset, we find weekly periodicity in the signatures, which allows us an extra framework for identifying outliers as significant deviations from weekly medians. We then apply our seasonal disorder analysis to the New York City traffic data and seasonal (spring, summer, winter, fall) time windows. We do find seasonal differences in traffic order.
  PubDate: 2021-04-01
  DOI: 10.1007/s42421-021-00033-4
Model Free Identification of Traffic Conditions Using Unmanned Aerial
Vehicles and Deep Learning
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract The purpose of this paper is to provide a methodological framework to identify traffic conditions based on non-calibrated video recordings captured from unmanned aerial vehicles (UAV) using deep learning. To this end, we propose two complementary to each other approaches: (i) identify in real time, with minimal computational cost, traffic conditions, (ii) localize, classify vehicles and approximate traffic variables (volume, speed, density) on a road segment from video captured by UAVs. Both problems are formulated as classification problems and tackled using Convolutional Neural Networks (CNN). The use of pre-trained CNNs is also investigated. Both approaches are, then, analysed based on their accuracy and feasibility in implementation. Findings indicate that all models developed achieve a detection accuracy of 89% and higher. The CNN with the best performance can classify traffic conditions between constrained and unconstrained traffic with 91% accuracy higher than what a pretrained model achieved and with significantly faster training times. Furthermore, findings indicated that pretrained neural network for traffic localization was able to predict the position and type of vehicles with a precision of 0.91. Based on the fundamental traffic diagram, it was shown that the two approaches provide compatible results and a feasible representation of traffic on the study area. Finally, possible applications in the field of transportation and traffic monitoring are discussed.
  PubDate: 2021-04-01
  DOI: 10.1007/s42421-021-00038-z
Analyzing Parking Sentiment and its Relationship to Parking Supply and the
Built Environment Using Online Reviews
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Abstract: Abstract This study examines positive and negative sentiments associated with parking experiences reported in online Yelp reviews for four metropolitan areas in North America, leveraging large location-based social network (LBSN) data to understand parking sentiment as a measure of parking search or post-parking experiences. Demand from travelers and business owners for more parking is a significant issue for local transportation planners and decision-makers, but to date, there has been little study of how local parking management strategies or built environment characteristics modify parking experiences and sentiments. To understand this relationship, we first conduct a sentiment analysis (SA) to identify the emotional, affective content of parking-related reviews embedded in the Yelp reviews. We then use generalized mixed effects (GLME) models to examine the associations between parking sentiment and (a) parking management practices, and (b) characteristics of the built environment. The SA results show that positive and negative parking sentiments are significantly spatially clustered in each metropolitan area. GLME models show that sentiments are significantly associated with destination activity types, parking management strategies, and several built environment factors. The results of this study indicate how different interventions advocated by transportation policies may influence perceptions of parking in commercial and mixed-use districts with implications for overall support for neighborhood transportation planning best practice. Furthermore, the findings represent that emerging data mining and statistical methods can successfully leverage big data to reveal travel experiences and their relationship to urban contexts, providing an effective solution to obtaining experiential transportation information.
  PubDate: 2021-04-01
  DOI: 10.1007/s42421-021-00036-1