A5031711509- ECG Monitoring and Analysis
- Non-Invasive Vital Sign Monitoring
- Heart Rate Variability and Autonomic Control
- Healthcare Technology and Patient Monitoring
- Hemodynamic Monitoring and Therapy
- Cardiac electrophysiology and arrhythmias
- Digital Mental Health Interventions
- EEG and Brain-Computer Interfaces
- Mobile Health and mHealth Applications
- Atrial Fibrillation Management and Outcomes
- Time Series Analysis and Forecasting
- Health, Environment, Cognitive Aging
- Thermoregulation and physiological responses
- Acute Myocardial Infarction Research
- Cardiovascular Health and Risk Factors
- Intravenous Infusion Technology and Safety
- Postharvest Quality and Shelf Life Management
- Photosynthetic Processes and Mechanisms
- Copper-based nanomaterials and applications
- Meat and Animal Product Quality
- Machine Learning in Healthcare
- AI in cancer detection
- Light effects on plants
- COVID-19 diagnosis using AI
- Identification and Quantification in Food
Georgia Institute of Technology
2022-2025
Emory University
2022-2025
Moscow Institute of Thermal Technology
2024
The Wallace H. Coulter Department of Biomedical Engineering
2024
Huazhong Agricultural University
2023
Collaborative Innovation Center of Advanced Microstructures
2023
Nanjing University
2023
Duke University
2021
Hong Kong Baptist University
2018-2021
University of California, San Francisco
2019
Photoplethysmography (PPG) is a ubiquitous physiological measurement that detects beat-to-beat pulsatile blood volume changes and hence has potential for monitoring cardiovascular conditions, particularly in ambulatory settings. A PPG dataset created particular use case often imbalanced, due to low prevalence of the pathological condition it targets predict paroxysmal nature as well. To tackle this problem, we propose log-spectral matching GAN (LSM-GAN), generative model can be used data...
Photoplethysmography (PPG) monitoring has been implemented in many portable and wearable devices we use daily for health fitness tracking. Its simplicity cost-effectiveness enabled a variety of biomedical applications, such as continuous long-term heart arrhythmias, fitness, sleep tracking, hydration monitoring. One major issue that can hinder PPG-based applications is movement artifacts, which lead to false interpretations. In implementations, noisy PPG signals are discarded. Misinterpreted...
Stress is becoming an increasingly prevalent health issue, seriously affecting people and putting their lives at risk. Frustration, nervousness, anxiety are the symptoms of stress these common (40%) in younger people. It creates a negative impact on human damages performance each individual. Early prediction level can help to reduce its different serious issues related this mental state. For this, automated systems required so they accurately predict levels. This study proposed approach that...
Abstract Objective . Prompt identification and recognization of myocardial ischemia/infarction (MI) is the most important goal in management acute coronary syndrome. The 12-lead electrocardiogram (ECG) widely used as initial screening tool for patients with chest pain but its diagnostic accuracy remains limited. There early evidence that machine learning (ML) algorithms applied to ECG waveforms can improve performance. Most studies are designed classify MI from healthy controls thus limited...
Objective. Wearable devices equipped with plethysmography (PPG) sensors provided a low-cost, long-term solution to early diagnosis and continuous screening of heart conditions. However PPG signals collected from such often suffer corruption caused by artifacts. The objective this study is develop an effective supervised algorithm locate the regions artifacts within signals.Approach. We treat artifact detection as 1D segmentation problem. solve it via novel combination active-contour-based...
Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and becoming more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state art results on heart rate estimation, atrial fibrillation detection, motion artifact identification. Consequently, need interpretable has arisen within field signal In this paper, we pioneer novel explanatory metrics which leverage domain-expert...
Smartwatches and other wearable devices are equipped with photoplethysmography (PPG) sensors for monitoring heart rate aspects of cardiovascular health. However, PPG signals collected from such susceptible to corruption noise motion artifacts, resulting in inaccuracies during estimation. Conventional denoising methods filter or reconstruct ways that eliminate morphological information, even the clean segments signal should ideally be preserved. In this work, we develop an algorithm...
Bacterial identification is of great importance in clinical diagnosis, environmental monitoring, and food safety control. Among various strategies, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has drawn significant interest been clinically used. Nevertheless, current bioinformatics solutions use spectral libraries for the bacterial strains. Spectral library generation requires acquisition MALDI-TOF spectra from monoculture colonies, which...
Photoperiods integrate with the circadian clock to coordinate gene expression rhythms and thus ensure plant fitness environment. Genome-wide characterization comparison of rhythmic genes under different light conditions revealed delayed phase constant darkness (DD) reduced amplitude (LL) in rice. Interestingly, ChIP-seq RNA-seq profiling exhibit synchronous oscillation H3K9ac modifications at their loci long non-coding RNAs (lncRNAs) proximal loci. To investigate how rhythm is regulated...
Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices photoplethysmography (PPG) sensors deep neural networks has demonstrated some success proprietary algorithms in commercial solutions. However, to improve continuous detection ambulatory settings towards population-wide screening use case, we face several challenges, one of which the lack large-scale labeled training data. To address...
Label noise is omnipresent in the annotations process and has an impact on supervised learning algorithms. This work focuses of label performance models by examining effect random class-dependent a binary classification task: quality assessment for photoplethysmography (PPG). PPG signal used to detect physiological changes its can have significant subsequent tasks, which makes particularly good target field biomedicine. Random was introduced separately into training set emulate errors...
Despite advancements in digital health, it remains challenging to obtain precise time synchronization of multimodal physiological signals collected through different devices. Existing algorithms mainly rely on specific features that restrict the use cases certain signal types. The present study aims complement previous and solve a niche alignment problem when common type is available across devices.We proposed simple approach based direct cross-correlation temporal amplitudes, making...
. Physiological data are often low quality and thereby compromises the effectiveness of related health monitoring. The primary goal this study is to develop a robust foundation model that can effectively handle low-quality issue in physiological data.
Background: Rapid, reliable, and accurate interpretation of medical signals is crucial for high-stakes clinical decision-making. The advent deep learning allowed an explosion new models that offered unprecedented performance in time series processing but at a cost: are often compute-intensive lack interpretability. Methods: We propose Sparse Mixture Learned Kernels (SMoLK), interpretable architecture processing. method learns set lightweight flexible kernels to construct single-layer neural...
In this research, a nonlinear model describing the relationship between inoculation fermentation parameters and quality of yin rice were investigated based on artificial neural network genetic algorithm (ANN-GA) model. The ANN-GA had excellent potential for predicting viscosity property rice, optimized by using algorithm. Through model, were: 0.05 % lactic acid bacteria, Saccharomyces cerevisiae, 0.2 Rhizopus oryzae, then fermenting 48 h at 25 °C. results further validated experiments....
Bedside patient monitors are ubiquitous tools in modern critical care units to provide timely status. However, current systems suffer from high volume of false alarms leading alarm fatigue, one top technical hazards clinical settings. Many studies racing develop improved algorithms towards precision monitoring, while little has been done investigate the aspect algorithm generalizability across different health institutions. Our group developing an evolving framework termed SuperAlarm that...