A5037026116- Non-Invasive Vital Sign Monitoring
- Heart Rate Variability and Autonomic Control
- Diabetic Foot Ulcer Assessment and Management
- ECG Monitoring and Analysis
- Muscle activation and electromyography studies
- Spectroscopy and Chemometric Analyses
- Cardiovascular Health and Disease Prevention
- Advanced Chemical Sensor Technologies
- Fire Detection and Safety Systems
- Retinal Imaging and Analysis
- Advanced Image Fusion Techniques
- Glaucoma and retinal disorders
- Optical Imaging and Spectroscopy Techniques
- Industrial Vision Systems and Defect Detection
- Image Enhancement Techniques
- Human Pose and Action Recognition
- EEG and Brain-Computer Interfaces
- Video Surveillance and Tracking Methods
- Infrared Thermography in Medicine
- Fire effects on ecosystems
- Remote-Sensing Image Classification
- Gait Recognition and Analysis
- Islanding Detection in Power Systems
- Electrowetting and Microfluidic Technologies
- Electrocatalysts for Energy Conversion
North Minzu University
2016-2024
Guangxi Medical University
2021
First People's Hospital of Nanning
2021
Florida International University
2020
Minzu University of China
2018
Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection myocardial using computer-aided analysis electrocardiograms (ECG) provides an important reference for diagnosis CVD. The vectorcardiogram (VCG) could improve the performance ECG-based by affording temporal-spatial characteristics related to and capturing subtle changes in ST-T segment continuous cardiac cycles. We aim investigate if combination ECG VCG machine learning algorithms automatic detection.
A gait feature analysis method based on AlphaPose human pose estimation fused with sample entropy is proposed to address complicated, high‐cost, and time‐consuming postoperative rehabilitation of patients joint diseases. First, TensorRT was used optimize the inference AlphaPose, which consists target detection algorithm YOLOv3 algorithm. It can speed up latency throughput by about 2.5 times while maintaining algorithm’s accuracy. Second, optimized posture AlphaPose_trt process videos healthy...
Early fire detection is quite important to fighting of forest fire. A lightweight YOLO model proposed in this study. First, the YOLOv4 object selected as overall framework for detection. In order reduce number parameters and computation, study replaced YOLOv4's backbone network with MobileNetV3. Finally, data set flame smoke used training model, fire-like images are negative samples improve robustness model. The experimental results demonstrate that compared YOLOv4, architecture reduced by...
An intelligent wine detection and traceability method based on infrared spec-troscopy machine learning is proposed, in order to meet the needs of online rapid nondestructive testing wine. On basis extracting spectrum wine, principal component analysis (PCA) – support vector (SVM) model was modified by chemometrics. A total 300 grape samples were collected from six production areas. The composition analyzed ultra performance liquid chromatography-quadrupole time-of-flight mass spectrometry...
The present study aimed at testing the hypothesis that application of multiscale cross-approximate entropy (MCAE) analysis in nonlinear coupling behavior two synchronized time series different natures [i.e., R-R interval (RRI) and crest (CT, from foot to peakof a pulse wave)] could yield information on complexity related diabetes-associated vascular changes. Signals single waveform parameter (i.e., CT) photoplethysmography RRI electrocardiogram were simultaneously acquired within period one...
Diabetic peripheral neuropathy (DPN) is one of the most common chronic complications diabetes. It has become an essential public health crisis, especially for care in home. Synchronized electrocardiogram (ECG) and photoplethysmography (PPG) signals were obtained from healthy non-diabetic (n = 37) diabetic 85) subjects without neuropathy, recruited outpatient clinic. The conventional parameters, including low-/high-frequency power ratio (LHR), small-scale multiscale entropy index (MEISS),...
To investigate the value of decomposed short-time digital volume pulse (DVP) signals in discerning systemic vascular anomaly diabetic patients, demographic and anthropometric parameters, serum lipid profile, fasting blood glucose glycated hemoglobin (HbA1c) levels were obtained from 29 healthy adults (Group 1) age-matched type 2 diabetes mellitus patients 2). Six-second DVP right index finger acquired through photoplethysmography using ensemble empirical mode decomposition. Using one...
This study investigated the validity of a novel parameter, percussion entropy index (PEI), for assessing baroreflex sensitivity. PEI was acquired through comparing similarity in tendency change between amplitudes successive digital volume pulse (DVP) signals and changes R‐R intervals (RRI) cardiac cycles. Totally 108 upper middle‐aged volunteers were divided into three groups: healthy subjects (Group 1, age 41–80, n=41), those with well‐controlled type 2 diabetes mellitus (T2DM) 2, 41–82,...
Introduction: Walking speed can affect gait stability and increase the risk of falling. Methods: In this study, we design a device to measure distribution plantar pressure investigate impact walking on human movements body. We fused entropy acquired at multiple scales with signals evaluate effects gait. simultaneously collected data motion-induced from eight regions obtain regional pressure. To verify their accuracy, obtained during by using force table Qualisys system. then extracted peak...
To tackle the difficulty of extracting features from one-dimensional spectral signals using traditional analysis, a metabolomics analysis method is proposed to locate two-dimensional correlated feature bands and combine it with deep learning classification for wine origin traceability. Metabolomics was performed on 180 samples 6 different regions UPLC-Q-TOF-MS. Indole, Sulfacetamide, caffeine were selected as main differential components. By analyzing molecular structure these components...
This study investigated the application of a modified percussion entropy index (PEIPPI) in assessing complexity baroreflex sensitivity (BRS) for diabetic peripheral neuropathy prognosis. The was acquired by comparing obedience fluctuation tendency change between amplitudes continuous digital volume pulse (DVP) and variations peak-to-peak interval (PPI) from decomposed intrinsic mode function (i.e., IMF6) through ensemble empirical decomposition (EEMD). In total, 100 middle-aged subjects were...
This study was designed to evaluate the clinical applications of body mass index (BMI) and a percussion-entropy-based (PEINEW) for predicting development diabetic peripheral neuropathy (DPN) in group type 2 diabetes mellitus (DM) patients. The population comprised sample 90 subjects with diabetics (aged 37–86 years), who went through blood test photoplethysmography (PPG) measurement were then followed 5.5 years. Conventional parameters, including small-scale multiscale entropy (MEISS), pulse...
To address issues of detail loss, limited matching datasets, and low fusion accuracy in infrared/visible light fire image fusion, a novel method based on the Generative Adversarial Network Wavelet-Guided Pooling Vision Transformer (VTW-GAN) is proposed. The algorithm employs generator discriminator network architecture, integrating efficient global representation capability Transformers with wavelet-guided pooling for extracting finer-grained features reconstructing higher-quality images....
<abstract> <sec><title>Purpose</title><p>Coronary microvascular dysfunction (CMD) is emerging as an important cause of myocardial ischemia, but there a lack non-invasive method for reliable early detection CMD.</p> </sec> <sec><title>Aim</title><p>To develop electrocardiogram (ECG)-based machine learning algorithm CMD that will lay the groundwork patient-specific...
Diabetic peripheral neuropathy (DPN) is a very common neurological disorder in diabetic patients. This study presents new percussion-based index for predicting DPN by decomposing digital volume pulse (DVP) signals from the fingertip. In this study, 130 subjects (50 individuals 44 to 89 years of age without diabetes and 80 patients 37 86 with type 2 diabetes) were enrolled. After baseline measurement blood tests, 25 developed within following five years. removing high-frequency noise original...
Abstract Background The goal was to characterize retinal vasculature by quantitative analysis of arteriole-to-venule (A/V) ratio and vessel density in fundus photos taken with the PanOptic iExaminer System. Methods ophthalmoscope equipped a smartphone used acquire centered on optic nerve head. Two total 19 eyes from 10 subjects were imaged. Retinal vessels analyzed obtain A/V ratio. In addition, tree extracted using deep learning U-NET, processed percentage pixels within over entire image....
The rapid increase in machine learning prediction algorithms has generated a strong demand for applications that can successfully predict type 2 diabetes and/or peripheral neuropathy elderly subjects with metabolic disorders; however, the number of samples is key issue determining accurate prediction. To address this challenge, streaming data instantaneous frequency maximal energy (fEmax) were calculated from toe photoplethysmography signals, followed by procedures to quality model. Three...
One of the important factors air pollution is straw burning. It a good method to use unmanned aerial vehicle(UAV) image monitor But UAV quality will be deteriorated by suspended particles produced incineration. In order solve this problem, new enhancement algorithm proposed. Based on traditional single dehazing method, large gray area detected through histogram. Then, obtain modified coefficients calculated and dark channel prior corrected it. Finally Adaptive contrast used improve image....
Noise can be used by the stochastic resonance system to enhance ability of weak signal detection. Based on classic (SR) it get good results but also bring problem that it's hard find optimal parameters at same time. Single-well potential (SSR) was in this paper detect signals. SSR has only one parameter adjusted. It is easier adjust best state. This takes cross correlation coefficient as measurement index basis single-well resonance, detects multi-frequency periodic from test after with...
As panels located in the wilderness and affected by dust sandstorm, photovoltaic efficiency was reduced 30%-40% after a period of time even worse. Based on Internet things self-cleaning solar power system household micro-grid designed this paper. It included micro-grids control systems; presented. Nano-diamond powder, ethyl cellulose, solvent were mixed. They accorded to mass ratio 1:3:24. The slurry got with long ultrasonic heating dispersed, which adopted prepare film window glass cell...