A5021644682- Intracranial Aneurysms: Treatment and Complications
- Traumatic Brain Injury and Neurovascular Disturbances
- Cerebrovascular and Carotid Artery Diseases
- ECG Monitoring and Analysis
- AI in cancer detection
- Topic Modeling
- Traffic Prediction and Management Techniques
- Energy, Environment, Economic Growth
- Environmental Impact and Sustainability
- Natural Language Processing Techniques
- IoT and Edge/Fog Computing
- Privacy-Preserving Technologies in Data
- Data Mining Algorithms and Applications
- Traditional Chinese Medicine Analysis
- Phonocardiography and Auscultation Techniques
- Traditional Chinese Medicine Studies
- Radiomics and Machine Learning in Medical Imaging
- Digital Marketing and Social Media
- Biomedical Text Mining and Ontologies
- EEG and Brain-Computer Interfaces
- Anomaly Detection Techniques and Applications
- Speech and Audio Processing
- Imbalanced Data Classification Techniques
- Blockchain Technology Applications and Security
- COVID-19 diagnosis using AI
Hunan Normal University
2012-2023
National University Health System
2020-2023
National University of Singapore
2020-2023
Jiangxi University of Science and Technology
2023
Northeast Agricultural University
2023
Hunan Provincial People's Hospital
2020-2021
China University of Mining and Technology
2020
Donghua University
2016-2019
Tsinghua University
2017-2018
Ministry of Finance
2014
In data-driven medical research, multi-center studies have long been preferred over single-center ones due to a single institute sometimes not having enough data obtain sufficient statistical power for certain hypothesis testings as well predictive and subgroup studies. The wide adoption of electronic health records (EHRs) has made multi-institutional collaboration much more feasible. However, concerns infrastructures, regulations, privacy, standardization present challenge sharing across...
Paraphrase generation (PG) is important in plenty of NLP applications. However, the research PG far from enough. In this paper, we propose a novel method for statistical paraphrase (SPG), which can (1) achieve various applications based on uniform model, and (2) naturally combine multiple resources to enhance performance. our experiments, use proposed generate paraphrases three different The results show that be easily transformed one application another valuable interesting paraphrases.
Learning information-rich and generalizable representations effectively from unlabeled multivariate cardiac signals to identify abnormal heart rhythms (cardiac arrhythmias) is valuable in real-world clinical settings but often challenging due its complex temporal dynamics. Cardiac arrhythmias can vary significantly patterns even for the same patient (i.e., intra subject difference). Meanwhile, type of arrhythmia show different among patients structures inter In this paper, we address...
Abstract Objective . Cardiovascular disease is a major threat to health and one of the primary causes death globally. The 12-lead ECG cheap commonly accessible tool identify cardiac abnormalities. Early accurate diagnosis will allow early treatment intervention prevent severe complications cardiovascular disease. Our objective develop an algorithm that automatically identifies 27 abnormalities from databases. Approach Firstly, series pre-processing methods were proposed applied on various...
The thyroid disease has already been the second largest in field of endocrine, and classification is primary problem clinical treatment. In computer-aided diagnosis (CAD), machine learning techniques have widely used to assist medical experts decision making. This paper proposed a new method for based on random forest. Principal Component Analysis preserve variability data. Rotation Transformation can enlarge discrepancy base classifiers improve accuracy ensemble classifier. Our performs...
In PhysioNet/Computing in Cardiology Challenge 2020, we developed an ensembled model based on SE-ResNet to classify cardiac abnormalities from 12-lead electrocardiogram (ECG) signals.We employed two residual neural network modules with squeeze-and-excitation blocks learn the first 10-second and 30-second segments of used external open-source data for validation fine-tuning during development phase.We designed a multi-label loss emphasize impact wrong predictions training.We built rule-based...
Abstract Background The purpose of this study was to analyze myopic regression after corneal refractive surgery (CRS) in civilian pilots and explore the factors that may cause long-term regression. Methods We included who had undergone CRS correct their myopia at least 5 years follow-up. collected retrospective data completed eye examinations a questionnaire assess habits. Results A total 236 eyes were evaluated study. 211 Intrastromal ablations (167 laser situ keratomileusis, LASIK, 44...
Ningxia Province is rich in energy but fragile ecology. How to coordinate sustainable utilization of natural capital and the ecological environment a significant guarantee for social-economic development. This study uses improved three-dimensional footprint characterize status flows stocks from 2004 2017. Additionally, driving factors behind changes stock are revealed by partial least squares method (PLS). The results as follows: (1) From 2017, increased rapidly at an annual rate 4.52%,...
Purpose: To evaluate the attitudes toward epilepsy among parents of children with (CWE) in China and identify some related factors for future interventions to offer more social support CWE. Method: The Chinese Public Attitudes Toward Epilepsy (CPATE) scale was administered 234 CWE 203 normal Xiangya hospital during 2019–2020. Results: cumulative score (26.427 ± 6.688) significantly lower than that group (32.330 7.234, p < 0.001). Subanalysis showed positive control ( 0.001) education...
Aneurysmal subarachnoid hemorrhage (aSAH) is a significant cause of morbidity and mortality throughout the world. Dynamic nomogram to predict prognosis elderly aSAH patients after endovascular coiling has not been reported. Thus, we aimed develop clinically useful dynamic risk 6-month unfavorable outcome in coiling. We conducted retrospective study including 209 admitted People's Hospital Hunan Province for from January 2016 June 2021. The main measure was (mRS ≥ 3). used multivariable...
Besides relevancy, diversity of recommendation results is also an important requirement for both users and content providers. In this paper, we propose a novel ranking model utilizing factorized category features items diversified top-N recommendation. To combine relevancy in unified function, define the score formula as product user item feature vectors, plus discounted which respectively correspond to contributions diversity. Moreover, obtain best lists, learn these vectors from...
A significant number of ionic rare earth tailings slopes were generated during the process mining and factor safety these continued to decrease under action rainfall. This study focussed on a specific slope located in Dayu County, Ganzhou City. Through utilization MatDEM numerical simulation software, variations infiltration distribution destabilization evolution between different seasons comparatively examined. The results indicated that rainy season (May June), increased rainfall led rate...
Nowadays, multiple heterogeneous cellular networks coexist simultaneously, and mobile devices can freely select the appropriate network for data communication. Our measurement studies show that a barrier exists between applications. Triggering handovers various break present promise of saving energy However, most existing handover triggering methods do not adequately incorporate characteristics applications may cause unnecessary handovers. In this paper, we propose an application-based...
Abstract Damage to lamellar keratinocytes, an essential cellular component of the epidermal layer hoof tissue, can have a detrimental effect on health and overall production value dairy cows. We isolated cultured cow keratinocytes using Dispase II collagenase methods. purified them by differential digestion velocity adherent methods at each passaging identified keratin 14 immunofluorescence. established in vitro model inflammation laminar LPS investigated whether chicoric acid protects...
This paper describes a method to combine near-infrared spectroscopy and three layer back-propagation artificial neural network in order identify official unofficial rhubarbs. Thirty-three samples were taken as the training set, 62 test set. The effects of input node number, learning rate momentum on final error recognition accuracy for prediction set determined. A with eight nodes, 0.5 rate, 0.3 can achieve 100% 96.8% described offers quick efficient means identifying