A5107678784- ECG Monitoring and Analysis
- Non-Invasive Vital Sign Monitoring
- Medical Image Segmentation Techniques
- Heart Rate Variability and Autonomic Control
- EEG and Brain-Computer Interfaces
- Phonocardiography and Auscultation Techniques
- Image and Signal Denoising Methods
- Blood Pressure and Hypertension Studies
- Cardiovascular Health and Disease Prevention
- Spectroscopy and Chemometric Analyses
- Blind Source Separation Techniques
- Higher Education and Teaching Methods
- Photoacoustic and Ultrasonic Imaging
- Remote Sensing and Land Use
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Advanced Image Processing Techniques
- Cardiac Imaging and Diagnostics
- Image Enhancement Techniques
- Advanced Image Fusion Techniques
- Cardiac electrophysiology and arrhythmias
- Image Retrieval and Classification Techniques
- Advanced Measurement and Detection Methods
- GABA and Rice Research
- Robotics and Sensor-Based Localization
Nanjing University of Aeronautics and Astronautics
2023-2024
Shandong University
2010-2023
Chinese People's Liberation Army
2017
China Academy of Engineering Physics
2011
Changzhou Institute of Technology
2010
China University of Geosciences
2010
Linyi University
2007-2008
National Taiwan University
2005-2006
Electrocardiogram (ECG) and phonocardiogram (PCG) signals reflect the electrical mechanical activities of heart, respectively. Although studies have documented that some abnormalities in ECG PCG are associated with coronary artery disease (CAD), only few researches combined two for automatic CAD detection. This paper aims to differentiate between non-CAD groups using simultaneously collected signals. To entirely exploit underlying information these signals, a novel dual-input neural network...
Image dehazing is a technique to enhance the images acquired in poor weather conditions, such as fog and haze. Existing image methods are mainly based on dark channel prior. Since not reasonable for sky regions, segmentation region wised medium transmission method proposed this paper. Firstly, regions segmented by quad-tree splitting feature pixels detection. Then, estimation color characteristic observation of regions. The then filtered an edge preserving guided filter. Finally, estimated...
Heart rate fluctuates beat-by-beat asymmetrically which is known as heart asymmetry (HRA). It challenging to assess HRA robustly based on short-term heartbeat interval series.An area index (AI) was developed that combines the distance and phase angle information of points in Poincaré plot. To test its performance, AI used classify subjects with: (i) arrhythmia, (ii) congestive failure, from corresponding healthy controls. For comparison, existing Porta's (PI), Guzik's (GI), slope (SI) were...
Abstract Objective : Coronary artery disease (CAD) is a common fatal disease. At present, an accurate method to screen CAD urgently needed. This study aims provide optimal detection models for suspected according the differences in medical conditions, so as assist physicians make judgments on patients. Approach Electrocardiogram (ECG) and phonocardiogram (PCG) signals of 32 patients 30 with chest pain normal coronary angiograms (CPNCA) were simultaneously collected this paper. For each...
Magnetic resonance (MR) images often suffer from random noise pollution during image acquisition and transmission, which impairs disease diagnosis by doctors or automated systems. In recent years, many removal algorithms with impressive performances have been proposed. this work, inspired the idea of deep learning, we propose a denoising method named 3D-Parallel-RicianNet, will combine global local information to remove in MR images. Specifically, introduce powerful dilated convolution...
ABSTRACT From five paddy rice cultivars grown in Taiwan and harvested the summers of 1997, 1998, 1999, calibrated models were established by backpropagation neural network program through different morphological color features selection for classifying summer 2000. With 60 features, average classification rates Model 1 5 92 99.8%, respectively. most effective 50 loading first principal component, rate 2 was 90.0%. 35 selected from correlation coefficient matrix, 3 91.0%. 20 area,...
This paper aims to classify normal/abnormal heart sound signals from PhysioNet/CinC challenge 2016. The are segmented into four states, i.e., the first sound, systolic interval, second and diastolic interval. Multi-features extracted time domain, frequency domain entropy, which formed three features sets. set includes 20 time-domain features. 16 frequency-domain third time-domain, 4 entropy sets used as inputs for both back propagation neural network logistic regression. 10-fold...
An early return of the reflected component in arterial pulse has been recognized as an important indicator cardiovascular risk. This study aimed to determine effects blood pressure and sex factor on change wave reflection using Gaussian fitting method. One hundred ninety subjects were enrolled. They classified into four categories based systolic pressures (i.e., ≤110, 111–120, 121–130 ≥131 mmHg). Each category was also stratified for factor. Electrocardiogram (ECG) radial artery waveforms...
Owing to complex structural machine tools in the Internet of Things (IoT)-enabled manufacturing workshop, personnel lack intuitive and visual auxiliary maintenance methods, significantly resulting improper with low efficiency poor reliability. To tackle these problems, an Augmented Reality (AR)-driven industrial metaverse for IoT-enabled workshop is proposed. Through fusion adaptive information entropy sharpening adjustment algorithm, proposed method can solve problem that traditional...
Heart rate variability (HRV), systolic period (SPV), and diastolic (DPV) have shown potential for assessing cardiac function. It is unknown whether the time delay between myocardial electrical mechanical activities (i.e., electromechanical delay, EMD) also possesses variability, if it does, this EMD (EMDV) could render additional value function assessment. In paper, we extracted beat-to-beat from 5-min simultaneously recorded electrocardiogram phonocardiogram signals in 30 patients with...
Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along edge of patches for following two reasons: firstly, order to ensure same size input and output, zero-padding is used, which causes uncertainty edges output feature map during extraction process; secondly, sliding window with different strides will result degrees artifacts. In this paper, we propose an exponential-distance-weighted (EDW)...
A novel method for high-dimensional mutual information registration is proposed. This first calculates matrix, and then the entropy of that matrix. The maximal corresponds to optimal solution. was qualitatively quantitatively evaluated on simulated real brain images. obtained results show proposed can improve accuracy decrease time.
The wavelet packet is presented as a new kind of multi-scale analysis technique followed Wavelet analysis. fundamental and its realization arithmetic the method are described in this paper. A application approach packed on extracting feature pulse signal from energy distributing angle expatiated. It convenient for microchip to process judge by using make signals quantized analyzed. Kinds experiments simulated lab prove that it more accurate extract which based packed-energy spectrum