A5086380403- Traffic Prediction and Management Techniques
- Autonomous Vehicle Technology and Safety
- Transportation Planning and Optimization
- Neural Networks and Applications
- Transportation and Mobility Innovations
- Advanced Clustering Algorithms Research
- Older Adults Driving Studies
- EEG and Brain-Computer Interfaces
- Complex Network Analysis Techniques
- Computer Graphics and Visualization Techniques
- Traffic control and management
- Underground infrastructure and sustainability
- Human-Automation Interaction and Safety
- Mitochondrial Function and Pathology
- Advanced Bandit Algorithms Research
- Spatial and Panel Data Analysis
- Congenital heart defects research
- Extracellular vesicles in disease
- Image Enhancement Techniques
- Space Satellite Systems and Control
- Smart Grid Energy Management
- Fluid Dynamics Simulations and Interactions
- Tissue Engineering and Regenerative Medicine
- Electric Vehicles and Infrastructure
- Software System Performance and Reliability
New York University
2019-2025
University Transportation Research Center
2021-2024
SMART Global Holdings (United States)
2020
SMART Reading
2020
Nanchang Hangkong University
2018
A recent study suggests that systemic hypoxemia in adult male mice can induce cardiac myocytes to proliferate. The goal of the present experiments was confirm these results, provide new insights on mechanisms cardiomyocyte cell cycle reentry, and determine if also induces proliferation female mice.
Nowadays, electric vehicles (EVs) are increasingly equipped with advanced onboard devices capable of collecting and recording real-time charging data. The analysis such data from a large-scale EV fleet plays crucial role in supporting decision-making processes, particularly the deployment infrastructure formulation EV-focused policies. Nevertheless, challenges these significant, primarily due to privacy concerns high costs associated access. In response, this study introduces an innovative...
Few therapies have produced significant improvement in cardiac structure and function after ischemic injury (ICI). Our possible explanation is activation of local inflammatory responses negatively impact the repair process following injury. Factors that can alter immune response, including significantly altered cytokine levels plasma polarization macrophages T cells towards a pro-reparative phenotype myocardium post-MI valid strategy for reducing infarct size damage myocardial previous...
While deep learning has shown success in predicting traffic states, most methods treat it as a general prediction task without considering transportation aspects. Recently, graph neural networks have proven effective for this task, but few incorporate external factors that impact roadway capacity and flow. This study introduces the Roadway Capacity Driven Graph Convolution Network (RCDGCN) model, which incorporates static dynamic attributes spatio-temporal settings to predict network-wide...
Although traffic prediction has been receiving considerable attention with a number of successes in the context intelligent transportation systems, states over complex network that contains different road types remained challenge. This study proposes multi-scale graph wavelet temporal convolution (MSGWTCN) to predict networks. Specifically, spatial block is designed simultaneously capture information at levels, and gated employed extract dependencies data. The model jointly learns mount...
This study aims to develop a neural network model predict work zone capacity including various uncertainties stemming from traffic and operational conditions. The is formulated in terms of the number total lanes, open heavy vehicle percentage, intensity, duration. data used this paper are obtained previous studies published literature. To capture uncertainty capacity, provides two recent methods that enable models generate prediction intervals which determined by mean standard error....
In many large-scale evacuations, public agencies often have limited resources to evacuate all citizens, especially vulnerable populations such as the elderly and disabled people, demand for additional transportation means evacuation can be high. The recent development of ride-sourcing companies leveraged in evacuations an important resource future planning. contrast transit, availability drivers is highly dependent on price, since surge pricing will occur when high supply low. key challenge...
In traditional methods, fundamental diagrams (FDs) were calibrated offline with a limited number of links. Although few recent studies have paid attention to employing cluster techniques calibrate link FDs for network level analysis, they mainly focused on heuristic clustering such as k-means and hierarchical algorithm which might lead poor performance when there are overlaps between clusters. This paper proposed mixture model-based framework simulation. method can be applied discover...
Accurately and safely predicting the trajectories of surrounding vehicles is essential for fully realizing autonomous driving (AD). This paper presents Human-Like Trajectory Prediction model (HLTP++), which emulates human cognitive processes to improve trajectory prediction in AD. HLTP++ incorporates a novel teacher-student knowledge distillation framework. The "teacher" equipped with an adaptive visual sector, mimics dynamic allocation attention drivers exhibit based on factors like spatial...
The primary goal of traffic accident anticipation is to foresee potential accidents in real time using dashcam videos, a task that pivotal for enhancing the safety and reliability autonomous driving technologies. In this study, we introduce an innovative framework, AccNet, which significantly advances prediction capabilities beyond current state-of-the-art (SOTA) 2D-based methods by incorporating monocular depth cues sophisticated 3D scene modeling. Addressing prevalent challenge skewed data...
Traditional mobility management strategies emphasize macro-level oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics (DT-DIMA) system. The DT-DIMA system integrates real-time traffic information pan-tilt-cameras (PTCs), synchronizes this data into digital twin to accurately replicate the physical world, and predicts network-wide in real...
Transportation equity research has traditionally emphasized service accessibility and destination reachability while often overlooking the critical aspects of quality, such as infrequent schedules or overcrowded vehicles. This oversight can lead to a skewed understanding equity, high does not guarantee high-quality service. Addressing this gap, we propose transportation index called multi-dimensional, high-granularity (MDHG) index. Such an considers quality alongside population demographics....
This study aims to address the challenges of automatically recognizing and sizing work zones in complex urban environments. We developed a deep-learning based zone object detection model with data-centric approach iteratively enhance model's performance by augmenting custom training dataset collected from multiple sources, thereby overcoming sparsity annotated real-world images. The data is acquired traffic cameras, mined web, 3D-simulated An innovative topology-based inference method...
The rapid growth in terms of the availability transportation data provides great potential for introduction emerging data-driven methodologies into transportation-related research and development efforts. However, advanced models, such as artificial-intelligence based approaches, usually contain complicated modeling structures require strict formats along with a very complex execution environment. It is thus often challenging to deploy implement models real-world Moreover, full-fledged...