A5035131824- Scheduling and Optimization Algorithms
- Advanced Manufacturing and Logistics Optimization
- QR Code Applications and Technologies
- Optimization and Search Problems
- Optimization and Packing Problems
- Image Processing Techniques and Applications
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- RFID technology advancements
- Energy Load and Power Forecasting
- IoT and Edge/Fog Computing
- Digital Media Forensic Detection
- Video Surveillance and Tracking Methods
- Differential Equations and Numerical Methods
- Advanced Wireless Communication Techniques
- Advanced Optimization Algorithms Research
- Advanced Steganography and Watermarking Techniques
- Face and Expression Recognition
- Error Correcting Code Techniques
- Human Pose and Action Recognition
- Gait Recognition and Analysis
- Assembly Line Balancing Optimization
- Innovative Educational Techniques
- Energy Efficient Wireless Sensor Networks
- Supply Chain and Inventory Management
Guangdong Polytechnic Normal University
2016-2025
Beijing Jiaotong University
2023-2025
Sun Yat-sen University
2012-2024
Fujian Normal University
2022
State Intellectual Property Office
2021
SYSU-CMU International Joint Research Institute
2016-2018
Medizinische Hochschule Hannover
2018
Wenzhou Medical University
2018
Dongyang People's Hospital
2018
Changzhou Institute of Technology
2005-2012
Deep convolutional neural networks have been successfully applied to face detection recently. Despite making remarkable progress, most of the existing methods only localize each using a bounding box, which cannot segment from background image simultaneously. To overcome this drawback, we present and segmentation method based on improved Mask R-CNN, named G-Mask, incorporates into one framework aiming obtain more fine-grained information face. Specifically, in proposed method, ResNet-101 is...
Poor real-time performance in multi-QR codes detection has been a bottleneck QR code decoding-based Internet of Things (IoT) systems. To tackle this issue, we propose article rapid approach, which consists multistage stepwise discrimination (MSD) and Compressed MobileNet. Inspired by the object category determination analysis, preprocessed are extracted accurately on small scale using MSD. Guided image end-to-end model, obtain lightweight MobileNet deep weight compression manner to realize...
In this work, an assistance system based on the Artificial Intelligence of Things (AIoT) framework was designed and implemented to provide convenience for visually impaired people. This aims be low-cost multi-functional with object detection, obstacle distance measurement, text recognition achieved by wearable smart glasses, heart rate fall body temperature humidity-temperature monitoring offered intelligent walking stick. The total hardware cost is approximately $66.8, as diverse sensors...
Out-of-focus blurring of the QR code is very common in mobile Internet systems, which often causes failure authentication as a result misreading information hence adversely affects operation system. To tackle this difficulty, work firstly introduced an edge prior information, average distance between center point and clear images same batch. It motivated by theoretical analysis practical observation theory CMOS image sensing, optics blur invariants, invariance diffuse light spots. After...
Background: Mental health issues are increasingly prominent worldwide, posing significant threats to patients and deeply affecting their families social relationships. Traditional diagnostic methods subjective delayed, indicating the need for an objective effective early diagnosis method. Methods: To this end, paper proposes a lightweight detection method multi-mental disorders with fewer data sources, aiming improve procedures enable patient detection. First, proposed takes...
As the fundamental element of Internet Things, QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce logistics, we mainly focus on how to identify codes quickly accurately. An adaptive binarization approach is proposed solve problem uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, adaptively select block window robust under illumination. The method can eliminate impact effectively whilst meeting...
With RFID applying in library, this paper develops an Internet of Things System for Library Materials Management using Android based UHF mobile reader (Android reader) as its entry to increase the efficiency library materials management. The functions include user identification, inventorying, adding, refreshing, searching, and self-help borrowing & returning materials.
Abstract In Hyperspectral Imaging (HSI), the detrimental influence of noise and distortions on data quality is profound, which has severely affected following‐on analytics decision‐making such as land mapping. This study presents an innovative framework for assessing HSI band reconstructing low‐quality bands, based Prophet model. By introducing a comprehensive metric to start, authors approach factors in both spatial spectral characteristics across local global scales. effectively captures...
As the key technology for 5G applications in future, Internet of Things (IoT) is developing rapidly, and demand cultivation engineering talents IoT also expanding. The rise maker education has brought new teaching inspiration cultivating innovative technical IoT. In course, problems include lack adequate models, emphasis on products but less theory, letting students imitate practice. Focusing these problems, this paper proposes a Science, Technology, Engineering, Mathematics (STEM) model...
With the development of commodity economy, emergence fake and shoddy products has seriously harmed interests consumers enterprises. To tackle this challenge, customized 2D barcode is proposed to satisfy requirements enterprise anti-counterfeiting certification. Based on information hiding technology, approach can solve these challenging problems provide a low-cost, difficult forge, easy identify solution, while achieving function conventional barcodes. By weighting between perceptual quality...
With the development of Internet Things (IoT) technology, two-dimensional (2D) barcodes are widely used in smart IoT applications as a perception portal. In industries with many circulations and testing links like traceability, since existing 2D barcode cannot be changed once it is printed, can only replaced more expensive radio frequency identification (RFID) labels or new barcodes, causing waste human resources costs. For better circulation efficiency resource utilization, we propose...
Abstract With the development of 5G technology, short delay requirements commercialization and large amounts data change our lifestyle day-to-day. In this background, paper proposes a fast blind deblurring algorithm for QR code images, which mainly achieves effect adaptive scale control by introducing an evaluation mechanism. Its main purpose is to solve out-of-focus caused lens shake, inaccurate focus, optical noise speeding up latent image estimation in process multi-scale division...
Most birds sit on their eggs during incubation, a behaviour that likely evolved among non-avian dinosaurs. Several 'brooding' specimens of smaller species oviraptorosaurs and troodontids reveal these theropods sat eggs, although little is known incubation in larger theropod species. Here we examine egg clutches over large body size range order to understand the potential effect behaviour. Eggshell porosity indicates all were exposed nest, similar brooding birds. Although oviraptorosaur...