A5087810041- Geriatric Care and Nursing Homes
- Dementia and Cognitive Impairment Research
- Reliability and Maintenance Optimization
- Statistical Distribution Estimation and Applications
- Healthcare Operations and Scheduling Optimization
- Non-Invasive Vital Sign Monitoring
- Healthcare Policy and Management
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Global Health Care Issues
- Chronic Disease Management Strategies
- Frailty in Older Adults
- Diabetes Management and Research
- Bayesian Methods and Mixture Models
- ECG Monitoring and Analysis
- Heart Rate Variability and Autonomic Control
- Augmented Reality Applications
- Recommender Systems and Techniques
- Machine Fault Diagnosis Techniques
- Heart Failure Treatment and Management
- Art, Technology, and Culture
- Color Science and Applications
- Advanced Statistical Process Monitoring
- Explainable Artificial Intelligence (XAI)
- Cardiovascular Function and Risk Factors
Communication University of Zhejiang
2021-2024
University of South Florida
2017-2021
Chinese Academy of Sciences
2012
Many vital physiological features are embedded in photoplethysmography (PPG). Among them, heart beat carries the most significant importance for monitoring both clinical and mobile health-care settings. However, motion artifact induced by finger arm movement can corrupt PPG signal significantly cause serious false recognition of features, leading to erroneous medical decision. In this paper, we propose a processing method based on multi-scale data analysis using Empirical Mode Decomposition...
Photoplethysmograph (PPG) signal measured from wearable devices for tele-home healthcare is often corrupted by motion artifacts which cause false extraction of physiological features and lead to erroneous medical decision monitoring. In this paper we propose an innovative method combines the morphological characteristics with temporal variability information in series assess quality reject meaningless segments that are significantly contaminated aiming at improving accuracy derived vital...
Abstract Successful modeling of degradation data is great importance for both accurate reliability assessment and effective maintenance decision‐making. Many existing performance approaches either assume a homogeneous population units or characterize heterogeneous with some restrictive assumptions, such as pre‐specifying the number sub‐populations. This paper proposes Bayesian framework to relax conventional assumptions. Specifically, non‐parametric model formulation learning algorithm are...
In the field of reliability engineering, covariate information shared among product units within a specific group (e.g., manufacturing batch, an operating region), such as conditions and design settings, exerts substantial influence on lifetime prediction. The covariates each may be missing due to sensing limitations data privacy issues. same commonly encompass variety attribute types, discrete continuous or mixed types. Existing studies have mainly considered single-type at individual...
Cardiovascular diseases (CVD) constitute a group of chronic ailments that can have sudden onset, emphasizing the crucial need for their prediction and early prevention. The current clinical diagnosis CVD often requires comprehensive examinations, including laboratory imaging tests, symptom checks, physical examinations. These procedures be time-consuming, labor-intensive, expensive patients. Additionally, utilization accessible tabular test results, which are typically high-dimensional...
As the majority of service recipients U.S. long-term care system, elderly with disabilities experience heterogeneous functional limitation and performance degradation. Successful modeling degradation becomes great importance for decision making. Existing heterogeneity approaches are mainly restricted to single-level older adults. This article proposes a novel bi-level quantification framework systematically investigate at both sub-population individual levels. Specifically, Bayesian...
Electrical impedance tomography (EIT) is an promising imaging technology for continuous bedside monitoring of ventilation and perfusion. However, due to the spatial frequency overlapping cardiac components in heart-lung interaction system, it's difficult separate spontaneous breathing subjects. We introduce intuitive method based on multi-dimensional ensemble empirical mode decomposition explore intrinsic oscillation modes from EIT data. This study combines information with temporal...
The medical texts contain rich information about the health status of patients, including personal demographic details, examination items, diagnostic narratives, and corresponding outcomes. There is often an underlying dependency between a patient multiple texts. Such has substantial influence on accuracy reliability patient's comprehensive outcomes, thus necessitating modeling dependency. Most existing studies text classification focused only textual content overlooked inherent texts,...
The advancement in the field of AIGC has significantly enhanced level automation interactive animation design and potential to disrupt entire industry model. In context this transformative landscape, study introduces latest explorations integration into teaching model courses. Throughout process creating cases, which encompasses conceiving original works, designing producing them, setting student development goals assessment methods, several changes innovations were implemented based on...