Borui Zhang

ORCID: 0000-0001-6010-9305
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Multimodal Machine Learning Applications
  • Advanced Image and Video Retrieval Techniques
  • Physical Activity and Health
  • Natural Language Processing Techniques
  • Anomaly Detection Techniques and Applications
  • Optical measurement and interference techniques
  • Advanced Neural Network Applications
  • Fault Detection and Control Systems
  • Human Pose and Action Recognition
  • Explainable Artificial Intelligence (XAI)
  • Adversarial Robustness in Machine Learning
  • Traffic Prediction and Management Techniques
  • Cardiovascular and exercise physiology
  • Machine Learning in Healthcare
  • Obesity, Physical Activity, Diet
  • RNA Research and Splicing
  • Artificial Intelligence in Healthcare and Education
  • RNA and protein synthesis mechanisms
  • Spectroscopy and Chemometric Analyses
  • Cosmology and Gravitation Theories
  • Black Holes and Theoretical Physics
  • Robotic Path Planning Algorithms
  • Face recognition and analysis
  • Domain Adaptation and Few-Shot Learning

Chang'an University
2025

UNSW Sydney
2024

Sun Yat-sen University
2024

Tsinghua University
2021-2024

Education University of Hong Kong
2022-2024

National Engineering Research Center for Information Technology in Agriculture
2021-2024

University of Florida
2023-2024

Yanshan University
2024

Jinan University
2024

Shandong Iron and Steel Group (China)
2024

In recent years, obtaining RNA secondary structure information has played an important role in and gene function research. Although some structures can be gained experimentally, most cases, efficient, accurate computational methods are still needed to predict structure. Current prediction mainly based on the minimum free energy algorithm, which finds optimal folding state of vivo using iterative method meet or other constraints. However, due complexity biotic environment, a true always keeps...

10.3389/fgene.2019.00467 article EN cc-by Frontiers in Genetics 2019-05-22

10.1109/cvpr52733.2024.01885 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024-06-16

Abstract Traumatic brain injury (TBI), recognized as the world's most serious public health problem, currently lacks effective treatment options. The development of patch has great clinical significance whether it is used a skull implant material or TBI repair. In response to this critical challenge, novel 3D‐printed bi‐layer cranial‐brain (SMB6) with dual functionality, addressing both repair and regeneration, developed. first layer, incorporation high concentrations mesoporous bioactive...

10.1002/adfm.202314330 article EN Advanced Functional Materials 2024-01-15

Clinical text provides essential information to estimate the acuity of a patient during hospital stays in addition structured clinical data. In this study, we explore how can complement predictive learning task. We leverage an internal medical natural language processing service perform named entity extraction and negation detection on notes compose selected entities into new corpus train document representations. then propose multimodal neural network jointly time series signals...

10.48550/arxiv.1811.12276 preprint EN other-oa arXiv (Cornell University) 2018-01-01

This paper presents a deep relational metric learning (DRML) framework for image clustering and retrieval. Most existing methods learn an embedding space with general objective of increasing interclass distances decreasing intraclass distances. However, the conventional losses usually suppress variations which might be helpful to identify samples unseen classes. To address this problem, we propose adaptively ensemble features that characterizes from different aspects model both...

10.1109/iccv48922.2021.01185 article EN 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021-10-01

Air pollution is a critical environmental issue with significant impacts on human health and ecosystems, exacerbated by urbanization industrialization, leading to increased emissions. Forecasting air quality accurately crucial for risk mitigation policy direction. Recent advancements in deep learning have enhanced prediction capabilities automatically extracting features managing complex data. This paper compares machine approaches forecasting, highlighting their strengths weaknesses....

10.1051/itmconf/20257302002 article EN cc-by ITM Web of Conferences 2025-01-01

Monocular depth estimation (MDE) is a critical computer vision task that enhances environmental perception in fields such as autonomous driving and robot navigation. In recent years, deep learning-based MDE methods have achieved notable progress these fields. However, achieving robust monocular low-altitude forest environments remains challenging, particularly scenes with dense cluttered foliage, which complicates applications monitoring, agriculture, search rescue operations. This paper...

10.3390/rs17040717 article EN cc-by Remote Sensing 2025-02-19

ChatGPT, a leading large language model, has achieved some success beyond previous models and caught the world's attention since its release in late 2022. Businesses healthcare professional fields have raised strong interests investing to assist various kinds of information searching their domain expertise. Under influence searched may be received new personalized chat format, contrast traditional search engines with pages results for users evaluate open. Large generative AI present...

10.1080/02763869.2023.2194149 article EN Medical Reference Services Quarterly 2023-04-03

In this paper, a novel facial expression recognition method using local binary pattern (LBP) and phase quantization (LPQ) based on Gabor face image is proposed. To capture the salient visual properties, filter firstly adopted to extract features of among five scales eight orientations. Then encoded by LBP operator LPQ operator, respectively. Two-stage principal component analysis linear discriminant (PCA-LDA) approach are used reduce dimension fused feature combined feature. experiment,...

10.1109/compcomm.2016.7924724 article EN 2016-10-01

Multipotent mesenchymal stromal cells from the bone marrow ameliorate acute kidney injury through a mechanism other than transdifferentiation into renal tissue. Stromal exert immunoregulatory effects on dendritic and T cells, both of which are important in pathophysiology immune-mediated injury. We hypothesized that similar with function exist within adult kidney. isolated murine kidney-derived morphologic features, growth properties, an immunophenotype characteristic cells. These lacked...

10.1681/asn.2008030310 article EN Journal of the American Society of Nephrology 2009-03-19

Abstract Pre-production quality defect inspection is a crucial step in industrial manufacturing, and many traditional strategies suffer from inefficiency issues. This especially true for tasks such as mechanical performance testing of steel products, which involve time-consuming processes like offline sampling, specimen preparation, testing. The volume significantly impacts the production cycle, inventory, yield, labor costs. Constructing data-driven model predicting product implementing...

10.1007/s44196-024-00451-6 article EN cc-by International Journal of Computational Intelligence Systems 2024-04-02

Optical remote sensing image salient object detection (ORSI-SOD) poses significant challenges due to complicated variances and interfering surroundings. Although existing methods have achieved impressive performance, they encounter difficulties in balancing deep shallow features, leading limitations preserving integrity edge detail. To address this, we propose the Integrated Detailed Ensemble Learning (IDEL) framework, which incorporates hierarchical branches with supervision. By...

10.1109/tgrs.2024.3400032 article EN IEEE Transactions on Geoscience and Remote Sensing 2024-01-01

This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and ex-plainable measure between images. Most existing methods exacerbate the unexplain-ability by mapping each sample to single point in em-bedding space with distance metric (e.g., Mahalanobis distance, Euclidean distance). Motivated human se-mantic cognition, we propose generalized simi-larity paradigm represent two images graph then infer overall accordingly. Furthermore, establish...

10.1109/cvpr52688.2022.00738 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022-06-01

Social media addiction (SMA) has become a more serious problem for people when they are engaging in their social life with parents, siblings, and friends. The goal of this review is to go over previous studies that focused on the potential factors cause SMA how these make vulnerable such addiction. also summarizes effective treatments SMA, comparing advantages disadvantages. Through review, neuroticism proved contribute high level well-being responsible negative correlation SMA. Several...

10.54097/ehss.v8i.4378 article EN cc-by-nc Journal of Education Humanities and Social Sciences 2023-02-07

Purpose: This study investigated the associations between physical activity (PA), sedentary behavior, and executive function in preadolescents. Methods: One hundred twenty preadolescents were recruited from 2 Hong Kong primary schools. PA behavior recorded for 7 consecutive days by accelerometer. Executive performance, including inhibition (Stroop task Flanker task) working memory (Sternberg paradigm task), measured. Body mass index cardiorespiratory fitness (multistage test) tested. Latent...

10.1123/pes.2022-0016 article EN Pediatric Exercise Science 2022-07-20

This study aimed to investigate the effects of caffeine on performances simulated match, Wingate Anaerobic Test (WAnT), and cognitive function test elite taekwondo athletes. Ten athletes in Hong Kong volunteered participate two main trials a randomized double-blinded crossover design. In each trial, 1 h after consuming drink with (CAF) or placebo without (PLA), participants completed match sessions followed by WAnT. The were instructed complete three tests, namely Eriksen Flanker (EFT),...

10.3390/nu14163398 article EN Nutrients 2022-08-18

Digital Shearography Speckle Pattern Interferometry (DSSPI) is a non-destructive testing technique, which has wide range of applications in industrial field due to the merits non-contact, fast response, full-field measurement and high sensitivity. However, real application, loading methods parameters usually depend on experience operator, affect effectiveness accuracy test. Based this background principle DSSPI, model using finite element analysis software Matlab established simulate defects...

10.1016/j.rinp.2017.09.015 article EN cc-by-nc-nd Results in Physics 2017-01-01

Few studies have reported the cardiovascular health effects of different high-intensity interval training (HIIT) protocols among sedentary young women. We investigated impact a traditional HIIT programme and circuit (HICT) on lipid profiles inflammatory cytokine levels in Forty-two women were randomly assigned to HICT (body weight-based training), (cycling-based or control groups (n = 14 each). participants completed an 8-week three sessions per week. Total cholesterol (TC), triglyceride,...

10.1080/02640414.2024.2363708 article EN Journal of Sports Sciences 2024-04-17

In this paper, we conduct a comprehensive study of the next-to-minimal composite Higgs model (NMCHM) extended with dilaton field <a:math xmlns:a="http://www.w3.org/1998/Math/MathML" display="inline"><a:mi>χ</a:mi></a:math> (denoted as <c:math xmlns:c="http://www.w3.org/1998/Math/MathML" display="inline"><c:msub><c:mrow><c:mi>NMCHM</c:mi></c:mrow><c:mi>χ</c:mi></c:msub></c:math>). A pseudo-Nambu-Goldstone boson (pNGB) <e:math xmlns:e="http://www.w3.org/1998/Math/MathML"...

10.1103/physrevd.110.015023 article EN cc-by Physical review. D/Physical review. D. 2024-07-22
Coming Soon ...