A5100445279- Context-Aware Activity Recognition Systems
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Topic Modeling
- Electronic Health Records Systems
- Natural Language Processing Techniques
- Machine Learning in Bioinformatics
- Domain Adaptation and Few-Shot Learning
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- EEG and Brain-Computer Interfaces
- Multimodal Machine Learning Applications
- Non-Invasive Vital Sign Monitoring
- Anomaly Detection Techniques and Applications
- Biometric Identification and Security
- Genomics and Phylogenetic Studies
- ECG Monitoring and Analysis
- Occupational Health and Safety Research
- Dietetics, Nutrition, and Education
- Speech and dialogue systems
- Robotics and Automated Systems
- Disaster Response and Management
- IoT and Edge/Fog Computing
- Liver Disease Diagnosis and Treatment
- Blood Pressure and Hypertension Studies
Zhejiang Lab
2019-2025
Chinese University of Hong Kong
2025
Shenzhen University
2025
Chinese University of Hong Kong, Shenzhen
2025
University of Georgia
2021-2025
Suzhou Municipal Hospital
2024
Nanjing Medical University
2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2021-2024
University of Science and Technology of China
2024
University of California, San Diego
2024
Context-sensitive applications need data from sensors, devices, and user actions, might ad hoc communication support to dynamically discover new devices engage in spontaneous information exchange. Reconfigurable Context-Sensitive Middleware facilitates the development runtime operations of context-sensitive pervasive computing software.
Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken NLP. These LMs reach new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) four auto-encoder (BERT, Albert, Electra, T5) on UniRef BFD containing up to 393 billion amino acids. The were the Summit supercomputer using 5616 GPUs TPU Pod up-to 1024 cores. Dimensionality reduction revealed that raw...
Long-term electrocardiogram (ECG) has become one of the important diagnostic assist methods in clinical cardiovascular domain. ECG is primarily used for detection various diseases that are caused by cardiac arrhythmia such as myocardial infarction, cardiomyopathy, and myocarditis. In past few years, development an automatic heartbeat classification method been a challenge. With accumulation medical data, personalized patient possible. For long-term data method, holter, it difficult to obtain...
Abstract Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models taken NLP. These LMs reach new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) four auto-encoder (BERT, Albert, Electra, T5) on UniRef BFD containing up to 393 billion amino acids. The were the Summit supercomputer using 5616 GPUs TPU Pod up-to 1024 cores. Dimensionality reduction revealed that raw...
At present, the global tunnel construction industry is developing rapidly, but accidents are also common. A large number of casualties and property losses alarming people. It urgent to pay attention causes accidents, ensure safety sites, reduce accidents. Through literature case analysis, we have sorted out 35 typical causative factors for research which divided into 7 types. Based on variable system, prepared a measurement questionnaire, 536 valid questionnaires were collected. The...
In recent years, an increasing number of people have become concerned about their health. Most chronic diseases are related to lifestyle, and daily activity records can be used as important indicator Specifically, using advanced technology automatically monitor actual activities effectively prevent manage diseases. The data in this paper were obtained from acceleration sensors gyroscopes integrated smartphones. We designed efficient Adaboost-Stump running on a smartphone classify five common...
Osteosarcoma (OS) is the most prevalent primary malignant bone tumor. However, single-agent chemotherapy exhibits limited efficacy against OS and often encounters tumor resistance. Therefore, we designed constructed an integrated treatment strategy of photothermal therapy (PTT) combined with used a surface-encapsulated platelet-osteosarcoma hybrid membrane (OPM) that enhances circulation time enables OS-specific targeting.The OPM functions as shell structure, encapsulating multiple...
Ubiquitous computing represents the concept of everywhere, making and communication essentially transparent to users. Applications in this type environments are context sensitive. They use various contexts adaptively communicate with each other across multiple network environments, such as mobile ad hoc networks, Internet, phone networks. The property context-sensitivity often becomes inadequate these applications, where combinations users' actions need be analyzed over a period time....
This paper proposes a novel method based on Haar wavelet transform and uniform local binary patterns (ULBPs) to recognize ear images. Firstly, images are decomposed by transform. Then ULBPs combined simultaneously with block-based multi-resolution methods describe together the texture features of sub-images transformed wavelet. Finally, classified nearest neighbor method. Experimental results show that can boost effectively up intensity information unit. It is not only fast but also robust...
The use of a shared decision-making (SDM) process in antihyperglycemic medication strategy decisions is necessary due to the complexity conditions diabetes patients. Knowledge guidelines used as decision aids clinical situations, and during this process, no patient health are considered. In paper, we propose an SDM system framework for type-2 mellitus (T2DM) patients that not only contains knowledge abstracted from but also employs multilabel classification model uses class-imbalanced...
<p>Diabetic kidney disease (DKD), a severe diabetic complication affecting approximately one-third of patients, is the leading cause end-stage chronic disease. The benefits regular exercise for patients with DKD have been well documented, particularly in overweight DKD. However, underlying mechanisms are incompletely understood. present study demonstrates that improves function <i>db/db</i> mice through activating PPARδ-mediated fatty acid β-oxidation (FAO). Twelve-week...
Exercise elicits cardiometabolic benefits, reducing the risks of cardiovascular diseases and type 2 diabetes. This study aimed to investigate vascular metabolic effects gut microbiota from exercise-trained donors on sedentary mice with diabetes potential mechanism. Leptin receptor-deficient diabetic (db/db) nondiabetic (db/m+) underwent running treadmill exercise for 8 wk, during which fecal transplantation (FMT) was parallelly performed mice. Endothelial function, glucose homeostasis,...