A5100767320- Anomaly Detection Techniques and Applications
- Artificial Intelligence in Healthcare
- Industrial Vision Systems and Defect Detection
- EEG and Brain-Computer Interfaces
- COVID-19 diagnosis using AI
- Neural dynamics and brain function
- Time Series Analysis and Forecasting
- Tissue Engineering and Regenerative Medicine
- Reproductive Health and Technologies
- Imbalanced Data Classification Techniques
- Membrane Separation Technologies
- Ultrasound in Clinical Applications
- Digital Media Forensic Detection
- Acute Ischemic Stroke Management
- Neuroscience and Neural Engineering
- Cardiac, Anesthesia and Surgical Outcomes
- Machine Learning and Data Classification
- VLSI and Analog Circuit Testing
- Healthcare and Venom Research
- Color perception and design
- Pancreatic function and diabetes
- Spectroscopy Techniques in Biomedical and Chemical Research
- Functional Brain Connectivity Studies
- Integrated Circuits and Semiconductor Failure Analysis
- Music and Audio Processing
Boston Children's Hospital
2024
Korea University
2019-2024
Brighton and Sussex Medical School
2024
Rice University
2017
Florida State University
2009
Background: This study aimed to examine trends in the prevalence, incidence, metabolic characteristics, and management of type 2 diabetes mellitus (T2DM) among young adults South Korea.Methods: Young with T2DM were defined as individuals aged 19 39 years who met diagnostic criteria for T2DM. Data from Korean National Health Insurance Service-Customized Database (2010–2020, <i>n</i>=225,497–372,726) analyzed evaluate profiles, comorbidities, antidiabetic drug prescription....
Background and Purpose Moderate-intensity statin plus ezetimibe versus high-intensity alone may provide a greater low-density lipoprotein cholesterol (LDL-C) reduction in patients with recent ischemic stroke.Methods This randomized, open-label, controlled trial assigned stroke <90 days to rosuvastatin/ezetimibe 10/10 mg once daily (ROS10/EZT10) or rosuvastatin 20 (ROS20). The primary endpoint was LDL-C ≥50% from baseline at 90 days. Key secondary endpoints were <70 mg/dL multiple lipid...
Class imbalance problems have been reported as a major issue in various applications. Classification becomes further complicated when an occurs time series data sets. To address data, it is necessary to consider their characteristics (i.e., high dimensionality, correlations, and multimodality). Oversampling well-known approach for addressing this problem; however, such does not appropriately the of data. This paper addresses these limitations by presenting model-based oversampling approach,...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Abstract Introduction and aims Molecular regulation of mammalian skin development has been largely derived from murine studies. The lack human studies stems primarily the difficulties in prenatal access. There is an important need to study owing notable differences between mouse paucity mechanistic understanding congenital disorders. Methods We assembled first comprehensive multiomic reference atlas (21 samples 7 16 postconception weeks), combining single-cell (235 201 cells) spatial...
To investigate the neuronal response of conductivity during visual stimulation and compare that with BOLD, 30 young healthy volunteers were recruited from local community. We performed two independent experiments functional magnetic resonance electrical properties tomography (MREPT) MRI. found value was increased to some brain areas, indicating MREPT MRI can be used measure activity; therefore, conductivity-based fMRI signals may helpful for measuring activation stimulation.
While previous studies have demonstrated the feasibility of using ear-electroencephalography (ear-EEG) for development brain-computer interfaces (BCIs), most them been performed exogenous paradigms in offline environments. To verify reliable constructing ear-EEG-based BCIs, ear-EEG should be further another BCI paradigm, namely endogenous real-time online Exogenous and BCIs are to use EEG evoked by external stimuli induced self-modulation, respectively. In this study, we investigated whether...
This paper proposes to use machine learning (ML) methods predict wafer quality using Fab inline measured items, DC measurements, and DVS (Dynamic Voltage Stress) at sort. With developed ML approach, the predicted accuracy is more than 80% in 8 nm products used this study. We believe method can be further fine-tuned help enable ICs high level expected for automotive systems. By assigning predictive rankings, also helps best tooling system higher quality.
Abstract Identifying bacterial species is essential to epidemiological surveillance. However, the determination of a tedious and labor‐intensive process. Various machine learning methods have been used for identifying with mass spectral fingerprints. Although achieve real‐time identification without human experts, it still requires data preprocessing. To address this issue, we proposed unified solution convolutional neural network. The network automatically determined according their spectra...
Objectives: Yukmijihwang-won (Liuweidihuang-wan in Chinese) is a frequently used medicinal herbal formula. It as Yin tonic Korea and China to recover patients from deficiency. However, the scientific evidence on this drug has not revealed beneficial effect or mechanism of its effects neurological disorder. We designed study examine antidepressive analgesic (YJ-01) minor modification YJ-01, YJ-06 reserpine-induced pain-depression dyad mice model. Methods: Reserpine (1 mg/kg) was administered...
Background: The epidemiology of stroke and acute myocardial infarction (AMI) in Korea is limited by inaccurate methods for estimating incidence. Therefore, this study aimed to build the system national statistics AMI using claims-based identification algorithms. Methods: We identified algorithms based on 2018 National Health Insurance Service (NHIS) data. were validated investigation medical records sampled cases including patient groups control a 2-stage stratified sampling method. divided...
Background: Static parameters such as central venous pressure and pulmonary artery occlusion pressure, have limitation in evaluation of patientsâ volume status. Dynamic stroke variation (SVV), been used to evaluate intraoperative hemodynamic status, various operations. We examined if SVV is also effective for patients undergoing operation with prone position fluid management. Methods: Eighteen that received spinal surgery under November 2015 May 2016, were enrolled. Patients kept at an...