A5100624503- Human-Automation Interaction and Safety
- Traffic and Road Safety
- Safety Warnings and Signage
- Autonomous Vehicle Technology and Safety
- Heat Transfer and Boiling Studies
- Risk and Safety Analysis
- Heat Transfer and Optimization
- Traffic control and management
- Healthcare Technology and Patient Monitoring
- Robotic Path Planning Algorithms
- Spatial Cognition and Navigation
- Advanced Neural Network Applications
- Older Adults Driving Studies
- Urban Transport and Accessibility
- Visual and Cognitive Learning Processes
- Vehicle emissions and performance
- Entrepreneurship Studies and Influences
- Robotics and Sensor-Based Localization
- Advanced MRI Techniques and Applications
- Maternal Mental Health During Pregnancy and Postpartum
- Advanced Sensor and Control Systems
- Video Surveillance and Tracking Methods
- Suicide and Self-Harm Studies
- Spinal Fractures and Fixation Techniques
- Auditing, Earnings Management, Governance
Xiamen University
2023-2025
Hebei University of Technology
2025
Institute of Software
2025
Chinese Academy of Sciences
2025
Pennsylvania State University
2018-2024
Sun Yat-sen University
2013-2024
King's College London
2024
Guangdong University Of Finances and Economics
2024
Guangdong University of Finance
2024
Dalian Medical University
2024
This paper presents a new computational framework for early detection of driver distractions (map viewing) using brain activity measured by electroencephalographic (EEG) signals. Compared with most studies in the literature, which are mainly focused on classification distracted and nondistracted periods, this study proposes to prospectively predict start end distraction period, defined map viewing. The proposed prediction algorithm was tested data set continuous EEG signals recorded from 24...
Objective This study investigated drivers’ subjective feelings and decision making in mixed traffic by quantifying driver’s driving style type of interaction. Background Human-driven vehicles (HVs) will share the road with automated (AVs) traffic. Previous studies focused on simulating impacts AVs flow, investigating car-following situations, using simulation analysis lacking experimental tests human drivers. Method Thirty-six drivers were classified into three driver groups (aggressive,...
Most existing driver models focus on predicting driving performance in normal and near-collision situations without considering the impact of collision warning parameters behavior. This study develops a cognitive computational model based Queueing Network-Model Human Processor (QN-MHP) to quantify effects key (i.e., lead time, reliability, speech style) responses, connected vehicle systems (CVSs). The was validated by comparing its predictions response type, braking steering with data from...
Owing to the high cost of modern MRI systems, their use in clinical care and neurodevelopmental research is limited hospitals universities income countries. Ultra-low-field systems with significantly lower scanning costs present a promising avenue towards global accessibility, however reduced SNR compared 1.5 or 3T limits applicability for use. In this paper, we describe deep learning-based super-resolution approach generate high-resolution isotropic T2-weighted scans from low-resolution...
The role of cellular senescence in age-related diseases has been fully recognized. In various age-related-chronic lung diseases, the function alveolar epithelial cells (AECs) is impaired and regeneration disorders, especially bronchopulmonary dysplasia，pulmonary fibrosis (PF), chronic obstructive pulmonary disease (COPD), cancer, etc. Except for an increasing number studies are exploring developmental which typically originate childhood even neonatal period. This review provides overview...
We investigate how investors value corporate hypocrisy, the ethical dissonance between philanthropic giving and environmental misconduct, further examine moderating effect of analyst coverage. Using a sample Chinese-listed firms over 2006–2019, our findings reveal that hypocrisy is significantly negatively associated with firm value, suggesting brings out contingencies uncertainties in operation, erodes perceived trust from investors, results cognitive confusion market, eventually reduces...
<title>Abstract</title> Most two-stage detection and tracking methods currently adopt IoU distance appearance features when matching target results with trajectory predictions. However, this approach has shortcomings in two main aspects: 1. The selection of feature extraction networks often relies on established methods, such as Re-ID-related which are typically complex significantly slow down algorithm processing speed. 2. Feature lack consistency extracting single-frame features, leading...
Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains. However, their reliance on multiple sequential forward passes significantly limits real-time performance. Previous acceleration methods primarily focused reducing number of sampling steps or reusing intermediate results, failing to leverage variations spatial regions within image due constraints convolutional U-Net structures. By harnessing flexibility Transformers (DiTs) in handling variable...
<title>Abstract</title> Accurate detection of extremely small targets in aerial high-resolution images is critical for military and civilian applications. However, challenges such as target size, complex backgrounds, deformation hinder optimal performance. We propose QLDNet, a lightweight network that addresses these issues through synergistic combination non-strided convolution decoupled large-kernel convolutional attention. Specifically, the constructs quadruple aggregate connection...