A5019653584- ECG Monitoring and Analysis
- EEG and Brain-Computer Interfaces
- Phonocardiography and Auscultation Techniques
- Tensor decomposition and applications
- Non-Invasive Vital Sign Monitoring
- Transportation Planning and Optimization
- Cardiovascular Function and Risk Factors
- Advanced Computing and Algorithms
- Atrial Fibrillation Management and Outcomes
- Cardiac electrophysiology and arrhythmias
- PAPR reduction in OFDM
- Control Systems in Engineering
- Industrial Technology and Control Systems
- Smart Parking Systems Research
- Hydraulic and Pneumatic Systems
- Cardiac Arrhythmias and Treatments
- Traditional Chinese Medicine Studies
- Artificial Intelligence in Healthcare
- Industrial Vision Systems and Defect Detection
- Neural Networks and Reservoir Computing
- Heart Rate Variability and Autonomic Control
- Functional Brain Connectivity Studies
- Transportation Systems and Logistics
- Cardiac Imaging and Diagnostics
- Neural dynamics and brain function
Hebei University
2018-2024
Advanced Institute of Industrial Technology
2022-2024
Beijing Institute of Technology
2024
Wuhan University
2022
Novel techniques in deep learning networks are proposed for the staked sparse autoencoder (SAE) and bagged decision tree (TreeBagger), achieving significant improvement detection localization of myocardial infarction (MI) from single-lead electrocardiograph (ECG) signals. With our layer-wise training strategies, SAE-based diagnostic feature extraction network can automatically steadily extract distinguishing features ECG signals avoid vanishing gradient problem. This is formed by stacking...
Depression is a prevalent mental disorder that affects significant portion of the global population. Despite recent advancements in EEG-based depression recognition models rooted machine learning and deep approaches, many lack comprehensive consideration depression's pathogenesis, leading to limited neuroscientific interpretability. To address these issues, we propose hemisphere asymmetry network (HEMAsNet) inspired by brain for from EEG signals. HEMAsNet employs combination multi-scale...
Myocardial infarction (MI) causes rapid and permanent damage to the heart muscle. Without timely diagnosis treatment, it will deteriorate myocardial structure function. The precise localization of MI based on 12-lead electrocardiogram (ECG) signals still remains a great challenge. We, thus, present novel algorithm for automatically localizing from multilead ECG signals. image-based heartbeat tensorization establishes third-order lead <inline-formula> <tex-math notation="LaTeX">${\times }$...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Myocardial infarction (MI) causes rapid and permanent damage to the heart muscle. Therefore, it can deteriorate myocardial structure function if not timely diagnosed treated. However, is difficult determine precise localization of MI based on vectorcardiogram (VCG) due existing studies ignore spatiotemporal features VCG. xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> In...
Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based electrocardiograms (ECGs), but prolonged analysis ECG signals very time-consuming. This paper designs an model the Inception module, constructing multi-branch channels to process raw signals, gradient frequency during AF. The efficiently extracted QRS...
ST segment morphology is closely related to cardiovascular disease. It used not only for characterizing different diseases, but also predicting the severity of However, short duration, low energy, variable and interference from various noises make classification a difficult task. In this paper, we address problems single feature extraction accuracy classification, use gradient surface improve multi-classification. identify five morphologies: normal, upward-sloping elevation, arch-back...
Existing public transportation reservation systems operate on a first-come-first-served basis, and do not consider mobility priorities. During the COVID-19 pandemic, overcrowding in facilities must be mitigated. However, limited number of high-priority users such as healthcare workers should able to commute safely. Moreover, is also required even for regular passengers some cases when they really need move important reasons. In this study, we propose new e-ticket system that performs maximum...
Myocardial infarction (MI) can cause acute and permanent damage to the myocardial muscle. Vectorcardiogram (VCG) is formed by time varying coordinates of cardiac electrical activity in space. According different infarct locations, ring VCG three orthogonal planes has pathological morphological changes. Yet existing algorithms only extract information lead signals, but they do not fully consider correlation between planes. We proposed a depthwise separable convolution network (DSC-Net) for...
Background and Objective: Paroxysmal Atrial Fibrillation (PAF) may lead to the decline of atrial mechanism hemodynamic disturbance, which is major risk factor for stroke, myocardial infarction, heart failure other diseases. Although a number methods have been developed detect PAF, they rely on long ECG signals. Furthermore, most studies are only intra-patient test, ignoring individual specificity.Methods: This paper proposes an automatic detection algorithm based combination RR interval...
Assuming an aging society where the number of expressway users decreases and maintenance costs for infrastructures remain high, we propose a new method analyzing whether routes should be closed when their cost-benefit ratios deteriorate owing to in users. As case study, analyzed Kawasaki route (the Kanagawa No. 6 metropolitan Japan) according proposed method. It was found that costbenefit ratio would less than 1 2025 decrease However, if closed, vehicles there run on National Route 409 as...
Marine diesel engine lubricating oil after long-term use, due to pollution and chemical activity, internal impurities increased, lubrication effect gradually deteriorated. The purification device based on balanced charge agglomeration (BCA) can realize the on-line of oil. In order further improve efficiency, a control system PLC is designed in this paper. consists complex electromechanical integration equipment composed equipment, touch screen. precise parameters realized by PLC, which...