A5103160307- Advanced Image Processing Techniques
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Advanced Numerical Analysis Techniques
- Image and Signal Denoising Methods
- Assisted Reproductive Technology and Twin Pregnancy
- Health, Environment, Cognitive Aging
- Hydrocarbon exploration and reservoir analysis
- Reproductive Health and Technologies
- Image and Video Quality Assessment
- Image Enhancement Techniques
- Birth, Development, and Health
- Statistical Methods and Bayesian Inference
- Coal Properties and Utilization
- Demographic Trends and Gender Preferences
- Statistical Methods and Inference
- Statistical and numerical algorithms
- Nutritional Studies and Diet
- Advanced Statistical Methods and Models
- demographic modeling and climate adaptation
- Geoscience and Mining Technology
- Optimal Power Flow Distribution
- Optimal Experimental Design Methods
- Electric Vehicles and Infrastructure
- Metabolomics and Mass Spectrometry Studies
Fudan University
2025
Zhongshan Hospital
2025
Sanda University
2024
Shenzhen Institutes of Advanced Technology
2022-2024
Chinese Academy of Sciences
2024
City University of Macau
2024
University of Macau
2024
Simon Fraser University
2021-2023
Henan University
2021-2023
Shaanxi University of Science and Technology
2023
We develop scalable methods for fitting penalized regression spline based generalized additive models with of the order 104 coefficients to up 108 data. Computational feasibility rests on: (i) a new iteration scheme estimation model and smoothing parameters, avoiding poorly scaling matrix operations; (ii) parallelization iteration's pivoted block Cholesky basic (iii) marginal discretization covariates reduce memory footprint, efficient computing required crossproducts directly from discrete...
Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply edge devices. To alleviate this problem, many novel and effective solutions been proposed. Convolutional neural network (CNN) with attention mechanism has attracted increasing due its efficiency effectiveness. However, there still redundancy convolution operation. In paper, we propose Blueprint Separable Residual Network (BSRN) containing two...
This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus proposed solutions and results. The task of was to super-resolve an input a magnification factor ×4 based pairs low corresponding high resolution images. aim design network for that achieved improvement efficiency measured according several metrics including runtime, parameters, FLOPs, activations, memory consumption while at least maintaining PSNR 29.00dB DIV2K validation set. IMDN is set as...
The reformed Common Agricultural Policy of 2023-2027 aims to promote a more sustainable and fair agricultural system in the European Union. Among proposed measures, incentivized adoption cover crops soil during winter provides numerous benefits such as improved structure reduced nutrient leaching erosion. Despite this recognized importance, availability spatial data on is scarce. increasing field parcel declarations Union has not yet filled gap due its insufficient information content,...
Wood et al. (J Am Stat Assoc 112(519):1199–1210, 2017) developed methods for fitting penalized regression spline based generalized additive models, with of the order $$10^4$$ coefficients, to up $$10^8$$ data. The offered two three orders magnitude reduction in computational cost relative most efficient previous methods. Part gain resulted from development a set efficiently computing model matrix products when covariates each take only discrete values substantially smaller than sample size...
Abstract Background Longitudinal data analysis can improve our understanding of the influences on health trajectories across life-course. There are a variety statistical models which be used, and their fitting interpretation complex, particularly where there is nonlinear trajectory. Our aim was to provide an accessible guide along with applied examples using four sophisticated modelling procedures for describing growth trajectories. Methods This expository paper provides illustrative...
To explore the effects of donor sperm on reproductive quality life, sleep and erectile function in patients with severe oligoasthenospermia after failure intracytoplasmic injection (ICSI), to provide targeted reference for intervention. From January 2021 December 2023, who received assisted pregnancy treatment Obstetrics Gynecology Hospital Affiliated Tongji University were selected as study objects. Among them, 82 cases using ICSI set observation group, propensity score 1:1 matching control...
Deep neural networks have significantly improved the performance of low-level vision tasks but also increased difficulty interpretability. A deep understanding models is beneficial for both network design and practical reliability. To take up this challenge, we introduce causality theory to interpret propose a model-/task-agnostic method called Causal Effect Map (CEM). With CEM, can visualize quantify input-output relationships on either positive or negative effects. After analyzing various...
With the fluctuation and intermittence of distributed generation (DG) electric vehicle (EV), it is important to ensure safe stable operation distribution system. This paper presents a multi-objective approach network reconfiguration considering vehicle-to-grid (V2G) vehicles in system with renewable energy access. Firstly, function includes loss index, voltage deviation index stability margin index. The weight each determined by analytic hierarchy process (AHP). Secondly, charging...
There are millimeter, micron and nanometer scales of pores fractures in coal to describe different fissures communicating path quantitatively characterize their permeability. Such information provides an important basis for studying coalbed methane output mechanism. The a large number samples were observed counted by scanning electron microscopy optical microscopy. probability distribution models pore-fissure network then established. Different pore-fissures 2D reconstructed Monte Carlo...
In a context of growing interest in breeding more resilient animals, non-invasive indicator resilience would be very valuable. We hypothesized that the time-course concentrations several milk metabolites through short-term underfeeding challenge could reflect variation mechanisms to such challenge. submitted 138 one-year-old primiparous goats, selected for extreme functional longevity, i.e., productive longevity corrected yield (60 low line goats (Low_LGV), and 78 high (High_LGV)), 2-d...
Abstract In the process of ensemble empirical mode decomposition (EEMD) for motor rolling bearing time series, if classifier is trained directly using eigenvalues extracted from pattern components, there are two shortcomings leading to reduction fault identification accuracy as follows: has serious endpoint effects; correlation between features lead confusion feature vector classification boundary. Aiming at problems, in this paper, a diagnosis model was built. Firstly, LSTM used extend...
We proposed a new penalized B-splines estimator, the general P-spline, to accommodate non-uniform on unevenly spaced knots. It is complement Eilers and Marx's standard P-spline tailored for uniform equidistant At its core, we derived novel difference penalty that accounts irregular knot spacing, while still being easy compute interpret. Both variants are useful practical smoothing, because either one can produce more satisfactory fit than other, depending sequence used data analyzed....
Abstract Objective: To study the influencing factors of assisted pregnancy outcome in infertile men receiving reproduction. Design: From January 2023 to June 2023, a total 1037 who planned undergo IVF/ICSI-ET Department Assisted Reproductive Medicine First Maternal and Infant Health Hospital Affiliated Tongji University were selected as research objects. Logistic regression classification decision tree model used men. Receiver operating characteristic (ROC) curves evaluate effects two...
Abstract Objective This study investigated the risk factors of assisted pregnancy outcomes in infertile men receiving reproductive treatment and established a prediction model. Methods A cross-sectional survey was conducted on 1037 who underwent ICSI-ET at Reproductive Medicine Center Obstetrics Gynecology Hospital Affiliated to Tongji University from March 2023 September 2023, clinical information 403 gestation cycles (study group) 634 non-gestation (control were compared. Logistic...
With the rapid advancement of Vision Language Models (VLMs), VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically align with human expression and capture multifaceted nature IQA tasks. However, current methods are still far from practical usage. First, prior works focus narrowly on specific sub-tasks or settings, which do not diverse real-world applications. Second, their performance is sub-optimal due limitations in dataset coverage, scale, quality. To...
The demand for efficient 3D model generation techniques has grown exponentially, as manual creation of models is time-consuming and requires specialized expertise. While generative have shown potential in creating textured shapes from 2D images, their applicability industries limited due to the lack a well-defined camera distribution real-world scenarios, resulting low-quality shapes. To overcome this limitation, we propose GET3D--, first method that directly generates images with unknown...