A5020376195- Human Pose and Action Recognition
- Vehicular Ad Hoc Networks (VANETs)
- Autonomous Vehicle Technology and Safety
- Network Security and Intrusion Detection
- Diabetic Foot Ulcer Assessment and Management
- Stroke Rehabilitation and Recovery
- Evacuation and Crowd Dynamics
- Video Surveillance and Tracking Methods
- Genetics and Neurodevelopmental Disorders
- Genomics and Rare Diseases
- Anomaly Detection Techniques and Applications
- Congenital heart defects research
- Gait Recognition and Analysis
- Advanced Malware Detection Techniques
- Non-Invasive Vital Sign Monitoring
- Hand Gesture Recognition Systems
Oakland University
2022-2025
Children's Hospital of Zhejiang University
2022
Traditional limb kinematic analysis relies on manual goniometer measurements. With computer vision advancements, integrating RGB cameras can minimize labor. Although deep learning-based aim to offer the same ease as goniometers, previous approaches have prioritized accuracy over efficiency and cost PC-based devices. Nevertheless, healthcare providers require a high-performance, low-cost, camera-based tool for assessing upper lower range of motion (ROM). To address this, we propose...
Controller Area Network (CAN) is the de facto standard for in-vehicle networks. However, it inherently vulnerable to various attacks due lack of security features. Intrusion detection systems (IDSs) are considered effective approaches protect IDSs based on advanced deep learning algorithms have been proposed achieve higher accuracy. those generally involve high latency, require considerable memory space, and often result in energy consumption. To accelerate intrusion also reduce costs, we...
Human pose estimation (HPE) is a crucial computer vision task with wide range of applications in sports medicine, healthcare, virtual reality, and human-computer interaction. The demand for real-time HPE solutions necessitates the development efficient deep-learning models that can be deployed on resource-constrained devices. While few surveys exist this area, none delve deeply into critical intersection efficiency performance. This survey reviews state-of-the-art deep learning approaches...
<div class="section abstract"><div class="htmlview paragraph">In the dense fabric of urban areas, electric scooters have rapidly become a preferred mode transportation. As they cater to modern mobility demands, present significant safety challenges, especially when interacting with pedestrians. In general, e-scooters are suggested be ridden in bike lanes/sidewalks or share road cars at maximum speed about 15-20 mph, which is more flexible and much faster than pedestrians...
<div class="section abstract"><div class="htmlview paragraph">Controller Area Network (CAN), the de facto standard for in-vehicle networks, has insufficient security features and thus is inherently vulnerable to various attacks. To protect CAN bus from attacks, intrusion detection systems (IDSs) based on advanced deep learning methods, such as Convolutional Neural (CNN) Recurrent (RNN), have been proposed detect intrusions. However, those models generally introduce high latency,...
Mono-allelic loss-of-function variants in ARFGEF1 have recently caused a developmental delay, intellectual disability, and epilepsy, with varying clinical expressivity. However, given the heterogeneity low-penetrance mutations of ARFGEF1-related neurodevelopmental disorder, robustness gene-disease association requires additional evidence. In this study, five novel heterozygous were identified unrelated pediatric patients disorders, including one missense change (c.3539T>G), two canonical...
Upper limb kinematic analysis that has been employed in the clinical assessment of motion functions or rehabilitation training is traditionally tested manually with a goniometer. Nowadays, it trend to deploy different technology and devices including low-cost but accurate RGB cameras order save manual efforts. Among these, new method using deep learning-based investigated provide same ease accessibility as handheld The key measuring upper Range Motion (ROM) camera estimate joints accurately....