A5101991198- Spectroscopy and Chemometric Analyses
- Diabetes Management and Research
- Surgical Simulation and Training
- Anatomy and Medical Technology
- Artificial Intelligence in Healthcare
- Time Series Analysis and Forecasting
- Anomaly Detection Techniques and Applications
- Soft Robotics and Applications
- Domain Adaptation and Few-Shot Learning
- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging and Pathology Studies
- Lung Cancer Diagnosis and Treatment
- Dysphagia Assessment and Management
- Energy Load and Power Forecasting
- Voice and Speech Disorders
- Spectroscopy Techniques in Biomedical and Chemical Research
- Medical Research and Treatments
- Smart Agriculture and AI
- Statistical Methods and Inference
- Fault Detection and Control Systems
- Sparse and Compressive Sensing Techniques
- Network Security and Intrusion Detection
- Dental Radiography and Imaging
- Identification and Quantification in Food
Fujian University of Traditional Chinese Medicine
2025
Northeastern University
2021-2024
State Key Laboratory of Synthetical Automation for Process Industries
2024
Shanghai Jiao Tong University
2023-2024
Jiangsu Province Hospital
2021
Institute for Infocomm Research
2010-2020
Agency for Science, Technology and Research
2010-2020
Ministry of Public Security of the People's Republic of China
2020
Institute of Art
2020
Xi'an Jiaotong University
2020
To assist in the rapid clinical identification of brain tumor types while achieving segmentation detection, this study investigates feasibility applying deep learning YOLOv5s algorithm model to magnetic resonance images and optimizes upgrades it on basis. The research institute utilized two public datasets meningioma glioma imaging from Kaggle. Dataset 1 contains a total 3,223 images, 2 216 images. From 1, we randomly selected 3,000 used Labelimg tool annotate cancerous regions within These...
Tea is one of the most consumed beverages worldwide. The healthy effects tea are attributed to a wealthy different chemical components from tea. Thousands studies on constituents had been reported. However, data these individual reports have not collected into single database. lack curated database related information limits research in this field, and thus cohesive system should necessarily be constructed for deposit further application.The Metabolome (TMDB), manually web-accessible...
Background: The coronavirus disease 2019 (COVID-19) breaking out in late December is gradually being controlled China, but it still spreading other countries and regions worldwide. It urgent to conduct prediction research on the development spread of epidemic.Methods: A hybrid AI model proposed for COVID-19 prediction. First, by analyzing change infectious capacity virus carriers within a few days after infection, an improved SI (ISI) proposed. Second, considering effects prevention control...
The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety applications, such as emergency communications, regional surveillance, and disaster relief. Due to their limited battery capacity processing power, multiple UAVs are often required for complex tasks. In cases, control center is crucial coordinating activities, which fits well with the federated learning (FL) framework. However, conventional FL approaches focus on single task, ignoring potential...
Abstract Blood glucose (BG) prediction is an effective approach to avoid hyper- and hypoglycemia, achieve intelligent management for patients with type 1 or serious 2 diabetes. Recent studies have tended adopt deep learning networks obtain improved models more accurate results, which often required significant quantities of historical continuous glucose-monitoring (CGM) data. However, new limited dataset, it becomes difficult establish acceptable network prediction. Consequently, the goal...
Huanghua pear is an important fruit in China. The shape and condition of the stems are indices forclassifying pears. Images pears were acquired with a machine vision system. Using templates withdifferent sizes, algorithm for judging presence was developed. Meanwhile, stem head joint pointbetween body labeled. After calculating slopes approximate tangential lines atthe bottom positions, included angle these two obtained. It found that ofa broken smaller than good stem. Based on this feature,...
Pediatric teeth exhibit significant changes in type and spatial distribution across different age groups. This variation makes pediatric segmentation from cone-beam computed tomography (CBCT) more challenging than that adult teeth. Existing methods mainly focus on segmentation, which however cannot be adapted to of with individual (SDPTIC) children, resulting limited accuracy for segmenting Therefore, we introduce a novel topology structure-guided graph convolutional network (TSG-GCN)...
Splenomegaly (spleen enlargement) is one indication that processed poultry not acceptable for humanconsumption because of diseases such as tumors or septicemia. This study explored the possibility detectingsplenomegaly with a computer imaging system will assist human inspectors in food safety inspections. Images ofinternal viscera from 45-day-old commercial turkeys were taken fluorescent and UV lighting systems. Imageprocessing algorithms using linear transformation, morphological filtering,...
In vitro macro- and micro-indentation test systems have been designed to measure the dynamic micro-mechanical properties of human prostate tissues at actuation frequencies between 5 Hz 30 Hz, 0.5 20 respectively. The development
The limited-angle cone-beam Computed Tomography (CT) is often used in C-arm for clinical diagnosis with the advantages of cheap cost and radiation dose reduction. However, due to incomplete projection data, 3-dimensional CT images reconstructed by conventional methods, such as Feldkamp, Davis Kres (FDK) algorithm [1], suffer from heavy artifacts missing features. In this paper, we propose a novel pipeline neural networks jointly FDK-based network revisited Würfl et al.'s work [2] an image...
Modeling forces applied to cut biological material with laparoscopic scissors is important for haptic rendering in surgical simulation. The cutting process characterized deformation and fracture. An analytical model human iliac artery derived concepts of shearing fracture mechanics this study. experimental set-up was built verify the force model. Three pieces were scissors. Force required arterial wall corresponding angular displacement scissors' handle collected evaluate parameters able fit...
Mechanical and computational models consisting of flow channels with convergent oscillating constrictions have been applied to study the dynamics human vocal fold vibration. To best our knowledge, no mechanical model has studied using a material substitute similar physical properties for surgical experimentation. In this study, we design develop larynx agarose as substitute, assess its suitability Agarose is selected it exhibits nonlinear hyperelastic characteristics biological soft tissue....
Surgical traineeship has traditionally been based on a master apprentice model where learning takes place in the operating theatre. This approach changed over past few years with greater emphasis surgical training taking within skills laboratory. We developed high fidelity simulator, Image-guided Robotic Assisted simulator (IRAS) an incorporated robotic guidance feature. The robot system is to mimic process of experienced surgeon physically holding trainee's hands demonstrate manoeuvring...
Early alarm of hypoglycemia, detection asymptomatic and effective control blood glucose fluctuation make a great contribution to diabetic treatment. In this study, we designed multi-level hypoglycemia early system mine potential information in Continuous Glucose Monitoring (CGM) time series improve the overall performance for different clinical situations.Through symbolizing historical CGM records, Prefix Span was adopted obtain alarm/non-alarm frequent sequence libraries events. The longest...