A5101791696- Industrial Vision Systems and Defect Detection
- Integrated Circuits and Semiconductor Failure Analysis
- Advanced Neural Network Applications
- Advanced Fiber Laser Technologies
- Photonic Crystal and Fiber Optics
- Laser-Matter Interactions and Applications
- Wireless Communication Security Techniques
- Smart Grid Security and Resilience
- Hand Gesture Recognition Systems
- Human Pose and Action Recognition
- Radiation Effects and Dosimetry
- Breast Cancer Treatment Studies
- Radar Systems and Signal Processing
- Radiomics and Machine Learning in Medical Imaging
- Perovskite Materials and Applications
- Chaos-based Image/Signal Encryption
- 3D Modeling in Geospatial Applications
- Gait Recognition and Analysis
- Electrostatic Discharge in Electronics
- Electric Vehicles and Infrastructure
- Physical Unclonable Functions (PUFs) and Hardware Security
- Intelligent Tutoring Systems and Adaptive Learning
- Visual Attention and Saliency Detection
- QR Code Applications and Technologies
- Diabetic Foot Ulcer Assessment and Management
Shanghai Jiao Tong University
2011-2024
Sun Yat-sen University
2024
The First Affiliated Hospital, Sun Yat-sen University
2024
Xiangya Hospital Central South University
2024
Central South University
2024
Zunyi Normal College
2024
Harbin Medical University
2024
Third Affiliated Hospital of Harbin Medical University
2024
Universiti Sains Malaysia
2023
The People's Hospital of Guangxi Zhuang Autonomous Region
2019-2023
Printed circuit boards (PCBs) are a nearly ubiquitous component of every kind electronic device. With the rapid development integrated and semiconductor technology, size PCB can shrink down to very tiny dimension. Therefore, high-precision defect detection in PCBs needs be achieved. This paper reviews various methods by analysing more than 100 related articles from 1990 2022. The methodology how prepare this overview is firstly introduced. Secondly, manual reviewed briefly. Then, traditional...
Effective detection of dense printed circuit board (PCB) components contributes to the optimization automatic flow production. In addition, PCB component recognition is also essential prerequisite for early defect detection. Current approaches are not adept in both rapid and precise YOLOv8 models have exhibited effective performances detecting common objects, such as person, car, chair, dog etc. However, it still tricky inspect disparate precisely. Thus, a novel convolution neural network...
Abstract Background Identifying breast cancer patients with DNA repair pathway-related germline pathogenic variants (GPVs) is important for effectively employing systemic treatment strategies and risk-reducing interventions. However, current criteria risk prediction models prioritizing genetic testing among do not meet the demands of clinical practice due to insufficient accuracy. Methods The study population comprised 3041 enrolled from seven hospitals between October 2017 11 August 2019,...
Abstract Printing circuit board (PCB) defect inspection precisely and efficiently is an essential challenging issue. Therefore, based on several improvements upon YOLOv5‐nano, a novel lightweight detector named TD‐YOLO proposed to inspect tiny defects in PCBs. First, the ShuffleNet block implemented into backbone effectively reduce model weight. Second, anchors are designed using modified k‐means clustering accelerate convergence yield superior detection precision. Then, data augmentation...
Poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS) is a frequently used hole transport layer (HTL) that often constrains the stability and efficiency of inverted perovskite solar cells (PSCs) because its hydrophilic properties. In study, hydrophobic fluorinated derivative (PM6) was employed as an interfacial modifier for PEDOT:PSS layer. Modification with PM6 improved hydrophobicity work function (WF) mitigated formation charge recombination centers (Pb0) on surface. The...
Fully automatic postural assessment is highly useful, but has been challenging. Conventional methods either require manual by ergonomists or depend on special devices that are intrusive, thus being hardly feasible in daily activities and workplaces. In this work, an attention-based convolutional neural network (CNN) developed for whole-body assessment. The proposed learns to identify relevant regions (or body parts) extract features automatically. Risk of the posture estimated from extracted...
Abstract In order to investigate the process of optically triggered discharge formation, a model ion space-charge formation based on classical plane electrodes and revised for characteristic hollow-cathode (HCD) configuration is proposed in this paper. The primary modified factor our penetrating electric-field parameter, which influences ionization trigger electrons calculated via particle simulation. Optical-trigger experiments are carried out using different voltages under seed-electron...
A high accuracy variable beam entrance Faraday cup (VBEFC) system is designed in this work. The presented VBEFC for the current profile measurement of transient hollow cathode discharge (THCD) generated pulsed electron beam, which a new source energy flux metallic material processing. By proper designs array, fast response collector, grounding, and shielding, capable determining radial its temporal evolution THCD beam. results density distributions collected at varying locations times under...
Abstract Background While platinum sensitivity and resistance have long been central to treatment decisions in high-grade serous ovarian cancer (HGSOC), these categories are increasingly questioned real-world clinical settings. This study seeks develop a prognostic model based on platinum-free interval (PFI) as reliable indicator of patient prognosis, with additional exploration chemotherapy resistance-related genes pathways. Methods 70 HGSOC patients varied gene expression profiles...
To penetrate sensitive communication systems, attackers can attack the channel using an Active Time-Varying(ATV) way, which will lead to a great information loss. The conventional approach is encrypt original signal making it difficult for get information. However, this technology constrained by limited wireless terminal equipment. In paper, we choose insert artificial noise into channel, aims at disturbing and reducing loss of system once attacks occur. However has some side effects...