- Traffic control and management
- Transportation Planning and Optimization
- Traffic and Road Safety
- Traffic Prediction and Management Techniques
- Autonomous Vehicle Technology and Safety
- Transportation and Mobility Innovations
- Urban and Freight Transport Logistics
- Adaptive Control of Nonlinear Systems
- Vehicular Ad Hoc Networks (VANETs)
- Human-Automation Interaction and Safety
- Advanced Graph Neural Networks
- Complex Network Analysis Techniques
- Crystallization and Solubility Studies
- Vehicle emissions and performance
- X-ray Diffraction in Crystallography
- Advanced Vision and Imaging
- Photonic Crystals and Applications
- Computer Graphics and Visualization Techniques
- Iterative Learning Control Systems
- Advanced Control Systems Optimization
- Recommender Systems and Techniques
- Image Enhancement Techniques
- Urban Transport and Accessibility
- Air Traffic Management and Optimization
- IoT and Edge/Fog Computing
Chalmers University of Technology
2020-2024
Webb School of Knoxville
2024
China Southern Power Grid (China)
2024
Macau University of Science and Technology
2024
Shantou University
2024
First Affiliated Hospital of Shantou University Medical College
2024
Jinan University
2023
Wuhan University
2022
Zhejiang University
2022
Frontier Energy (United States)
2022
Traffic incident management in metropolitan areas is crucial for the recovery of road systems from accidents as well mobility and safety community. With continuous improvement computation communication technologies, connected automated vehicles (CAVs) exhibit potential to relieve incident-induced traffic degradation. To understand benefits CAVs on incidents, this paper models impacts with joint consideration microscopic CAV driving behaviors macroscopic assignment mixed environment...
Emergency vehicles (EVs) play a crucial role in providing timely help for the general public saving lives and avoiding property loss. However, very few efforts have been made EV prioritization on normal road segments, such as section between intersections or highways ramps. In this paper, we propose an lane pre-clearing strategy to prioritize EVs roads through cooperative driving with surrounding connected (CVs). The problem is formulated mixed-integer nonlinear programming (MINP) aiming at...
Dynamic traffic demand has been a longstanding challenge for the conventional transit system design and operation.The recent development of autonomous vehicles (AVs) makes it increasingly realistic to develop next generation transportation systems with potential improve operational performance flexibility.In this study, we propose an innovative modular buses (AMBs) that is adaptive dynamic demands not restricted fixed routes timetables.A unique transfer operation, termed as "in-motion...
Future connected vehicles: Communications demands, privacy and cyber-security 3
By reducing film thickness to a few nanometers, the narrow-band-gap CuS turns highly transparent. Surface modification by self-assembled monolayer is key factor obtain thin, dense, and continuous film. The growth mechanism identified as “layer-by-layer followed islanding.” After annealing, p-type conductivity of ∼2×103Scm−1 achieved at room temperature, thinnest conductive has an average transparency 92% between 400 800nm. Using films front contact layers, dye-sensitized solar cell was...
Abstract This paper presents a cooperative traffic control strategy to increase the capacity of nonrecurrent bottlenecks such as work zones by making full use spatial resources upstream zones. The area is divided into two zones: regulation and merging areas. basic logic that large gap more efficient in accommodating vehicles than several small scattered gaps with same total length. In area, nonlinear programming model developed balance both improvements safety risks. A two‐step solving...
Shared electric scooters (e-scooter) are booming across the world and widely regarded as a sustainable mobility service. An increasing number of studies have investigated e-scooter trip patterns, safety risks, environmental impacts, but few considered energy efficiency e-scooters. In this research, we collected operational data e-scooters from major provider in Gothenburg to shed light on performance real cases. We first develop multiple logarithmic regression model examine consumption...
Purpose This study aims to make full use of the advantages connected and autonomous vehicles (CAVs) dedicated CAV lanes ensure all CAVs can pass intersections without stopping. Design/methodology/approach The authors developed a signal coordination model for arteries with by using mixed integer linear programming. non-stop constraints are proposed adapt characteristics CAVs. As it is continuous problem, various situations that arrive at analyzed. rules discovered simplify problem...
Integrating a foreground object into background scene with illumination harmonization is an important but challenging task in computer vision and augmented reality community. Existing methods mainly focus on appearance consistency or the shadow generation, which rarely consider global harmonization. In this paper, we formulate seamless as exchange aggregation problem. Specifically, firstly apply physically-based rendering method to construct large-scale, high-quality dataset (named IH) for...
An unconventional left-turn treatment called contraflow lane (CLL) design has been increasingly used in China to relieve traffic congestion associated with movements at signalized intersections. This study proposed a procedure for estimating the queue length intersections CLL design. Field data were collected six approaches five city of Handan, China, and 40 h recorded. A binary logit model was developed estimate probability driver stopping presignal when there are still vacant spaces...
Connected and Automated Vehicles (CAVs) are characterized by diverse communication attributes, embodying the trajectory of future automotive progress. Meanwhile, transportation system will be in a mixed stage CAVs Human-Driven (HDVs) for long time. The study capacity strategies traffic systems is great significance popularization deployment infrastructures. However, current research mainly focuses on analysis scenario with full penetration CAVs, while influence caused HDVs Vehicle-to-Vehicle...
With increasing traffic demand in urban areas of metropolises, many tunnels have been constructed to improve road capacity and mobility. The distance between two consecutive is relatively short which usually forms a weaving section, leading considerable conflicts. objective this study evaluate the safety performance such inter-tunnel sections. Conflict prediction models based on negative binomial regression were developed identify influential factors. Field data collected at ten selected...
Graph embedding is becoming increasingly popular due to its ability of representing large-scale graph data by mapping nodes low-dimensional space. Current research usually focuses on transductive learning, which aims generates fixed node embeddings training the whole graph. However, dynamic changes constantly with new additions and interactions. Unlike inductive learning attempts dynamically generate over time even for unseen nodes, more suitable real-world applications. Therefore, we...
The primary objective of this study is to predict the short‐term demand free‐floating bike sharing (FFBS) using deep learning approach. FFBS trip data in Shanghai city are collected from Mobike Company. Other datasets such as weather and air quality also collected. spatiotemporal patterns indicates that weekday rides exhibit an obvious commuting pattern while weekend usually involved with various purposes. Then, a hybrid neural network (HDL‐net) developed for different time intervals...
Most of the recent studies tackling routing problems like Traveling Salesman Problem (TSP) with machine learning use a transformer or Graph Neural Network (GNN) based encoder architecture. However, many them apply these encoders naively by allowing to aggregate information over whole TSP instances. We, on other hand, propose data preprocessing method that allows focus most relevant parts instances only. In particular, we graph sparsification for representations passed GNNs and attention...
Academic papers are the cornerstone of knowledge dissemination and crucial for researchers' career development. This is particularly true rapidly evolving research domains such as transportation, evidenced by surge journals in past decade. While abundant literature offers guidance on successful publication strategies, insights into reasons rejection rare. study fills this gap examining why rejected area transportation. We present concrete evidence based data from over 5,000 transport papers....