A5102016858- Guidance and Control Systems
- Robotic Path Planning Algorithms
- Aerospace and Aviation Technology
- Image and Video Quality Assessment
- Visual perception and processing mechanisms
- Evaluation Methods in Various Fields
- Wireless Sensor Networks and IoT
- Energy, Environment, and Transportation Policies
- Vehicle emissions and performance
- Muscle activation and electromyography studies
- Hand Gesture Recognition Systems
- Advanced Adaptive Filtering Techniques
- Advanced Sensor and Control Systems
- Color Science and Applications
- Image Enhancement Techniques
- Tactile and Sensory Interactions
- Image and Signal Denoising Methods
- Hate Speech and Cyberbullying Detection
- Visual Attention and Saliency Detection
- Air Traffic Management and Optimization
- Digital Filter Design and Implementation
- Electric Vehicles and Infrastructure
China Southern Power Grid (China)
2024-2025
University of Shanghai for Science and Technology
2023
Tongji University
2020
Queensland University of Technology
2012-2015
Australian Genome Research Facility
2012
Tohoku University
1995
The rapid proliferation of electric vehicles (EVs) necessitates advanced infrastructural adaptations to accommodate increased demand. This paper introduces a novel dynamic spatiotemporal graph neural network (D-ST-GNN) model designed optimize the placement and management EV charging stations in urban environments. Leveraging real-time data theory, D-ST-GNN dynamically represents evolving landscape, incorporating factors such as traffic patterns, station connectivity, user Employing...
A number of hurdles must be overcome in order to integrate unmanned aircraft into civilian airspace for routine operations. The ability the land safely an emergency is essential reduce risk people, infrastructure, and aircraft. To date, few field‐demonstrated systems have been presented that show online replanning repeatability from failure touchdown. This paper presents development guidance, navigation, control (GNC) component automated landing system (AELS) intended address this gap,...
Deaf and hearing-impaired people always face communication barriers. Non-invasive surface electromyography (sEMG) sensor-based sign language recognition (SLR) technology can help them to better integrate into social life. Since the traditional tandem convolutional neural network (CNN) structure used in most CNN-based studies inadequately captures features of input data, we propose a novel inception architecture with residual module dilated convolution (IRDC-net) enlarge receptive fields...
This study uses the cosine similarity ratio, embedding regression, and manual re-annotation to diagnose hate speech classification. We begin by computing ratio on a dataset "Measuring Hate Speech" that contains 135,556 annotated comments social media. way, we show basic use of as description content. then classification starting from understanding inconsistency human annotation dataset. Using regression diagnostic, found female annotators are more sensitive racial slurs target black...
The quality of acquired images can be surely reduced by improper exposures. Thus, in many vision-related industries, such as imaging sensor manufacturing and video surveillance, an approach that routinely accurately evaluate exposure levels is urgent need. Taking image input, a method expected to output scalar value, which represent the overall perceptual level examined image, ranging from extremely underexposed overexposed. However, studies focusing on assessment (IELA) are quite sporadic....
The paper discusses three approximations of IIR periodically time-varying (PTV) digital filters. Two conventional approximations, i.e. time-invariant difference equation and PTV are first reviewed. It turns out that computation hardware complexity the two is in proportion to period. To reduce an efficient approximation based on extended Pade proposed. With this approximation, frequency-domain specifications approximated by a with coefficients. How design how determine order obtain desired...