Wenyuan Li

ORCID: 0000-0002-3489-2647
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Entrepreneurship Studies and Influences
  • Advanced Clustering Algorithms Research
  • AI in cancer detection
  • Generative Adversarial Networks and Image Synthesis
  • Data Mining Algorithms and Applications
  • Innovation and Socioeconomic Development
  • Anomaly Detection Techniques and Applications
  • Power System Reliability and Maintenance
  • Face and Expression Recognition
  • Advanced Graph Neural Networks
  • Family Business Performance and Succession
  • Radiomics and Machine Learning in Medical Imaging
  • Domain Adaptation and Few-Shot Learning
  • Complex Network Analysis Techniques
  • Digital Marketing and Social Media
  • Energy Load and Power Forecasting
  • Technology Adoption and User Behaviour
  • Web and Library Services
  • Cryptography and Data Security
  • Medical Imaging and Analysis
  • Neural Networks and Applications
  • Advanced Malware Detection Techniques
  • Risk and Safety Analysis
  • Gene expression and cancer classification
  • Remote-Sensing Image Classification

Shenzhen University
2023-2025

Chongqing University
2004-2024

Jiangsu University
2017-2024

Second Affiliated Hospital of Zhejiang University
2024

Chinese Academy of Sciences
2021-2023

Institute of Information Engineering
2021-2023

Guilin University of Technology
2023

University of California, Los Angeles
2018-2022

Computational Diagnostics (United States)
2020-2022

South China Normal University
2022

Abstract Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation multinational settings. Competitions be accelerators medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this mind, we organized the PANDA challenge—the largest histopathology competition date, joined 1,290 developers—to catalyze development...

10.1038/s41591-021-01620-2 article EN cc-by Nature Medicine 2022-01-01

This paper aims to investigate the relationship between antecedents of trust in online shopping and purchase intention. Specifically, it examines perceived service quality, website reputation, as well mediating role moderating risk An survey was used collect data (356 valid responses) SmartPLS structural equation modelling (PLS-SEM) employed hypothesize a model. Data were collected from September December 2019. Results suggest over The slope for intention is moderated by risk, showing that...

10.1080/23311975.2020.1869363 article EN cc-by Cogent Business & Management 2021-01-01

Small and medium enterprises (SMEs) have become a vibrant dynamic sector of the world economy. Information technology plays vital role in improving productivity competitiveness SMEs. The business environment has brought fierce competition among SMEs and, therefore, requires owners to interact with internal external members actively. Hence, this study aims investigate impact technology, organization, as important factors performance small medium-sized enterprises. It also examines mediating...

10.3390/su13010075 article EN Sustainability 2020-12-23

Prostate cancer is the most common and second deadly form of in men United States. The classification prostate cancers based on Gleason grading using histological images important risk assessment treatment planning for patients. Here, we demonstrate a new region-based convolutional neural network framework multi-task prediction an epithelial head head. Compared with single-task model, our model can provide complementary contextual information, which contributes to better performance. Our...

10.1109/tmi.2018.2875868 article EN publisher-specific-oa IEEE Transactions on Medical Imaging 2018-10-12

Load curve data refers to the electric energy consumption recorded by meters at certain time intervals delivery points or end user points, and contains vital information for day-to-day operations, system analysis, visualization, reliability performance, saving adequacy in planning. Unfortunately, it is unavoidable that load curves contain corrupted missing due various random failure factors transfer processes. This paper presents <i xmlns:mml="http://www.w3.org/1998/Math/MathML"...

10.1109/tsg.2010.2053052 article EN IEEE Transactions on Smart Grid 2010-07-29

Existing deep learning-based remote sensing images semantic segmentation methods require large-scale labeled datasets. However, the annotation of datasets is often too time-consuming and expensive. To ease burden data annotation, self-supervised representation learning have emerged recently. need to learn both high-level low-level features, but most existing usually focus on one level, which affects performance for images. In order solve this problem, we propose a multitask method capture...

10.1109/jstars.2021.3090418 article EN cc-by IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021-01-01

Social entrepreneurship orientation (SEO) is a behavioral construct of social (SE); therefore, we examined the influence SEO organization on and financial performance. A random sample 810 employees was drawn from enterprises Pakistan during COVID-19 pandemic. Although increasing research focuses SE, discipline continues to disintegrate, this has led appeals for careful investigation associations firms' SE. In recent decade, "social entrepreneurship" earned its importance as segment...

10.3389/fpsyg.2021.755080 article EN cc-by Frontiers in Psychology 2022-02-14

Purpose This study focuses on how entrepreneurial bricolage (EB) drives both competitive advantage (CA) and sustainability performance (SP). Design/methodology/approach Relying structural equation modeling, data were collected from 200 small medium-sized enterprise (SME) manufacturers in Ghana. Findings The results indicate that EB CA SP positively. SL positively moderated the relationship between CA, while moderating role of was not supported. Originality/value concludes can enhance SP, a...

10.1108/lodj-06-2023-0330 article EN Leadership & Organization Development Journal 2024-01-30

This paper proposes a chronological probability model of photovoltaic (PV) generation on the basis conditional and nonparametric kernel density estimation. In addition to randomness PV power, correlation powers between adjacent time points uncertainty start end moments output can be represented. The proposed employed produce random power series curve using stochastic sampling method. data three generators in different regions with distinct weather conditions 34-node distribution network are...

10.1109/tpwrs.2013.2293173 article EN IEEE Transactions on Power Systems 2014-01-31

Electronic commerce is becoming a significant hub for sourcing products/services which helps organizations to connect with potential customers and gain competitive advantages, though little empirical work focuses on small businesses operating in developing countries date. Increasingly, companies are looking utilize social media stakeholders pursue several benefits. This study aims investigate the technological, organizational, environmental (TOE) factors that influence small- medium-sized...

10.13106/jafeb.2020.vol7.no10.989 article EN Journal of Asian Finance Economics and Business 2020-10-15

Abstract Based on the value co-creation theory, this study proposed a theoretical model of effects growth social enterprises. Primary data was obtained using field surveys through close-ended questionnaire from January to June 2019. The respondents were employees enterprises working in Punjab province Pakistan. Partial least squares structural equation modeling used for quantitative analysis and verify statistical significance direct link between enterprise growth, negative moderating...

10.1515/erj-2019-0359 article EN Entrepreneurship Research Journal 2020-08-24

Deep neural networks, in particular convolutional have rapidly become a popular choice for analyzing histopathology images. However, training these models relies heavily on large number of samples manually annotated by experts, which is cumbersome and expensive. In addition, it difficult to obtain perfect set labels due the variability between expert annotations. This paper presents novel active learning (AL) framework image analysis, named PathAL. To reduce required annotations, PathAL...

10.1109/tmi.2021.3135002 article EN IEEE Transactions on Medical Imaging 2021-12-13

Abstract Background Chronic obstructive pulmonary disease (COPD) is a frequently diagnosed yet treatable condition, provided it identified early and managed effectively. This study aims to develop an advanced COPD diagnostic model by integrating deep learning radiomics features. Methods We utilized dataset comprising CT images from 2,983 participants, of which 2,317 participants also epidemiological data through questionnaires. Deep features were extracted using Variational Autoencoder,...

10.1186/s12931-024-02793-3 article EN cc-by Respiratory Research 2024-04-18

Sustainability is a strategic priority for businesses. This study examines how green vertical leadership influences project performance, with proactive and reactive innovation as mediators. Green leadership, marked by centralized decision-making oversight, enhances compliance-driven sustainability structured innovation. Results show that fosters both innovation, improving environmental efficiency outcomes. drives long-term sustainability, while ensures regulatory adherence. Both types link...

10.47191/ijcsrr/v8-i4-10 article EN International Journal of Current Science Research and Review 2025-04-10

Histology review is often used as the `gold standard' for disease diagnosis. Computer aided diagnosis tools can potentially help improve current pathology workflows by reducing examination time and interobserver variability. Previous work in cancer grading has focused mainly on classifying pre-defined regions of interest (ROIs), or relied large amounts fine-grained labels. In this paper, we propose a two-stage attention-based multiple instance learning model slide-level weakly-supervised ROI...

10.48550/arxiv.1905.13208 preprint EN other-oa arXiv (Cornell University) 2019-01-01

The detection and removal of cloud in remote sensing images are essential for earth observation applications. Most previous methods consider as a pixel-wise semantic segmentation process (cloud v.s. background), which inevitably leads to category-ambiguity problem when dealing with semi-transparent clouds. We re-examine the under totally different point view, i.e. formulate it mixed energy separation between foreground background images, can be equivalently implemented an image matting...

10.1109/iccv.2019.00029 article EN 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2019-10-01

Despite the recent progress in deep learning and remote sensing image interpretation, adaption of a model between different sources data still remains challenge. This paper investigates an interesting question: do synthetic generalize well for applications? To answer this question, we take building segmentation as example by training on city map well-known video game “Grand Theft Auto V” then adapting to real-world images. We propose generative adversarial based framework improve...

10.3390/rs12020275 article EN cc-by Remote Sensing 2020-01-14

Load curve data records the electric energy consumptions at time intervals and plays an important role in operation planning of power systems. Unfortunately, load curves always contain abnormal, noisy, unrepresentative, missing due to various random factors. It is crucial identify repair such data. Previous works focused on detecting Y-outliers that are unusual (Y-axis) a small temporal neighborhood. This paper presents different class X-outliers have abnormal according known periodicity...

10.1109/tpwrs.2011.2167022 article EN IEEE Transactions on Power Systems 2011-10-17
Coming Soon ...