Zhihui Chen

ORCID: 0000-0003-0175-0404
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Computational Techniques and Applications
  • Video Surveillance and Tracking Methods
  • Genetic and phenotypic traits in livestock
  • Advanced Image and Video Retrieval Techniques
  • Photoreceptor and optogenetics research
  • Advanced Neural Network Applications
  • Genetic Mapping and Diversity in Plants and Animals
  • Functional Brain Connectivity Studies
  • Web Applications and Data Management
  • Olfactory and Sensory Function Studies
  • Visual Attention and Saliency Detection
  • Simulation and Modeling Applications
  • EEG and Brain-Computer Interfaces
  • Genetic diversity and population structure
  • Image Enhancement Techniques
  • 3D Surveying and Cultural Heritage
  • Morphological variations and asymmetry
  • Lipid Membrane Structure and Behavior
  • AI and Big Data Applications
  • Advanced Decision-Making Techniques
  • Educational Technology and Pedagogy
  • Optical Imaging and Spectroscopy Techniques
  • Digital Radiography and Breast Imaging
  • Robotics and Sensor-Based Localization
  • Advanced Image Fusion Techniques

Tianjin University of Science and Technology
2022-2023

Zhejiang University of Technology
2022

Zhejiang University
2022

Lishui Central Hospital
2022

Wenzhou Medical University
2022

Beijing University of Technology
2018-2021

South China Normal University
2021

Huaihua University
2020

Xiamen University
2016-2020

Shaoguan University
2020

Abstract Secretory vesicle swelling is central to cell secretion, but the underlying mechanism of swelling, particularly synaptic vesicles, not completely understood. The G αi3 ‐PLA2‐mediated involvement water channel AQP‐1 in regulation secretory exocrine pancreas and αo ‐mediated AQP‐6 neurons have previously been reported. Furthermore, role vH + ‐ATPase neurotransmitter transport into vesicles has also shown. Using nanometer‐scale precision measurements isolated present study reports for...

10.1002/jnr.22180 article EN Journal of Neuroscience Research 2009-07-16

The quality of remote sensing images has been greatly improved by the rapid improvement unmanned aerial vehicles (UAVs), which made it possible to detect small objects in most complex scenes. Recently, learning-based object detection introduced and gained popularity image processing. To improve accuracy small, weak scenes, this work proposes a novel hybrid backbone composed convolutional neural network an adaptive multi-scaled transformer, referred as HAM-Transformer Net. Net firstly...

10.3390/rs15194817 article EN cc-by Remote Sensing 2023-10-03

Object tracking is a challenging task in computer vision based intelligent transportation systems. Recently, Siamese object methods have attracted significant attention due to their highly efficient performance. These usually train network match the initial target patch of first frame with candidates new frame. In these methods, offline training deep neural and online instance searching are effectively combined. However, do not include template update or re-identification, which easily...

10.1109/tits.2020.3006927 article EN IEEE Transactions on Intelligent Transportation Systems 2020-07-28

Neural networks (NNs) have emerged as a new tool for genomic selection (GS) in animal breeding. However, the properties of NN used GS prediction phenotypic outcomes are not well characterized due to problem over-parameterization and difficulties using whole-genome marker sets high-dimensional input. In this note, we developed an R package called snnR that finds optimal sparse structure by minimizing square error subject penalty on L1-norm parameters (weights biases), therefore solving NN. We...

10.1093/jas/sky071 article EN Journal of Animal Science 2018-02-24

Abstract Images captured in low light conditions suffer from visibility, blurred details and strong noise, resulting unpleasant visual appearance poor performance of high level tasks. To address these problems, existing approaches have attempted to enhance the visibility low-light images using convolutional neural networks (CNN). However, due insufficient consideration characteristics information different frequency layers image, most them yield blurry amplified noise. In this work, fully...

10.1038/s41598-023-40899-8 article EN cc-by Scientific Reports 2023-08-29

Classification of dynamic functional connectivity (DFC) is becoming a promising approach for diagnosing various neurodegenerative diseases. However, the existing methods generally face problem overfitting. To solve it, this paper proposes convolutional neural network with three sparse strategies named SCNN to classify DFC. Firstly, an element-wise filter designed impose constraints on DFC matrix by replacing redundant elements zeroes, where specially constructed quantify spatial and temporal...

10.1109/jbhi.2021.3100559 article EN IEEE Journal of Biomedical and Health Informatics 2021-07-27

Automated guided vehicles are widely used in warehousing environments for automated pallet handling, which is one of the fundamental parts to construct intelligent logistics systems. Pallet detection a critical technology vehicles, directly affects production efficiency. A novel method based on point cloud data proposed, consists five modules including preprocessing, key extraction, feature description, surface matching and registration. The proposed combines color with geometric features...

10.3390/s22208019 article EN cc-by Sensors 2022-10-20

Cyclic AMP acting on protein kinase A controls sporulation and encystation in social solitary amoebas. In Dictyostelium discoideum, adenylate cyclase R (ACR), is essential for spore encapsulation. addition to its (AC) domain, ACR harbors seven transmembrane helices, a histidine two receiver domains. We investigated the role of these domains regulation AC activity. Expression an ACR-YFP fusion acr− cells rescued their defective phenotype revealed that associated with nuclear envelope...

10.1074/jbc.m110.156380 article EN cc-by Journal of Biological Chemistry 2010-10-22

Abstract The fine periodic growth patterns on shell surfaces have been widely used for studies in the ecology and evolution of scallops. Modern X‐ray CT scanners digital cameras can provide high‐resolution image data that contain abundant information such as formation rate, ontogenetic age, life span shellfish organisms. We introduced a novel multiscale processing method based matched filters with Gaussian kernels partial differential equation ( PDE ) hierarchical decomposition to segment...

10.1002/ece3.2789 article EN cc-by Ecology and Evolution 2017-02-09

The dynamic nature of the brain functional connectivity (FC) is well accepted in recent years. However, most current FC classification methods are based on static estimation FC. In this paper, we propose a novel convolutional neural network with an element-wise filter for classifying (DFC-CNN). First, DFC matrix estimated to quantify DFC. Then, taking as input, DFC-CNN model employs one-dimensional kernels extract high-level features Moreover, specially designed matrix, which further...

10.1109/bibm47256.2019.8983245 article EN 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2019-11-01

10.1007/s11191-021-00270-7 article EN Science & Education 2021-08-24

Abstract With the rapid development of information technology, countries are striving to make efforts in fields technology and artificial intelligence. The construction course system intelligence assisted computer basic teaching colleges is not only related personal future students, but also national industry. This paper first studies current situation course’s mode, then analyzes existing problems course, finally gives strategy new system.

10.1088/1742-6596/1533/3/032042 article EN Journal of Physics Conference Series 2020-04-01

Extraskeletal Ewing sarcoma (EES) is a member of the family tumors which pathologically known as small, round, blue cell tumor involving bone and soft tissue. The prevalence EES only 15%-25% all often occurs in patients aged from 20-mo-old to 30-years-old resulting an unfavorable prognosis.The present case report described 7-year-old patient with palpable mass 33 mm × 27 28 deep neck symptoms persistent dyspnea over past 5 mo. After laboratory examinations, abnormal physiological biochemical...

10.12998/wjcc.v10.i19.6595 article EN World Journal of Clinical Cases 2022-06-24

The complete chloroplast genome of Firmina danxiaensis, an important deciduous tree, was identified and sequenced in this study. size is 161,205 bp, the GC content 36.88%. A total 129 genes were identified, including 84 protein-coding genes, 8 rRNA 37 tRNA genes. 10 plastome accessions from Sterculiaceae selected to assess phylogenetic placement genus result showed that F. danxiaensis most closely related simplex.

10.1080/23802359.2020.1715294 article EN cc-by Mitochondrial DNA Part B 2020-01-02

The relationship between simultaneous limbs blood pressure differences and Ankle–Brachial Index (ABI) is controversial. This paper aims to investigate the association of pressures with ABI as current non-invasive diagnosis method in clinical primary care. A cross-sectional study was performed analysis them. results showed that [Formula: see text] independently associated inter-arm (OR, 15.469; CI, (1.776–134.773); text]) inter-ankle 7.189; (1.010–51.179); when systolic difference...

10.1142/s0219876218420161 article EN International Journal of Computational Methods 2018-10-15

Humans can easily learn new concepts from just a single exemplar, mainly due to their remarkable ability imagine or hallucinate what the unseen exemplar may look like in different settings. Incorporating such an diverse samples of tracked instance help trackers alleviate over-fitting problem low-data tracking regime. To achieve this, we propose effective adversarial approach, denoted as "hallucinator" (AH), for robust visual tracking. The proposed AH is designed firstly transferable...

10.48550/arxiv.1906.07008 preprint EN other-oa arXiv (Cornell University) 2019-01-01
Coming Soon ...