A5039897185- Respiratory viral infections research
- Imbalanced Data Classification Techniques
- Influenza Virus Research Studies
- Advanced biosensing and bioanalysis techniques
- Metaheuristic Optimization Algorithms Research
- Financial Distress and Bankruptcy Prediction
- Evolutionary Algorithms and Applications
- Advanced Computational Techniques and Applications
- Mosquito-borne diseases and control
- Software System Performance and Reliability
- Recommender Systems and Techniques
- Cervical Cancer and HPV Research
- Bone health and osteoporosis research
- Hepatitis B Virus Studies
- Luminescence and Fluorescent Materials
- Viral Infections and Immunology Research
- Vehicle License Plate Recognition
- Molecular Sensors and Ion Detection
- Non-Destructive Testing Techniques
- Viral gastroenteritis research and epidemiology
- Molecular Communication and Nanonetworks
- Liver Disease Diagnosis and Treatment
- Neonatal Respiratory Health Research
- Machine Learning and ELM
- Machine Learning and Data Classification
Sun Yat-sen University
2024
Bengbu University
2020-2024
Sun Yat-sen Memorial Hospital
2024
Bengbu Medical College
2010-2024
Anhui University of Science and Technology
2024
Shanghai First Maternity and Infant Hospital
2020-2023
First Affiliated Hospital of Jinan University
2020-2023
Zhejiang Chinese Medical University
2023
Zhejiang University
2023
Xinxiang Medical University
2023
Group recommendation research has recently received much attention in a recommender system community. Currently, several deep-learning-based methods are used group to learn preferences of groups on items and predict the next ones which may be interested. However, their effectiveness is disappointing. To address this challenge, article proposes novel model called multiattention-based (MAGRM). It well utilizes deep neural network structures achieve accurate recommendation. We train its two...
Since minority samples are substantially less common than majority samples, many industrial applications, such as credit card fraud detection (CCFD) and defective part identification, call for imbalanced classification. The performance of a classifier tends to suffer from the noisy in or classes. This work proposes new undersampling scheme, called clustering-based noisy-sample-removed scheme (NUS) class first clustered. distance sample cluster center that is furthest away used radius build...
A dandelion algorithm (DA) is a recently developed intelligent optimization for function problems. Many of its parameters need to be set by experience in DA, which might not appropriate all self-adapting and efficient proposed this work lower the number DA's simplify structure. Only normal sowing operator retained; while other operators are discarded. An adaptive seeding radius strategy designed core dandelion. The results show that achieves better performance on standard test functions with...
A dandelion algorithm (DA) is a recently-proposed intelligent optimization and shows an excellent performance in solving function problems. However, like other algorithms, it converges slowly falls into local optima easily. To overcome these two flaws, with probability-based mutation (DAPM) proposed this paper. In DAPM, both Gaussian Levy mutations can be used interchangeably according to given probability model. paper, three models are discussed, namely linear, binomial, exponential models....
Lupus nephritis is a rare immunological disorder. Genetic factors are considered important in its causation. We aim to systematically investigate the pathogenic gene variants patients with lupus nephritis.
Abstract Influenza‐like illness can be caused by a wide range of respiratory viruses. In order to investigate the epidemiology viral pathogens related influenza‐like in children Wuhan, largest city central China, throat swab samples were collected from 1,472 young patients, July 2008 June 2010, before and after occurrence 2009 pandemic influenza A (H1N1) virus (pH1N1). It was found that 923 patients (62.7%) positive for at least 1 90 (9.8%) detected multiple (≥2) viruses real‐time PCR...
Credit card fraud detection (CCFD) is an important issue concerned by financial institutions. Existing methods generally employ aggregated or raw features as their representations to train models. Yet such tend fall short of effectively exposing the characteristics various frauds. In this work, we propose a spatial-temporal gated network (STGN) automatically learn new informative transactional containing users' behavioral information for CCFD. A recurrent neural net unit specifically...
Human metapneumovirus (HMPV) is a worldwide distributed pathogen of the respiratory tract. The objectives this study were to identify HMPV infections among children with influenza‐like illness (ILI) in Wuhan and assess circulation patterns molecular diversity area. From July 2008 December 2013, total 3,883 throat swab samples collected from ILI outpatients under 16 years old. RNA was detected 171 (4.40%). All four subtypes identified, which A2 most common subtype (61/145, 42.1%), followed by...
Healthcare systems, empowered by the integration of Artificial Intelligence (AI) and Internet Things networks, are undergoing significant advancements, ushering in a new era enhanced treatment experiences improved quality life. Edge computing plays pivotal role as an architectural enabler; however, it also presents numerous energy-related challenges spanning sensors, communication, edge devices. One most formidable is proliferation complex communication protocols across various devices,...
Fluorine-18 labeled N,N-diethyl-2-(2-(4-(2-fluoroethoxy)phenyl)-5,7-dimethylpyrazolo[1,5-a]pyrimidin-3-yl)acetamide ([
The mayfly algorithm (MA), as a newly proposed intelligent optimization algorithm, is found that easy to fall into the local optimum and slow convergence speed. To address this, an improved based on dynamic elite strategy (DESMA) in this paper. Specifically, it first determines specific space near best current population, dynamically sets search radius. Then generating certain number of mayflies within range. Finally, one among generated selected replace population when fitness value better...
Abstract #4155 Background: At present, our understanding of the development bone metastasis is limited. Therefore, little progress has been made in preventing skeletal breast cancer patient. A satisfactory animal model that avoids species-specific factor and simultaneously shares similarities to clinical pathophysiological progression metastasizing unavailable. subpopulation (CD44+/CD24-/lower) cells possesses stem/progenitor cell properties (cancer stem-like cell). CD44 potentiates...
In this paper, two methods to suppress the higher-order modes in substrate integrated waveguide (SIW) cavity are proposed. One is use double coupling irises instead of single iris between cavities, which prevents TE <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">301</sub> mode from being excited effectively. The other etch narrow slots on metallic plate destroys xmlns:xlink="http://www.w3.org/1999/xlink">102</sub> mode. theories suppression...
Workflow system has become a standard solution for managing complex business process. How to guarantee its correctness is key requirement. Many methods only focus on the control-flow verification, while they neglect modeling and checking of data-flows. Although some studies are presented repair data-flow errors, do not consider effect delete operations or weak circulation relations repairing results. What's more, errors may bring in new errors. In order solve these problems, we use workflow...
Classification technology plays an important role in machine learning. In the process of classification, presence noisy samples datasets tends to reduce performance a classifier. This work proposes clustering-based Noisy-sample-Removed Under-sampling Scheme (NUS) for imbalanced classification. First, minority class are clustered. For each cluster, its center is taken as spherical center, and distance farthest from cluster radius form hypersphere. The Euclidean every majority calculated...
Stress urinary incontinence (SUI) remains a prevalent complication after Holmium Laser Enucleation of the Prostate (HoLEP). This retrospective analysis aims to delineate perioperative and anatomical determinants SUI as observed on preoperative multiparametric magnetic resonance imaging (mpMRI) in patients subjected HoLEP.