This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, ...magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user's transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.
Few measures of healthcare accessibility have considered multiple transportation modes when people seek healthcare. Based on the framework of the 2 Step Floating Catchment Area Method (2SFCAM), we ...proposed an innovative method to incorporate transportation modes into the accessibility estimation. Taking Florida, USA, as a study area, we illustrated the implementation of the multi-mode 2SFCAM, and compared the accessibility estimates with those from the traditional single-mode 2SFCAM. The results suggest that the multi-modal method, by accounting for heterogeneity in populations, provides more realistic accessibility estimations, and thus offers a better guidance for policy makers to mitigate health inequity issues.
•Findings confirm acceptance assumptions for pooling made by SAV simulation studies.•61% of respondents chose pooled SAVs over private autonomous cars.•Changes with long-term impact, such as shedding ...a car, are harder to induce.•Push & pull measures on comfort, cost, and time encourage sustainable mode choices.
Autonomous vehicles, understood as vehicles that do not require manual steering, will cause disruptive changes in the transportation sector. Many studies on autonomous vehicles address the sustainability potential of this technology, and they assume that vehicles will no longer be privately owned and will be used with pooling options (multiple riders on a trip). However, there is currently little evidence to indicate whether this assumption is supported by user preference. To address this gap, an online choice experiment including 709 participants was conducted. It assumed the full-market penetration of autonomous vehicles and explored future mode choices, considering both short-term and long-term mobility decisions. The experiment tested the influence of 15 short-term and 13 long-term decision instruments to encourage the adoption of shared and pooled use of autonomous vehicles, like autonomous taxis and autonomous public transport. Our findings partly support the assumption in the existing literature that vehicles are likely to be used in a pooled mode. In the control condition, 61% of Swiss respondents preferred pooled autonomous vehicles over private autonomous cars. Moreover, stated preferences indicated that combined instruments influencing comfort, cost, and time are likely to increase the proportion of pooled uses of autonomous vehicles.
•There are statistical differences in bicycle use motivations between experienced and new cyclists.•Recent bicyclists were motivated to switch to bicycling by utilitarian factors.•Effects of ...congestion and poor quality transit on travel time reliability are the main reason for mode change for recent bicyclists.•Experienced cyclists were more motivated by a passion for cycling.
Bogotá has recently seen an increase in bicycle commuting with this means of transport being currently used for around 880,000 daily trips, in contrast to 475,000 in 2011. What has led bicycle ridership to nearly double in nine years and what are the factors influencing a growing number of residents to switch to bicycle commuting? Using data from an intercept survey, we analyze the personal attitudes, commuting preferences, and mode change motivations of utilitarian bicyclists (people bicycling for work, study, shopping, errands, or health). We conducted an ordered probit model and statistical tests of differences in means between four statistically different quartiles based on the time period for which they have been bicycling. Quartiles of cyclists were further divided based on socioeconomic and attitudinal characteristics into two groups: those who have recently taken up bicycle commuting (people who started bicycling 3 years ago or less) and those experienced utilitarian cyclists who adopted this mode much earlier (people who started bicycling 4 years ago or more). Results show that recent and experienced cyclists differ in how they view the bicycle as a transport vehicle: recent cyclists were more motivated to switch to bicycling for rational reasons such as saving money and shifting from a poor-quality transit system while the longer-term cyclists were more motivated by a passion for bicycling.
•A transport mode classification method for crowdsourcing urban sensing is proposed.•Individual travels are classified into travel modes using sensors in a smartphone.•Our approach yields high ...accuracy despite the low sampling interval for efficiency.•The sampling window is dynamic which can cover an entire vehicle travel period.•Our prototype provides 82% overall accuracy performed in Zurich, Switzerland.
We present a prototype mobile phone application that implements a novel transportation mode detection algorithm. The application is designed to run in the background, and continuously collects data from built-in acceleration and network location sensors. The collected data is analyzed automatically and partitioned into activity segments. A key finding of our work is that walking activity can be robustly detected in the data stream, which, in turn, acts as a separator for partitioning the data stream into other activity segments. Each vehicle activity segment is then sub-classified according to the vehicle type. Our approach yields high accuracy despite the low sampling interval and does not require GPS data. As a result, device power consumption is effectively minimized. This is a very crucial point for large-scale real-world deployment. As part of an experiment, the application has been used by 495 samples, and our prototype provides 82% accuracy in transportation mode classification for an experiment performed in Zurich, Switzerland. Incorporating location type information with this activity classification technology has the potential to impact many phenomena driven by human mobility and to enhance awareness of behavior, urban planning, and agent-based modeling.
In recent years, with the development of science and technology, people have more and more choices for daily travel. However, assisting with various mobile intelligent services by transportation mode ...detection has become more urgent for the refinement of human activity identification. Although much work has been done on transportation mode detection, accurate and reliable transportation mode detection remains challenging. In this paper, we propose a novel transportation mode detection algorithm, namely T2Trans, based on a temporal convolutional network (i.e., TCN), which employs multiple lightweight sensors integrated into a phone. The feature representation learning of multiple preprocessed sensor data using temporal convolutional networks can improve transportation mode detection accuracy and enhance learning efficiency. Extensive experimental results demonstrated that our algorithm attains a macro F1-score of 86.42% on the real-world SHL dataset and 88.37% on the HTC dataset, with an average accuracy of 86.37% on the SHL dataset and 89.13% on the HTC dataset. Our model can better identify eight transportation modes, including stationary, walking, running, cycling, car, bus, subway, and train, with better transportation mode detection accuracy, and outperform other benchmark algorithms.
A petroleum supply chain is a large complex supply chain composed of several sub-problems. Numerous studies have focused on solving a portion of these problems, which led to a non-optimal solution. ...This study addresses a new multi-period multi-echelon and multi-transportation integrated petroleum supply chain model to obtain a global optimal solution. The main feature of this paper is to design an integrated supply chain model that considers both installation and capacity expansion of pipeline routes and facilities simultaneously, and optimizes location-allocation facilities and routes, capacity expansion, inventory, production, exportation and importation, as well as routing and transportation modes over a vast geographical area. To achieve this, a deterministic mixed-integer linear problem was developed and applied to a real world problem based on the information derived from Iran's petroleum chain. Numerous scenarios and sensitivity analyses have been presented for different cases to deepen more in the model. They showed that the optimal solution is less sensitive to variations of the cost parameters, but changes in the amount of demands and injected crude oil change the objective value remarkably. In general, the analysis showed that the developed model has the ability to present the best strategy in complex market situations.
•The paper addresses the integrated strategic and tactical planning of petroleum chain.•Both installation and capacity expansion are considered for facilities and routs.•Decisions of proposed model are found to be insensitive to the parameter changes.•Proposed model is applicable for any petroleum supply chain regardless of region.
Urban Air Mobility (UAM) is an emerging transportation system that aims at revolutionizing urban mobility through the deployment of small electric vertical takeoff and landing (eVTOL) aircraft. The ...development of UAM is largely driven by advances in Intelligent Technology (IT). This review article provides an overview of the UAM system and discusses the application of IT in UAM. Major challenges facing UAM are also identified, and an outlook on the future of this promising transportation system is presented. Our main conclusions suggest that IT is a fundamental driver of UAM, enabling a range of applications such as air traffic management and autonomous drone control. However, the UAM system is facing a number of challenges, including eVTOL technology, system integration issues, and noise pollution. Despite these challenges, the future of UAM appears promising; as a disruptive transportation mode, UAM is expected to play an important role in addressing the growing demand of urban transportation in the coming decades.
Display omitted
Urban air mobility (UAM) is expected to be a new alternative future transportation system to overcome the limitations of infrastructure investment and resolve traffic congestion cost issues in urban ...areas. This study aims to estimate the parameters of the mode choice model incorporating the cleaner transportation mode and evaluate the environmental impact by calculating the reduction of greenhouse gas emissions from ground traffic. A stated preference survey is employed to estimate the parameters for each travel mode, including the emerging travel mode. The awareness and experience of the air travel modes remove the hesitation concerning travel mode choice having positive values, but concerns about taking new types of air mobility reduce the probability of choosing urban air mobility. The macroscopic travel demand forecasting program simulates the travel demand of urban air mobility to calculate the reduction of CO2 emissions between before and after the introduction. While about 30 thousand of urban air mobility travel demand are generated after the introduction of urban air mobility in the urban area, it reduces about 90 thousand tons of CO2 emissions from the ground traffic. The introduction of urban air mobility causes modal shifts from ground traffic, reducing climate change and global warming. Policymakers should evaluate the feasibility of introducing urban air mobility, including environmental impact assessment, and an appropriate transit fare policy is required for the proliferation of urban air mobility.
•Introducing the Cleaner Production on Transport Network System.•Estimating Travel Demand of Electricfied Urban Air Mobility.•Evaluating the Environmental Impact incorporating the CO2 Emission Reduction.•Policy Responses for the proliferation of Electricfied Urban Air Mobility.