Xiaoyang Xu

ORCID: 0000-0003-1772-8631
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Heavy metals in environment
  • Meteorological Phenomena and Simulations
  • Adversarial Robustness in Machine Learning
  • Face and Expression Recognition
  • Privacy-Preserving Technologies in Data
  • Computer Graphics and Visualization Techniques
  • Precipitation Measurement and Analysis
  • Traffic Prediction and Management Techniques
  • Urban and Freight Transport Logistics
  • Imbalanced Data Classification Techniques
  • Face recognition and analysis
  • Microbial Community Ecology and Physiology
  • Advanced Neural Network Applications
  • Domain Adaptation and Few-Shot Learning
  • Flood Risk Assessment and Management
  • Plant Stress Responses and Tolerance
  • Data Management and Algorithms
  • Medical Image Segmentation Techniques
  • Advanced Optical Sensing Technologies
  • Advanced MRI Techniques and Applications
  • Research Data Management Practices
  • Advanced Clustering Algorithms Research
  • Metaheuristic Optimization Algorithms Research
  • Human Mobility and Location-Based Analysis
  • Chemical and Environmental Engineering Research

Changzhou University
2023-2024

Wuhan University
2024

Anhui Normal University
2023-2024

Shanghai Public Security Bureau
2024

Tianjin University
2023

Shandong Jianzhu University
2023

Xidian University
2023

Tianjin Normal University
2022

Fudan University
2019-2021

Chengdu University of Information Technology
2021

The perennial ryegrass Lolium perenne can be used in conjunction with cadmium (Cd)-tolerant bacteria such as Cdq4–2 (Enterococcus spp.) for bioremediation of Cd-contaminated soil. In this study, a theoretical basis was provided to increase the efficiency L. remediation soil using microorganisms maintain stability microbiome. experimental design involved three treatment groups: CK (soil without Cd addition) control, 20 mg·kg–1 soil, and + Cdq4–2, all planted perenne. collected on day 60...

10.1016/j.ecoenv.2024.115957 article EN cc-by-nc-nd Ecotoxicology and Environmental Safety 2024-01-21

Image ordinal estimation is to predict the label of a given image, which can be categorized as an regression problem. Recent methods formulate problem series binary classification problems. Such cannot ensure that global relationship preserved since relationships among different classifiers are neglected. We propose novel approach, termed Convolutional Ordinal Regression Forest or CORF, for image estimation, integrate and differentiable decision trees with convolutional neural network...

10.1109/tnnls.2021.3055816 article EN IEEE Transactions on Neural Networks and Learning Systems 2021-02-20

10.1109/cvpr52733.2024.01153 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024-06-16

Abstract Lightning matters to human life and natural fires so much that monitoring predicting lightning are highly important. A simple proxy for climatic cloud‐to‐ground (CG) density is evaluated defined as the product of convective available potential energy (CAPE) precipitation rate using data from 2005 2017 in Sichuan Southwest China. CAPE times (CP) relates monthly distribution magnitude negative basin region more closely, while CP describes positive plateau appropriately. Except...

10.1002/joc.7451 article EN International Journal of Climatology 2021-11-13

In machine learning and data analysis, dimensionality reduction high-dimensional visualization can be accomplished by manifold using a t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm. We significantly improve this scheme introducing preprocessing strategy for the t-SNE our preprocessing, we exploit Laplacian eigenmaps to reduce first, which aggregate each cluster Kullback–Leibler divergence (KLD) remarkably. Moreover, k-nearest-neighbor (KNN) algorithm is also involved in...

10.3390/e25071065 article EN cc-by Entropy 2023-07-14

Cadmium (Cd) pollution has been rapidly increasing due to the global rise in industries. Cd not only harms ecological environment but also endangers human health through food chain and drinking water. Therefore, remediation of Cd-polluted soil is an imminent issue. In this work, ryegrass a strain Cd-tolerant bacterium were used investigate impact inoculated bacteria on physiology biochemistry enrichment contaminated with different concentrations (4 20 mg/kg). The results showed that...

10.3390/plants13121657 article EN cc-by Plants 2024-06-15

The fraudulent website image is a vital information carrier for telecom fraud. efficient and precise recognition of images critical to combating dealing with websites. Current research on websites mainly carried out at the level feature extraction similarity study, which have such disadvantages as difficulty in obtaining data, insufficient analysis, single identification types. This study develops model based entropy method leader decision Inception-v3 transfer learning address these...

10.23919/jcc.fa.2023-0450.202401 article EN China Communications 2024-01-01

The diagnosis of bearing faults is an important guarantee for the healthy operation mechanical equipment. Due to time-varying working conditions equipment, it necessary achieve fault under conditions. However, superposition two-dimensional speed and acceleration brings great difficulties via data-driven models. long short-term memory (LSTM) model based on infinitesimal method effective solve this problem, but its performance still has certain limitations. On basis, article proposes a...

10.3390/s23156730 article EN cc-by Sensors 2023-07-27

Recorded provenance facilitates reproducible science. Provenance metadata can help determine how data were possibly transformed, processed, and derived from original sources. While is crucial for verification validation, there remains the issue of granularity - detail at which must be provided to a user, especially conducting When are reproduced successfully need detailed minimal an essence recorded suffices. However, when not correctly users want quickly drill down into fine-grained...

10.1109/escience.2016.7870920 article EN 2016-10-01

With broad applications in various public services like aviation management and urban disaster warning, numerical precipitation prediction plays a crucial role weather forecast. However, constrained by the limitation of observation conventional meteorological models, predictions are often highly biased. To correct this bias, classical correction methods heavily depend on profound experts who have knowledge aerodynamics, thermodynamics meteorology. As can be influenced countless factors,...

10.48550/arxiv.1910.07633 preprint EN other-oa arXiv (Cornell University) 2019-01-01

In order to reduce the energy consumption of cellular network and build a green communication network, it is very necessary accurately predict changes in traffic load base station. this paper, we propose novel station forecasting model, named LSTCN, which combining Long Short-Term Memory Network (LSTM) Time Convolutional (TCN). We conducted experiments on real data experimental results show that model proposed paper has higher prediction accuracy than previous methods.

10.1109/iccis53528.2021.9645961 article EN 2021-10-15

Numerical precipitation prediction plays a crucial role in weather forecasting and has broad applications public services including aviation management urban disaster early-warning systems. However, numerical (NWP) models are often constrained by systematic bias due to coarse spatial resolution, lack of parameterizations, limitations observation conventional meteorological models, sample size long-tail distribution. To address these issues, we present data-driven deep learning model, named...

10.1109/mis.2021.3088543 article EN IEEE Intelligent Systems 2021-06-11

Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements. Previous research consistently highlights the potential privacy breaches in SL systems by server adversaries reconstructing training data. However, these studies often rely on strong assumptions or compromise system utility to enhance attack performance. This paper introduces new semi-honest Data Reconstruction Attack SL, named Feature-Oriented (FORA)....

10.48550/arxiv.2405.04115 preprint EN arXiv (Cornell University) 2024-05-07

Numerical Weather Prediction (NWP) can reduce human suffering by predicting disastrous precipitation in time. A commonly-used NWP the world is European Centre for medium-range weather forecasts (EC). However, it necessary to correct EC forecast through Bias Correcting on Precipitation (BCoP) since we still have not fully understood mechanism of precipitation, making often some biases. The existing BCoPs suffers from limited prior data and fixed Spatio-Temporal (ST) scale. We thus propose an...

10.48550/arxiv.2004.05793 preprint EN other-oa arXiv (Cornell University) 2020-01-01
Coming Soon ...