A5032950508- Crystallization and Solubility Studies
- X-ray Diffraction in Crystallography
- Advanced Image and Video Retrieval Techniques
- Electrochemical Analysis and Applications
- Electrochemical sensors and biosensors
- Remote-Sensing Image Classification
- Asymmetric Hydrogenation and Catalysis
- Advanced biosensing and bioanalysis techniques
- Advanced Vision and Imaging
- Innovative concrete reinforcement materials
- Metal complexes synthesis and properties
- Conducting polymers and applications
- Multimodal Machine Learning Applications
- Image Retrieval and Classification Techniques
- Advanced Image Fusion Techniques
- Remote Sensing and Land Use
- Advanced Neural Network Applications
- Organic Electronics and Photovoltaics
- Domain Adaptation and Few-Shot Learning
- Human Pose and Action Recognition
- Image and Signal Denoising Methods
- Recycled Aggregate Concrete Performance
- Concrete and Cement Materials Research
- Generative Adversarial Networks and Image Synthesis
- Sparse and Compressive Sensing Techniques
Guangdong University of Technology
2019-2025
University of Electronic Science and Technology of China
2025
Ministry of Education of the People's Republic of China
2022-2024
Sichuan University
2024
Fujian Agriculture and Forestry University
2024
Nanjing University of Science and Technology
2022-2023
Zhejiang University of Science and Technology
2010-2023
South China University of Technology
2023
Fujian University of Technology
2023
Zhejiang University
2017-2023
With the rapid development of deep learning technology and improvement in computing capability, has been widely used field hyperspectral image (HSI) classification. In general, models often contain many trainable parameters require a massive number labeled samples to achieve optimal performance. However, regard HSI classification, large is generally difficult acquire due difficulty time-consuming nature manual labeling. Therefore, research works focus on building model for classification...
Abstract In the quest for identification of catalytic transformations to be used in chemical biology and medicinal chemistry, we identified iron(III) meso ‐tetraarylporphines as efficient catalysts reduction aromatic azides their amines. The reaction uses thiols reducing agents tolerates water, air, other biological components. A caged fluorophore was employed demonstrate that can performed even living mammalian cells. However, vivo experiments nematodes ( Caenorhabditis elegans ) zebrafish...
With the development of hyperspectral imaging technology, images (HSIs) have become important when analyzing class ground objects. In recent years, benefiting from massive labeled data, deep learning has achieved a series breakthroughs in many fields research. However, labeling HSIs requires sufficient domain knowledge and is time-consuming laborious. Thus, how to apply effectively small samples an topic research HSI classification. To solve this problem, we propose semisupervised Siamese...
Surface defect detection plays an essential role in industry, and it is challenging due to the following problems: 1) similarity between nondefect texture very high, which eventually leads recognition or classification errors 2) size of defects tiny, are much more difficult be detected than larger ones. To address such problems, this article proposes adaptive image segmentation network (AIS-Net) for pixelwise surface defects. It consists three main parts: multishuffle-block dilated...
Accurate segmentation of 3D dental models derived from intra-oral scanners (IOS) is one the key steps in many digital applications such as orthodontics and implants. However, it difficult to accurately segment individual teeth gums due following problems: 1) shape appearance adjacent are very similar, which easy be misidentified; 2) boundary between often indistinct, especially orthodontic patients with abnormalities missing crowded teeth. To solve problems, a Dual-Branch Geometric Attention...
Abstract Simplifying solution‐processing of bulk‐heterojunction (BHJ) organic solar cells (OSCs) via efficient interfacial layers with good generality is in great demand for pushing their large‐scale applications. In this study, such a novel and cost‐effective self‐assembled monolayer (SAM) reported herein as hole transport layer (HTL) high efficiency OSCs. The SAM‐structured 4‐(5,9‐dibromo‐7 H ‐dibenzo[ c , g ]carbazol‐7‐yl)butyl)phosphonic acid (DCB‐BPA) enables not only enhanced photon...
The disorder of the macrophage phenotype and hostile by-product lactate evoked by pathogenic infection in hypoxic deep wound inevitably lead to stagnant skin regeneration. In this study, hydrogen sulfide (H
In the hyperspectral image, each pixel corresponds to a small area on Earth's surface and represents intrinsic characteristic of objects, which can be applied for recognition land covers. Nevertheless, image processing should face some critical issues, sample set problem may most challenging one in research. Deep learning (DL), has successfully been many fields, also introduced classification. However, large gap between massive parameters tuned limited labeled samples lead overfitting...
A 3-D Gabor wavelet provides an effective way to obtain the spectral-spatial-fused features for hyperspectral image, which has shown advantageous performance material classification and recognition. In this paper, instead of separately employing magnitude phase features, which, respectively, reflect intensity variation surface materials in local area, a cascade superpixel regularized feature fusion (CSRGFF) approach been proposed. First, filters with particular orientation are utilized...
Accurate and rapid diagnosis of COVID-19 using chest X-ray (CXR) plays an important role in large-scale screening epidemic prevention. Unfortunately, identifying from the CXR images is challenging as its radiographic features have a variety complex appearances, such widespread ground-glass opacities diffuse reticular-nodular opacities. To solve this problem, we propose adaptive attention network (AANet), which can adaptively extract characteristic findings infected regions with various...
This study presents the results of a comprehensive experimental program on compressive behavior hybrid fiber-reinforced polymer (FRP)–concrete–steel double-skin tubular columns (DSTCs) filled with ultrahigh-performance concrete (UHPC) or engineered cementitious composites (ECC). The use UHPC ECC, being novel engineering material unique characteristics, leads to many advantages such DSTCs compared conventional normal strength (NSC). Particularly, tendency cracking FRP tube and NSC in could be...
LLMs have demonstrated remarkable abilities at interacting with humans through language, especially the usage of instruction-following data. Recent advancements in LLMs, such as MiniGPT-4, LLaVA, and X-LLM, further enlarge their by incorporating multi-modal inputs, including image, video, speech. Despite effectiveness generating precise detailed language understanding given modality signal, these give up ability to ground specific parts thus only constructing a coarse-grained mapping....
Abstract Background The objective of this study was to evaluate the effect bone marrow mesenchymal stem cells (BMSCs) on apoptosis granulosa (GCs) in rats. BMSCs and GCs were isolated from separated into one following three groups: an untreated control group (control), a cisplatin (5 mg/L) treatment (cisplatin), co-cultured with treated (BMSC). GC analyzed by annexin V staining real-time PCR analysis for apoptosis-related genes. also determined 9 10 month-old perimenopausal rats that saline...
Brick waste is the second-largest source of China's construction and demolition waste. Reprocessing brick into recycled aggregate (RBA) to fabricate new concrete [i.e., (RBAC)] has proved be an effective solution. RBAC generally used as nonstructural owing its inferior mechanical durability properties compared with natural (NAC). To achieve substantially enhanced that would qualify for potential structural use, fiber-reinforced polymer (FRP) jacketing will adopted in this study provide...
Automatic diagnosis of Coronavirus disease 2019 (COVID-19) using chest computed tomography (CT) images is great significance for preventing its spread. However, it difficult to precisely identify COVID-19 due the following problems: 1) location and size lesions can vary greatly in CT images; 2) unique characteristics are often imperceptible imaging findings. To solve these problems, a Deep Dual Attention Network ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Cracks in building facades are inevitable due to the age of building. found facade may be further exacerbated if not corrected immediately. Considering extensive size some buildings, there is definitely a need automate inspection routine facilitate process. The incorporation deep learning technology for classification images has proven an effective method many past civil infrastructures like pavements and bridges. There is, however, limited research built environment sector. In order align...
Asymmetric generator: Chiral (S)-2-(isopropylsulfinyl)phenol and a more electron-rich methoxy derivative (R=OCH3) are capable of inducing even catalyzing chirality-generating trans–cis isomerization two 2,2′-bipyridine ligands in an octahedral coordination sphere ruthenium complex. Detailed facts importance to specialist readers published as "Supporting Information". Such documents peer-reviewed, but not copy-edited or typeset. They made available submitted by the authors. Please note: The...
Abstract In this paper, we propose a highly accurate inpainting algorithm which reconstructs an image from fraction of its pixels. Our is inspired by the recent progress non‐local processing techniques following idea ‘grouping and collaborative filtering’. our framework, first match group similar patches in input image, then convert problem estimating missing values for stack matched to low‐rank matrix completion, finally obtain result synthesizing all restored patches. algorithm, how...
Clay brick waste is one of the largest construction wastes by output. Traditionally, clay reutilized in mortar/concrete as aggregate replacement after crushing or cement grinding, but these two methods reutilization have certain adverse effects on quality mortar/concrete. In this study, a new method, named paste was developed; dust (CBD) used to replace cementitious with composition kept unchanged. To compare effectiveness and methods, mortar mixes different ratios CBD (either replacement)...