Traffic prediction, as a core component of intelligent transportation systems (ITS), has been investigated thoroughly in the literature. Nevertheless, timely accurate traffic prediction still remains an open challenge due to nonlinearities and complex patterns flows. In addition, most existing methods focus on grid-based computing problems (e.g., crowd in-out flow prediction) point-based detector data prediction), ignoring segment-based tasks. this study, we propose attention-based...

Pedestrians are the most vulnerable road users due to lack of mass, speed, and protection compared other types users. Adverse weather conditions may reduce friction visibility thus increase crash risk. There is limited evidence considerable discrepancy with regard impacts on injury severity in literature. This article investigated factors affecting pedestrian level under different based a publicly available accident database Great Britain.Accident data from Britain that through STATS19 were...

We present a novel approach for simulating thin hyperelastic skin. Real human skin is only few millimeters thick. It can stretch and slide over underlying body structures such as muscles, bones, tendons, revealing rich details of moving character. Simulating challenging because it in close contact with the shares its geometry. Despite major advances elastodynamics cloth soft bodies computer graphics, methods are difficult to use due need deal non-conforming meshes, collision detection,...

Gradual penetration of automated vehicles (AVs) into current motorway systems will usher the stage mixed traffic in which AVs coexist with human driven vehicles. Thus, there is an urgent need to identify possible impacts this on operation. To investigate potential benefits or losses due introducing existing systems, study conducts a comprehensive evaluation based simulation using 5.3 km stretch Auckland Motorway and data provided by New Zealand Traffic Agent (NZTA). We analyze different AV...

The COVID-19 pandemic has severely impacted human activities in a way never documented modern history. prevention policies and measures have abruptly changed well-established urban mobility patterns. In this context, we exploit different sources of data to gain insights into the effects restrictive on daily exhaust emissions post-pandemic periods. Manhattan, most densely populated borough New York City, is chosen as study area. We collect generated by taxis, sharing bikes, road detectors...

Abstract Let $E$ be a uniform bundle on an arbitrary generalized Grassmannian $X$ defined over $\mathbb{C}$. We show that if the rank of is at most so-called effective good divisibility variety minimal rational tangents ($e.d.(\textrm{VMRT})$ for short), then necessarily splits. For some Grassmannians, we prove upper bounds $e.d.(\textrm{VMRT})$ are optimal and classify all unsplit bundles ranks. Under special assumptions, morphisms to flag varieties must constant, which partially answers...

Abstract Federated learning (FL) is a technology that allows multiple devices to collaboratively train global model without sharing original data, which hot topic in distributed intelligent systems. Combined with satellite network, FL can overcome the geographical limitation and achieve broader applications. However, it also faces issues such as straggler effect, unreliable network environments non-independent identically (Non-IID) samples. To address these problems, we propose an...

Summary Variable speed limit (VSL) is an emerging intelligent transportation system (ITS) measure to improve operational and safety performance of motorway systems. Rule‐based algorithms have been widely used in VSL applications because their comprehensibility ease application. However, most the proposed literature under this category are rather rough for control. Pre‐specified rules show some difficulties appropriately activating/deactivating control actions real time non‐stationary...

Massive bike-sharing systems (BSS) usage and performance data have been collected for years over various locations. Nevertheless, researchers encountered several challenges while dealing with massive BSS data. The that could be enhanced in the previous studies are 1) reducing high dimensionality noise of time series 2) extracting informative patterns out This paper extracts reduce dimensions by exploring representation clustering A reduced dimension allows us to efficiently approximate...

With the development of artificial intelligence (AI) and continuous improvement medical informatization, health assessment auxiliary diagnosis based on physiological time series has become a hot research topic. However, direct use raw data is inappropriate due to privacy protection regulations in medial scenarios. Therefore, we designed privacy-preserved framework Visibility Graph (VG) transformation Neural Network (GNN) for multi-classification. In particular, proposed Time Labeled (TLVG),...

This study presents a comprehensive framework for estimating passengers' transfer times and extracting their distribution related routes using WIFI probe data. The departure time of preceding station, arrival subsequent train running are selected to obtain times. Then, the collected data is analyzed kernel density estimation candidate distribution. Gaussian mixture models adopted extract each possible route at both peak hours off-peak hours. method tested two stations Xi'an metro system with...

Ramp metering (RM) and variable speed limits (VSLs) are two widely used intelligent transportation system (ITS) means to improve manage motorway traffic. The former controls the flow of traffic into motorways from on-ramps, latter affects on main line. An integrated approach prudent use these ITS measures can help achieve optimal utilization motorways. This study proposed a new method integrate RM with VSL controllers attain an efficient equitable system. was combine local coordinated...

Variable speed limits (VSLs) have a potential to improve mobility and safety of motorway through harmonisation traffic flow. However, the success VSL is highly dependent on drivers’ compliance displayed limits. Emerging technologies in field connected autonomous vehicles (CAVs) likely revolutionise way will be operated near future. can integrated with CAVs where automatically obey 100% penetration rate long‐term goal. At initial stage deployment, coexist manually driven motorways. This study...

Freeway traffic management and control often rely on input from fixed-point sensors. A sufficiently high sensor density is required to ensure data reliability accuracy, which results in installation maintenance costs. Moreover, sensors encounter difficulties provide spatiotemporally wide-ranging information due the limited observable area. This research exploits utilization of connected automated vehicles (CAVs) as an alternative source for freeway management. To handle inherent uncertainty...

Due to unavoidable expansion of car-ownership, traffic congestion and emissions in developing countries keep on increasing. Meanwhile, high construction costs statutory restrictions hinder traditional road infrastructure improvement projects. Thus, exploring cost-effective management solutions relieve becomes one the most significant challenges faced by transportation authorities, especially countries. Active (ATM) systems that are environmentally sustainable relatively low-cost particularly...

Rapidly advancing hardware and software technologies have made it possible to develop a new generation of supervisory control data-acquisition (SCADA) system. The Web-based SCADA system described here consists intelligent RTUs, each which has modularized architecture supports HTTP protocol, distributed master station, Web server/browser structure decomposes the functions into multiple sets site components. Both design development for this been carried out in accordance with well-proven...

Most existing bike usage prediction studies aim at building models to fit continuous data rather than categorical data, which may result in an over-fitting problem and therefore reduce the potential of model capture more generalized trends predictions. This study explores a multi-categorical probabilistic approach for sharing demand prediction. In order overcome weakness using single point measurements describe conditions, we prepare three alternatives range, local variation, trend over...