A5014106677- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Cardiovascular Function and Risk Factors
- Congenital Heart Disease Studies
- Cardiac Valve Diseases and Treatments
- Cardiac pacing and defibrillation studies
- Cardiomyopathy and Myosin Studies
- Cardiovascular and Diving-Related Complications
- Cardiac Arrhythmias and Treatments
- Adversarial Robustness in Machine Learning
- Machine Learning and Data Classification
- Privacy-Preserving Technologies in Data
- Conducting polymers and applications
- Coronary Artery Anomalies
- Cryptography and Data Security
- Advanced Neural Network Applications
- Neural Networks and Applications
- Cardiac electrophysiology and arrhythmias
- Covalent Organic Framework Applications
- Text and Document Classification Technologies
- Cardiovascular Issues in Pregnancy
- Electrochemical Analysis and Applications
- Assembly Line Balancing Optimization
- Energy Efficiency and Management
Shenzhen University
2024
Southern University of Science and Technology
2018-2023
Shanghai Center for Brain Science and Brain-Inspired Technology
2020-2022
Shanghai Jiao Tong University
2006-2022
Shanghai Children's Medical Center
2006-2022
Collaborative Innovation Center of Chemistry for Energy Materials
2021
Xiamen University
2021
University of Science and Technology of China
2015-2020
Queen Mary Hospital
2009-2011
University of Hong Kong
2009-2010
The performance of traditional multiobjective evolutionary algorithms (MOEAs) often deteriorates rapidly as the number decision variables increases. While some efforts were made to design new by adapting existing techniques large-scale single-objective optimization MOEA context, specific difficulties that may arise from have rarely been studied. In this paper, exclusive challenges along with increase a problem (MOP) are examined empirically, and popular benchmarks categorized into three...
Abstract Large-scale multi-objective optimization problems (MOPs) that involve a large number of decision variables, have emerged from many real-world applications. While evolutionary algorithms (EAs) been widely acknowledged as mainstream method for MOPs, most research progress and successful applications EAs restricted to MOPs with small-scale variables. More recently, it has reported traditional (MOEAs) suffer severe deterioration the increase As result, motivated by emergence large-scale...
<h3>Objective</h3> The M-mode-derived left ventricular shortening fraction is incorporated into most of the paediatric oncology protocols for monitoring cardiotoxicity. This study tested hypothesis that alteration myocardial deformation and mechanical dyssynchrony may occur in asymptomatic children after anthracycline therapy despite having fractions within limits normal. <h3>Design</h3> Cross-sectional study. <h3>Setting</h3> Tertiary cardiac centre. <h3>Methods</h3> Left longitudinal,...
The field of adversarial textual attack has significantly grown over the past few years, where commonly considered objective is to craft examples (AEs) that can successfully fool target model. However, imperceptibility attacks, which also essential for practical attackers, often left out by previous studies. In consequence, crafted AEs tend have obvious structural and semantic differences from original human-written text, making them easily perceptible. this work, we advocate leveraging...
Minimum cost seed selection for competitive influence maximization, which selects a set of key users (called set) to spread its widely into the network at minimum in social network, is algorithmic problem analysis. Due application potential multiple fields, such as market expansion, election campaigns, and cultural competition, numerous studies have been emerging recently. Despite these efforts, this has not satisfactorily solved since only finding (nearly) optimal solution minimization but...
Abstract An electron conductive matrix, or collector, facilitates transport in an electrochemical device. It is stationary and does not change during the entire operation once it built. The interface of this matrix electrode constructed at a 2D level micro‐scale, naturally limits breadth depth reactions. Herein, idea enhanced coupled with conducting molecule that can extend interfacial reactions first introduced. With spatialized interspace, present understanding process opens up new realm...
Standard echocardiographic view recognition is a prerequisite for automatic diagnosis of congenital heart defects (CHDs). This study aims to evaluate the feasibility and accuracy standard in CHDs children using convolutional neural networks (CNNs). A new deep learning-based network method was proposed automatically efficiently identify commonly used views. total 367,571 image slices from 3,772 subjects were train validate model where 23 views diagnose identified. The F1 scores majority all...
Secundum atrial septal defect (ASD) is one of the most common congenital heart diseases (CHDs). This study aims to evaluate feasibility and accuracy automatic detection ASD in children based on color Doppler echocardiographic images using convolutional neural networks. In this study, we propose a fully system for ASD, which includes three stages. The first stage used identify four target views (that is, subcostal view focusing atrium septum, apical four-chamber view, low parasternal...
In children with coronary disease, clinical decision should be based on detailed measurements of the arteries by two-dimensional echocardiography. We aimed to establish artery reference indexed diameter and z scores regression equations in a large cohort Chinese Han children.We measured proximal right (RCA), left main (LMCA), anterior descending, circumflex artery, aortic annulus, calculated coronary-aorta index (coronary artery-to-aortic annulus ratio) 506 normal hearts whose ages ranged...
Neural network pruning is a popular approach to reducing the computational complexity of deep neural networks. In recent years, as growing evidence shows that conventional methods employ inappropriate proxy metrics, and new types hardware become increasingly available, hardware-aware incorporates characteristics in loop has gained attention. Both accuracy efficiency (latency, memory consumption, etc.) are critical objectives success pruning, but conflict between multiple makes it impossible...
Multi-fidelity simulation is an effective approach to balancing speed and accuracy in expensive simulation, its performance affected by the quality of multi-fidelity models. Building high-quality models non-trivial, especially for complex systems, because current manual modeling methods require sufficient domain knowledge experience, increasing labor time costs. Motivated issues, this paper focuses on one most crucial types, discrete event develops a computer-aid method called...
Multi Automated Guided Vehicle (multi-AGV) systems are widely used in Work-in-Process (WIP) warehouses to improve the efficiency of material transportation. However, collisions and deadlocks between AGVs inevitable. Many algorithms have been proposed solve these problems, but their performance is inefficient WIP warehouse due lack consideration its features. In this paper, fill gap current research real-world application requirement, we construct a collision deadlock solving model for...
A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the real function evaluations. However, search efficiency these SAEAs is not yet satisfactory. More efforts are needed further exploit useful information from evaluations in order better guide process. Facing this challenge, paper proposes a Hyperbolic Neural Network (HNN) based preselection operator...
Abstract Objective Clinical decision making in children with heart disease relies on detailed measurements of cardiac structures using two‐dimensional and M‐mode echocardiography. However, no echocardiographic reference values are available for the Chinese children. We aimed to establish z‐score regression equations left a population‐based cohort healthy Han Method Echocardiography was performed 545 normal heart. The dimensions aortic valve annulus (AVA), sinuses Valsalva (ASV), sinotubular...
Due to computationally and/or financially costly evaluation, tackling expensive multi-objective optimization problems is quite challenging for evolutionary algorithms. One popular approach these building cheap surrogate models replace the real function evaluations. To this end, various kinds of surrogate-assisted algorithms (SAEAs) have been proposed, which predict fitness values, classifications, or relation candidate solutions. However, off-spring generation, despite its important role in...