Cheng He

Cheng He
Huazhong University of Science and Technology | hust · School of Electrical and Electronic Engineering

Doctor of Engineering

About

65
Publications
24,036
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
876
Citations
Introduction
Surrogate-assisted optimization, multi-objective optimization, constraint handling, large-scale optimization, the combination of deep learning and evolutionary algorithm, and real-world problems.
Additional affiliations
August 2020 - present
Southern University of Science and Technology
Position
  • Professor (Assistant)
September 2018 - July 2020
Southern University of Science and Technology
Position
  • PostDoc Position
September 2012 - July 2018
Huazhong University of Science and Technology
Position
  • PhD Student

Publications

Publications (65)
Article
Full-text available
In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhi...
Article
Full-text available
As a typical large-scale multiobjective optimization problem extracted from real-world applications, the voltage transformer ratio error estimation (TREE) problem is challenging for existing evolutionary algorithms (EAs). Due to the large number of decision variables in the problems, existing algorithms cannot solve TREE problems efficiently. Besid...
Article
Full-text available
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), neural architecture search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent training of CNNs for performance evaluation, most existing NAS methods are computationally exp...
Preprint
Full-text available
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries.Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationall...
Preprint
Full-text available
Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction. However, the issue of feature alignment remains as neglected by most existing approaches for simplicity. Direct pixel addition between upsampled and local features leads to feature maps with misaligned contexts that, in turn, translate to mis-c...
Article
Despite the remarkable successes of convolutional neural networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN. Among various neural architecture search (NAS) methods that are motivated to automate designs of high-performance CNNs, the differentiable NAS and population-based NAS are attracting increasing...
Article
Full-text available
Multi-objective evolutionary algorithms (MOEAs) have shown promising performance in solving various optimization problems, but their performance may deteriorate drastically when tackling problems containing a large number of decision variables. In recent years, a large amount of efforts have been devoted to addressing the challenges brought by larg...
Article
Constrained multiobjective optimization problems (CMOPs) are widespread in real-world applications. Nevertheless, CMOPs with discontinuous feasible regions are challenging for existing evolutionary algorithms due to the difficulty of passing through the infeasible regions. Moreover, there are only several benchmark test problems specified for promo...
Preprint
Full-text available
In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhi...
Article
Deep neural networks are widely used in the domain of image classification, and a large number of excellent deep neural networks have been proposed in recent years. However, hand-crafted neural networks often require human experts for elaborate designs, which can be time-consuming and error-prone. Hence, neural architecture search (NAS) methods hav...
Article
Only a small number of function evaluations can be afforded in many real-world multi-objective optimization problems where the function evaluations are economically/computationally expensive. Such problems pose great challenges to most existing multi-objective evolutionary algorithms which require a large number of function evaluations for optimiza...
Article
Full-text available
Various works have been proposed to solve expensive multiobjective optimization problems (EMOPs) using surrogate-assisted evolutionary algorithms (SAEAs) in recent decades. However, most existing methods focus on EMOPs with less than 30 decision variables, since a large number of training samples are required to build an accurate surrogate model fo...
Article
Full-text available
Inverse design has long been an efficient and powerful design tool in the aircraft industry. In this paper, a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning. A Conditional Variational AutoEncoder (CVAE) and an integrated generative network CVAE-GAN that combines the CVAE with the Wasse...
Chapter
Large-scale multiobjective optimization problems (LSMOPs) are emerging and widely existed in real-world applications, which involve a large number of decision variables and multiple conflicting objectives. Evolutionary algorithms (EAs) are naturally suitable for multiobjective optimization due to their population-based property, allowing the search...
Chapter
In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries. Despite the steady stream of impressive empirical results, most existing NAS algorithms are computationally prohibitive to execute due to the costly iterations of stochastic gradient descent (SGD) training. In this work, we pro...
Chapter
Mating restriction strategies are capable of restricting the distribution of parent solutions for effective offspring generation in evolutionary algorithms (EAs). Studies have shown the importance of these strategies in improving the performance of EAs for multiobjective optimization. Our previous study proposed a specific manifold learning inspire...
Chapter
In the past decades, a number of surrogate-assisted evolutionary algorithms (SAEAs) have been developed to solve expensive multiobjective optimization problems (EMOPs). However, most existing SAEAs focus on low-dimensional optimization problems, since a large number of training samples are required (which is unrealistic for EMOPs) to build an accur...
Chapter
Large-scale multiobjective optimization problems (LSMOPs) exist widely in real-world applications, and they are challenging for existing evolutionary algorithms due to their massive volume of search space. Despite that a number of large-scale multiobjective evolutionary algorithms (LSMOEAs) have been proposed in recent years, their effectiveness in...
Article
Full-text available
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to the classification performance. While a series of gradient based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyper-parameters. Owing to the high robustness and wide applic...
Code
The source codes of POCEA, which are appliable on PlatEMO v2.6.
Article
Full-text available
Constrained multiobjective optimization problems (CMOPs) widely exist in real-world applications, and they are challenging for conventional evolutionary algorithms (EAs) due to the existence of multiple constraints and objectives. When the number of objectives or decision variables is scaled up in CMOPs, the performance of EAs may degenerate dramat...
Conference Paper
Large-scale multiobjective optimization problems (LSMOPs) are emerging and widely existed in real-world applications, which involve a large number of decision variables and multiple conflicting objectives. Evolutionary algorithms (EAs) are naturally suitable for multiobjective optimization due to their population-based property, allowing the search...
Article
Full-text available
Multipopulation methods are highly effective in solving dynamic optimization problems. Three factors affect this significantly: 1) the exclusion mechanisms to avoid the convergence to the same peak by multiple subpopulations; 2) the resource allocation mechanism that assigns the computational resources to the subpopulations; and 3) the control mech...
Article
Full-text available
Abstract Due to acromegaly’s insidious onset and slow progression, its diagnosis is usually delayed, thus causing severe complications and treatment difficulty. A convenient screening method is imperative. Based on our previous work, we herein developed a new automatic diagnosis and severity-classification model for acromegaly using facial photogra...
Preprint
Full-text available
In the recent past, neural architecture search (NAS) has attracted increasing attention from both academia and industries. Despite the steady stream of impressive empirical results, most existing NAS algorithms are computationally prohibitive to execute due to the costly iterations of stochastic gradient descent (SGD) training. In this work, we pro...
Preprint
Full-text available
Despite the remarkable successes of Convolutional neural networks (CNN) in computer vision, it is time-consuming and error-prone to manually design a CNN. Among various neural architecture search (NAS) methods that are motivated to automate designs of high-performance CNNs, the differentiable NAS and population-based NAS are attracting increasing i...
Preprint
Despite significant advances in image-to-image (I2I) translation with Generative Adversarial Networks (GANs) have been made, it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a pair of generator and discriminator. Existing multimodal I2I translation methods adopt multiple domain-spe...
Article
Crossover is a crucial operation for generating promising offspring solutions in evolutionary multi-objective optimization. Among various crossover operators, the simulated binary crossover (SBX) is the most widely used in evolutionary multi-objective optimization. Despite that SBX is effective in solving problems with regular Pareto sets, its perf...
Article
Full-text available
Offspring generation plays an important role in evolutionary multiobjective optimization. However, generating promising candidate solutions effectively in high-dimensional spaces is particularly challenging. To address this issue, we propose an adaptive offspring generation method for large-scale multiobjective optimization. First, a preselection s...
Article
Full-text available
Recently, increasing works have proposed to drive evolutionary algorithms using machine learning models. Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models. Since it usually requires a certain amount of data (i.e., the candidate solutions generated by the algorith...
Chapter
Full-text available
Deep learning has achieved enormous breakthroughs in the field of image recognition. However, due to the time-consuming and error-prone process in discovering novel neural architecture, it remains a challenge for designing a specific network in handling a particular task. Hence, many automated neural architecture search methods are proposed to find...
Chapter
Full-text available
The convolution neural network is prominent in image processing, and a large number of excellent deep neural networks have been proposed in recent years. However, the hand-actuated design of a neural network is time-consuming, laborious, and challenging. Thus many neural architecture search (NAS) methods have been proposed, among which the evolutio...
Code
This is the Matlab implementation of the benchmark problems in "Evolutionary Large-Scale Multiobjective Optimization for Ratio Error Estimation of Voltage Transformers".
Article
Full-text available
Ratio error estimation of the voltage transformers plays an important role in modern power delivery systems. Existing ratio error estimation methods mainly focus on periodical calibration but ignore the time-varying property. Consequently, it is difficult to efficiently estimate the state of the voltage transformers in real time. To address this is...
Article
Full-text available
Under certain smoothness assumptions, the Pareto set of a continuous multiobjective optimization problem is a piecewise continuous manifold in the decision space, which can be derived from the Karush-Kuhn-Tucker condition. Despite that a number of multiobjective evolutionary algorithms (MOEAs) have been proposed, their performance on multi-objectiv...
Article
Full-text available
Diversity preservation is a crucial technique in multi-objective evolutionary algorithms (MOEAs), which aims at evolving the population towards the Pareto front with a uniform distribution and a good extensity. In spite of many diversity preservation approaches in existing MOEAs, most of them encounter difficulties in tackling complex Pareto fronts...
Article
Full-text available
Many real-world optimization applications have more than one objective, which are modeled as multiobjective optimization problems. Generally, those complex objective functions are approximated by expensive simulations rather than cheap analytic functions, which have been formulated as data-driven multiobjective optimization problems. The high compu...
Preprint
Full-text available
Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models.Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorith...
Article
Full-text available
A variety of evolutionary algorithms have been proposed for many-objective optimization in recent years. However, the difficulties in balancing the convergence and diversity of the population and selecting promising parents for offspring reproduction remain. In this paper, we propose a subregion division-based evolutionary algorithm with an effecti...
Code
The source codes of LSMOF.
Article
Full-text available
In this work, we propose a framework to accelerate the computational efficiency of evolutionary algorithms on large-scale multiobjective optimization. The main idea is to track the Pareto optimal set directly via problem reformulation. To begin with, the algorithm obtains a set of reference directions in the decision space and associates them with...
Article
Full-text available
In evolutionary multi-objective optimization, the Pareto front is approximated using a set of representative candidate solutions with good convergence and diversity. However, most existing multi-objective evolutionary algorithms have general difficulty in the approximation of Pareto fronts with complicated geometries. To address this issue, we prop...
Article
Full-text available
The evolutionary algorithms (EAs) are a family of nature-inspired algorithms widely used for solving complex optimization problems. Since the operators (e.g. crossover, mutation, selection) in most traditional EAs are developed on the basis of fixed heuristic rules or strategies, they are unable to learn the structures or properties of the problems...
Code
This is the code of our proposed CSEA in "A Classification-Based surrogate-Assisted Evolutionary Algorithm for Expensive Many-Objective Optimization". It works under the framework of PlatEMO (see website http://bimk.ahu.edu.cn/index.php?s=/Index/Software/index.html). The loss function of the neural network is constructed by the mean square error,...
Article
Conventional switching ripple suppressor design methods require the domain expert to tune the design parameters, which is attributed to the multiple and complicated performance requirements and real-world restrictions in switching ripple suppressor design. However, the expert tuning method is time-consuming and inefficient, and the designed switchi...
Experiment Findings
Full-text available
Article
Full-text available
Surrogate-assisted evolutionary algorithms have been developed mainly for solving expensive optimization problems where only a small number of real fitness evaluations are allowed. Most existing surrogate-assisted evolutionary algorithms are designed for solving low-dimensional single or multi-objective optimization problems, which are not well sui...
Article
Multi-objective vehicle routing problem with time windows (VRPTW) has important applications in engineering and computer science, and it is a NP-hard problem. In the last decade, numerous new methods for multi-objective VRPTW have sprung up. However, the calculation speed of most algorithms is not fast enough, and on the other hand, these algorithm...
Code
The source codes of the radial space division based evolutionary algorithm (RSEA). The implementation of the algorithm is based on the Matlab platform named PlatEMO (http://bimk.ahu.edu.cn/index.php?s=/Index/Software/index.html), please add the folder ”RSEA” into the ”Algorithm” folder of PlatEMO.
Article
Full-text available
Evolutionary algorithms have been used to solve a variety of many-objective optimization problems, where these problems contain more than three conflicting objectives. Most existing evolutionary algorithms have shown to perform well on many-objective optimization problems with regular Pareto optimal fronts, their performance, however, will often co...
Book
Full-text available
This book constitutes the proceedings of the 12th International Conference On Bio-inspired Computing: Theories and Applications, BIC-TA 2017, held in Harbin, China, December 2017. The 50 full papers presented were selected from 143 submissions. The papers deal with studies abstracting computing ideas such as data structures, operations with data, w...
Conference Paper
Vehicle routing problem with time windows has an important practical significance, but it is NP-Hard problem. In order to solve the problem, an optimization algorithm based on P system is proposed. The encoding of glowworm’s location is considered as evolutionary object and discrete glowworm evolution mechanism and variable neighborhood evolution m...
Article
Full-text available
Laser technology is vital in production of precision electronic components and has been widely used in modern industry. In laser soldering systems, accurate temperature control remains a challenging problem, since the temperature is highly sensitive to laser power and thermodynamic parameters of solder joints. In this paper, a good solution is prop...

Projects

Projects (3)
Project
This project mainly includes three goals: (1) Proposing benchmark test suits and real-world test problems to promote the application of evolutionary algorithms to the industry. (2) Designing high efficient evolutionary algorithms for accelerating the evolutionary algorithms on large-scale optimization. (3) Applying and refining the designed algorithms for specific real-world applications.
Project
Model-based evolutionary algorithms aims to build data-driven models for assisting the optimization of some specific multiobjective optimization problems. The model can be used at different levels, e.g., offspring generation, objective estimation, preselection, etc.