Regionalization for urban air mobility application in metropolitan areas: case studies in San Francisco and New York

In a new era of mobility where the transportation of persons or goods via flying vehicles over urban areas has garnered great interest in its application in urban space. With the anticipated utilization of sUAS in urban airspace, a multi-dimensional understanding of urban space is essential. As a first step to assess the feasibility of Urban Air Mobility (UAM) in urban areas, we conduct regionalization and correspondence analysis in highly urbanized areas – San Francisco, CA and Manhattan, NY – by incorporating population dataset and urban 3D airspace to delineate the regional boundaries. Regionalization is carried out using graph-based clustering technique called SKATER (Spatial ‘K’luster Analysis by Tree Edge Removal) to group the regions having similar characteristics and address the compound effect of both population and spatial information. By classifying the regions into five categories through correspondence analysis, the operational and economic feasibility of each region is evaluated. The results provide the region maps of each city with the most and least attractive regions for UAM application with the temporal notion, whether the clusters are daytime-intensive or nighttime-intensive areas. The outcomes have several unique information that can benefit drone delivery target area identification, landing location identification, demand prediction. Our approach can contribute to providing a useful basis for management for UAM in urban areas as well as the process of regulating airspace use.

A Posture Recognition System to Track Drivers’ Activities While Driving

To improve traffic safety, different systems were invented to warn drivers when detecting a conflict. However, drivers may be already aware of such conflicts. In these cases, warning drivers may not effective and may lead drivers to not pay attention to warnings in the case of serious conflicts. The purpose of this study is to develop a novel posture recognition system to detect different driver activities while driving. If drivers are not braking or decelerating in the case of a conflict, they are alerted and notified about the conflict. The proposed system is based on a passive method for measuring bodypostures by using two force sensor arrays to inspect the pressure patterns exhibited in the driver’s seat and backrest. Different sensors' distributions were tested to find the most suitable distribution to improve the accuracy of the recognition. A virtual reality (VR) driving simulation was developed to test the accuracy of recognition in an immersive environment. Experiments were carried out to test the posture recognition accuracy in both realistic and VR settings. The results showed that the system could recognize different postures with high accuracy. Such a system can be used to alert drivers and disengage autonomous mode in the case of self-driving and autonomous vehicles when the situation unsafe.

An integrated agent-based model of travel demand and package deliveries

With the increased shift from in-store shopping to e-commerce, we can expect the share of delivery vehicles in cities to rise as well. This puts great pressure on cities and surrounding areas as emissions rise and space becomes scarce. Because the last leg of the delivery chain is so costly, there have been many studies on how the last-mile issue can be diminished. However, most studies only cover deliveries independently from the orders. This paper presents a modelling approach that integrates travel demand, package orders and subsequent deliveries within the same framework. One of the benefits of the integrated modelling approach is that the model can evaluate the agents’ locations at all times during the simulation. This allows us to model different states of delivery on a microscopic level. We have applied the model to Karlsruhe, Germany with a synthetic population of just over 300.000 agents. The results show that the model simulates both package orders and the subsequent delivery tours realistically. The model framework allows for detailed analysis of delivery states and success rates and can be used for scenario analysis of different delivery methods and changes in online shopping behaviour.

Machine Learning and statistic predictive modeling for road traffic flow

Traffic forecasting is a research topic debated by several researchers affiliated to a range of disciplines. It is becoming increasingly important given the growth of motorized vehicles on the one hand, and the scarcity of lands for new transportation infrastructure on the other. Indeed, in the context of smart cities and with the uninterrupted increase of the number of vehicles, road congestion is taking up an important place in research. In this context, the ability to provide highly accurate traffic forecasts is of fundamental importance to manage traffic, especially in the context of smart cities. This work is in line with this perspective and aims to solve this problem. The proposed methodology plans to forecast day-by-day traffic stream using three different models: the Multilayer Perceptron of Artificial Neural Networks (ANN), the Seasonal Autoregressive Integrated Moving Average (SARIMA) and the Support Machine Regression (SMOreg). Using those three models, the forecast is realized based on a history of real traffic data recorded on a road section over 42 months. Besides, a recognized traffic manager in Morocco provides this dataset; the performance is then tested based on predefined criteria. From the experiment results, it is clear that the proposed ANN model achieves highest prediction accuracy with the lowest absolute relative error of 0.57%.

Modelling of a Stochastic Spatiotemporal Variable in Transport Domain

In this article, building on our previous work, we engage in spatiotemporal modelling of transport demand in the Montreal metropolitan area over the period of six years. We employ classical machine learning and regression models, which predict bike-sharing demand in the form of daily cumulative sums of bike trips for each considered docking station. Hourly estimates of demand are then determined by considering the statistical distribution of demand across individual hours of an average day. In order to capture seasonal and other regular variation of demand, longer-term distribution characteristics of bike trips, such as their average number falling on each day of the week, month of the year, etc., were also used as input attributes. We initially conjectured that weather would be an important source of irregular variation in bike-sharing demand, and subsequently included several available meteorological variables in our models. We validated our models by Hold-Out and 10-Fold Cross-Validation, with encouraging results.

The convergence of Internet of Things, Blockchain and Connected Vehicles: Conceptual Advantages and Disadvantages of a new Cooperative Intelligent Transportation System

This paper intends to explore the convergence of some technological innovations that could lead to new cooperative Intelligent Transportation Systems (ITS). The technologies that might soon converge and lead to some new developments are: the Blockchain Technology (BT) concept, Internet of Things (IoT) and Connected and Automated Vehicles (CAV). Advantages and disadvantages of the new concepts founding a new ITS system are discussed in this conceptual paper. Blockchain technology has been recently introduced and many research ideas have been presented for application in the transportation sector. In this paper, we discuss a system that is based on a dedicated blockchain, able to involve both drivers and city administrations in the adoption of promising and innovative technologies that will create cooperation among connected vehicles. The proposed blockchain-based system can allow city administrators to reward drivers when they are willing to share travel data. The system manages in a special way the creation of rewards which are assigned to drivers and institutions participating actively in the system. Moreover, the system allows keeping a complete track of all transactions and interactions between drivers and city management on a completely open and shared platform. The main idea is to combine connected vehicles with BT to promote Cooperative ITS use, a better use of infrastructures and a more sustainable eco-system of cryptocurrencies. A short description of BT is introduced to evidence energy problems of sustainability in the implementation of Proof of Work (PoW) that is adopted by many blockchains.

On the use of active mobile and stationary devices for detailed traffic data collection: A simulation-based evaluation

The process of collecting traffic data is a key component to evaluate the current state of a transportation network and to analyze movements of vehicles. In this paper, we argue that both active stationary and mobile measurement devices should be taken into account for high-quality traffic data with sufficient geographic coverage. Stationary devices are able to collect data over time at certain locations in the network and mobile devices are able to gather data over large geographic regions. Hence, the two types of measurement devices have complementary properties and should be used in conjunction with each other in the data collection process. To evaluate the complementary characteristics of stationary and mobile devices for traffic data collection, we present a traffic simulation model, which we use to study the share of successfully identified vehicles when using both types of devices with varying identification rate. The results from our simulation study, using freight transport in southern Sweden, shows that the share of successfully identified vehicles can be significantly improved by using both stationary and mobile measurement devices.

Predicting Severity of Accidents in Malaysia By Ordinal Logistic Regression Models

This study was aimed at determining the relationships of accident severity using road environment and traveller characteristics. Ordinal logistic regression models were used in this study. The accident data was provided by Malaysian Research Institute of Road Safety (MIROS) for all accidents which occurred in Penang state during 2006-2011. It was observed that motorbikes were predominantly involved in these accidents, hence, it was decided to develop three separate models; one for the overall data, and others for accidents with and without motorbikes. Logistic regression models showed that commercial land use, road width and experience of driver are important factors that may increase severity of accidents. Shoulder width was found to decrease the severity of motorbike accidents. Commercial land use, road width and driver experience have more impact on motorbike accidents as compared to accidents of other vehicles.

Environmental Awareness and Inclination towards Walking: A Smartphone Application based study

Walking is considered to be one of the sustainable modes of transportation which reduces traffic demand leading to lower levels of pollution and congestion. It has resulted in improved physical and psychological health of individuals. This study focuses on studying walking behavior of travelers in Bahrain. Walking data was collected through Moves mobile application while a questionnaire survey was conducted to find the characteristics of the participants. Walking distance per day was found to be approximately 400m on average which is insufficient to have any significant impact on health. There was no significant change in walking behavior between day and night timings. Walking behavior was found to be related to familiarity with location, financial status and family structure of the participants. Personal characteristics (age, gender, etc.) and perception of the participant did not have any significant impact on walking behavior. It is recommended to increase awareness related to walking and improve pedestrian facilities in all areas of Bahrain to promote walking.

Modelling Heterogeneous and Undisciplined Traffic Flow using Cell Transmission Model

This research calibrates Cell Transmission Model (CTM) for heterogeneous and non-lane disciplined traffic, as observed in Pakistan and some other developing countries by constructing a flow-density fundamental traffic flow diagram. Currently, most of the traffic simulation packages used for such heterogonous and non-lane-disciplined traffic are not calibrated for local traffic conditions and most of the traffic flow models are developed for comparatively less heterogeneous and lane-disciplined traffic. The flow-density fundamental traffic flow diagram is developed based on extensive field data collected from Karachi, Pakistan. The calibrated CTM model is validated by using actual data from another road and it was concluded that CTM is capable of modelling heterogeneous and non-lane disciplined traffic and performed very reasonably. The calibrated CTM will be a useful input for the application of traffic simulation and optimization packages such as TRANSYT, SIGMIX, DISCO, and CTMSIM.