•A CNN architecture is proposed to infer transportation modes from GPS trajectories.•An adaptable and efficient layout for the input layer of the CNN is designed.•Key factors in the CNN: remove ...anomalies, data augmentation, use the bagging concept.•The proposed CNN achieves the accuracy of 84.8%, higher than other studies.
Identifying the distribution of users’ transportation modes is an essential part of travel demand analysis and transportation planning. With the advent of ubiquitous GPS-enabled devices (e.g., a smartphone), a cost-effective approach for inferring commuters’ mobility mode(s) is to leverage their GPS trajectories. A majority of studies have proposed mode inference models based on hand-crafted features and traditional machine learning algorithms. However, manual features engender some major drawbacks including vulnerability to traffic and environmental conditions as well as possessing human’s bias in creating efficient features. One way to overcome these issues is by utilizing Convolutional Neural Network (CNN) schemes that are capable of automatically driving high-level features from the raw input. Accordingly, in this paper, we take advantage of CNN architectures so as to predict travel modes based on only raw GPS trajectories, where the modes are labeled as walk, bike, bus, driving, and train. Our key contribution is designing the layout of the CNN’s input layer in such a way that not only is adaptable with the CNN schemes but represents fundamental motion characteristics of a moving object including speed, acceleration, jerk, and bearing rate. Furthermore, we ameliorate the quality of GPS logs through several data preprocessing steps. Using the clean input layer, a variety of CNN configurations are evaluated to achieve the best CNN architecture. The highest accuracy of 84.8% has been achieved through the ensemble of the best CNN configuration. In this research, we contrast our methodology with traditional machine learning algorithms as well as the seminal and most related studies to demonstrate the superiority of our framework.
•Tweets are mapped into numerical feature vectors using word-embedding models.•Tweets are classified into non-traffic, traffic incident, and traffic information.•Classification task is performed ...using convolutional and recurrent neural networks.•51,100 tweets are collected, labeled, and publicly released for future research.•Models’ superiority is demonstrated through several evaluation steps.
In recent years, several studies have harnessed Twitter data for detecting traffic incidents and monitoring traffic conditions. Researchers have utilized the bag-of-words representation for converting tweets into numerical feature vectors. However, the bag-of-words not only ignores the order of tweet's words but suffers from the curse of dimensionality and sparsity. A common approach in literature for dimensionality reduction is to build the bag-of-words on the top of pre-defined traffic keywords. The immediate criticisms to such a strategy are that the pre-defined set of keywords may not include all traffic keywords and the tweet language is subjected to change over time. To address these shortcomings, we utilize the power of deep-learning architectures for both representing tweets in numerical vectors and classifying them into three categories: 1) non-traffic, 2) traffic incident, and 3) traffic information and condition. First, we map tweets into low-dimensional vector space through word-embedding tools, which are also capable of measuring the semantic relationship between words. Supervised deep-learning algorithms including convolutional neural network (CNN) and recurrent neural network (RNN) are then deployed on the top of word-embedding models for detecting traffic events. For training and testing our proposed model, a large volume of traffic tweets is collected through Twitter API endpoints and labeled through an efficient strategy. Experimental results on our labeled dataset show that the proposed approach achieves clear improvements over state-of-the-art methods.
This study explores the cycling usage and frequency determinants in college campuses located in the Baltimore Metropolitan Area. The study discerns the attitudes of individuals toward the proposed ...infrastructure and environmental improvements with the goal of promoting biking to campus. We develop a structural equation model (SEM) using the travel information of 780 individuals, which was collected between December 2014 and June 2015. The results indicate risk factors have a higher explanatory value on bike-to-campus frequency than campus infrastructure and program. We further examine how and to what extent mixed populations on college campuses respond to latent factors. The findings pinpoint that males are less concerned about the risk-related indicators such as theft and road and environment-related obstacles such as poor road conditions. However, females have a positive attitude toward campus-related improvements such as pro-bike programs. Overall, students show a negative attitude toward the road and environmentally-related obstacles compared to staff and faculty. Minority groups, specifically African American and Asian, show a positive attitude toward campus-related improvements, unlike white participants. The findings can assist planners and advocates in implementing effective policy measures to increase bike-to-campus frequency.
•Minorities have a positive attitude toward campus-related improvements.•Students have a negative attitude toward road and environmentally-related obstacles, compared to staff and faculty•Females are more concerned about risk-related indicators and environment related obstacles.•Females have a positive attitude toward campus-related improvements such as pro-bike programs.•Strong/fearless and enthused/confident cyclists were less concerned about road and environmentally-related indicators.
This study explores speed choice behavior of travelers under realistic and fabricated Dynamic Message Signs (DMS) content. Using web-based survey information of 4,302 participants collected by Amazon ...Mechanical Turk in the United States, we develop a set of multivariate latent-based ordered probit models participants. Results show female, African-Americans, drivers with a disability, elderly, and drivers who trust DMS are likely to comply with the fabricated messages. Drivers who comply with traffic regulations, have a good driving record, and live in rural areas, as well as female drivers are likely to slow down under fabricated messages. We highlight that calling or texting, taking picture, and tuning the radio are distracting activities leading drivers to slow down or stop under fictitious scenarios.
This study analyzed community resiliency by evaluating access to essential delivery services before and during the COVID-19 pandemic. Data were collected from October 2020 to September 2021 in a ...stated-preference survey about delivery services in Southwest Virginia. A significantly larger proportion of respondents without vehicle access relied on third-party restaurant app delivery use than those with a vehicle. Compared to more urban areas, respondents who lived in rural locations were three times more unsatisfied with delivery services due to a lack of accessibility to stores and delivery options.
The implementation of connected and automated vehicles promises increased safety and efficiency by leveraging advances in technology. With this new technology, some vulnerabilities could lead to ...cyberattacks. Without a focus on cybersecurity, vehicles may be attacked, reducing the efficiency and safety advantages promised through technological advancement. This research performed an impact analysis on traffic operations of cyberattacks on Vehicular Ad-Hoc Networks (VANET). A roadway traffic and communications simulation was created using the Veins modeling platform that incorporated V2X communication and could model Denial of Service (DoS) and Man in the Middle (MITM) attacks on an urban street network. The number of compromised intersections and attack success rate were varied to understand the impact of each attack scenario. Each attack’s worst-case scenario resulted in an over 20% increase in travel time delay per vehicle as the attack severity increased. Also, the attacks had a wide variation in delay upon the transportation network, decreasing the travel time reliability and the ability for road users to predict delay on their journey.
This study addresses car-following models that are currently used for simulating AV and CAV. Diverse car-following models, Intelligent Driver Model (IDM), Improved IDM (IIDM), IIDM with ...Constant-Acceleration Heuristic (CAH), and MIcroscopic model for Simulation of Intelligent Cruise control (MIXIC) are examined with the state-of-the-art vehicle trajectory data, Highway Drone dataset (HighD), and genetic algorithm. There is no commercial level 5 AV or CAV as of 2022; therefore, the authors generate hypothetical AV trajectories based on the actual vehicle trajectories and the assumption of an ideal AV. Based on the analysis, the calibrated IIDM with CAH shows the most fit on AV behavior.
This article studies self-reported route change behavior of 4,706 licensed drivers in the continental U.S. through a stated preference survey when they encounter road sign messages. Respondents are ...asked to score their likelihood of route change and speed change on a 5-point Likert scale to three messages: (1) "Heavy Traffic Due to Accident," (2) "Road Closure Due to Police Activity," and (3) "Storm Watch, Flooding in Area Soon." We fulfill three objectives. First, we identify the relationship between the route change behavior and socioeconomic and attitudinal-related factors. Second, we explore the impact of road sign messages with different contents on route change behavior. Third, we test the association between route change and speed change behaviors. The results demonstrate that: (1) the response of participants to compromised dynamic message signs varies according to the socioeconomic standing and attitude of participants, (2) the response of participants varies under different messages, and socioeconomic and attitudinal factors impact this differentiation, and (3) the likelihood of route change is positively associated with slowing down. This means, in practice, a malicious adversary has the potential to shunt and disturb traffic by disseminating fabricated messages and engineering route choice of drivers.
Traffic signs often convey critical information to drivers. To ensure visibility in nighttime or low light conditions, traffic signs must be in compliance with the minimum retroreflectivity standards ...outlined by the manual on uniform traffic control devices (MUTCD). Among all of the assessment methods (visual nighttime inspection, retroreflectivity measurement) and management methods (expected life, blanket replacement, and control signs) outlined in the MUTCD, expected sign life has been the most selected by agencies for maintaining compliance. In current literature, little research exists with regard to schedule sign replacement, focusing rather on the current favorite predictor, sign age. However, after collecting data on 1683 in-service traffic signs across the state of Utah, this study primarily concluded that not only sign age, but other contributing factors affect sign retroreflective performance. Aiming to determine the effects of various damage forms on sign retroreflectivity, statistical methods, including regression models, chi-square test, t-test, and odds ratio were employed to analyze traffic sign data. At the conclusion, the strong association between damage and retroreflectivity compliance of traffic signs was evident. In addition, to identify more critical damage forms, the effects of various forms on traffic sign retroreflectivity were compared. These conclusions provide insight to inform transportation agencies in the development of sign management plans and schedule sign replacement.
This study sheds light on the travel behavior of drivers when they encounter fabricated messages in work zones. Using the response of 4302 participants to a stated preference survey, we develop a ...multivariate ordered response model and a structural equation model to study speed change and distraction response behavior. The results of our models for fabricated announcements signify that drivers normally follow the announcement and are affected likewise. The selected socioeconomic and attitudinal variables are shown to have mixed impacts in our speed and distraction models. Some variables are statistically significant for each model, while other variables are only statistically significant for one of the models. For instance, drivers that have seen a fabricated announcement before are less likely to speed up when encountering the message, while drivers who rely on technology for their daily travels are more likely to be distracted. Higher income is shown in our models to signify undesirable behaviors: speeding up and being distracted. Contrastingly, female drivers are less likely to do nothing or be distracted by the announcement. The findings, taken together, have implications for researchers and practitioners. First, they illustrate how cyberattacks can destabilize traffic in work zone and put the life of work zone crew members in jeopardy. Second, they explain the degree of compliance with compromised dynamic message signs.