Uncovering the direct causal relationships between decision variables and optimization objectives can significantly simplify the complexity of optimization problems. However, most existing constrained multi-objective evolutionary algorithms (CMOEAs) fail to address constrained multi-objective optimization from this perspective. To bridge this gap, this study introduces a novel algorithm, CI-CMOEA (Causal Intervention-based CMOEA), which leverages causal intervention techniques to enhance optimization performance. CI-CMOEA begins by constructing a causal relationship network that captures the interactions between decision variables and optimization objectives. Using this network, a genetic operator with a causal relationship mask is designed to group decision variables based on their causal impact on the objectives. By focusing genetic operations on key variables with significant causal influence, the algorithm effectively guides the evolutionary optimization process towards better solutions. To further improve performance, CI-CMOEA employs a dual-population collaboration mechanism. One population operates under relaxed epsilon constraints to explore the solution space, while the other disregards constraints to enhance convergence. Preliminary experiments on the LIR-CMOP test suite demonstrate that CI-CMOEA not only accurately identifies the causal relationships between decision variables and objectives but also outperforms eight state-of-the-art CMOEAs in terms of IGD, IGD+ and HV metrics, showcasing its superior optimization performance and reliability.

Accurate retinal vessel segmentation plays a critical role in the early detection and monitoring of ophthalmic diseases. In this work, we propose a novel retinal vessel segmentation method that integrates Neural Architecture Search (NAS) with a U-shaped encoder-decoder network, optimized using particle swarm optimization (PSO). The framework automates the design of scalable architectures by exploring an extensible search space built with lightweight construction modules, including 3 × 3 convolutions, batch normalization, attention modules, and residual connections. Experimental results on the DRIVE and CHASE_DB1 datasets demonstrate that the searched model achieves superior segmentation accuracy with the fewest parameters (only 0.04M) compared to existing methods. Furthermore, the model exhibits competitive performance on the crack bench-mark dataset CrackLS315, highlighting the strong generalization capability of the searched architecture. In conclusion, the proposed method achieves an optimal balance between segmentation accuracy and model complexity, demonstrating its potential for clinical applications.

To address slow convergence and formation maintenance challenges in swarm robotic entrapment tasks, a predictive entrapment control algorithm that combines gene regulatory network and sliding mode control (GRN-SMC) is proposed. First, to stabilize the target position information generated by the hierarchical GRN, a novel sorting rule is designed. Then, an artificial neural network (ANN) is employed to perform on-line prediction of the swarm robots’ kinematic states. These predicted values are then fed into a specifically designed sliding mode controller, which ultimately outputs the optimal control velocities for the swarm robots. Comparative simulation experiments with three state-of-the-art algorithms demonstrate that our method achieves significant improvements in tracking accuracy(error reduced by 82%), single-iteration execution time(reduced by 29%), and formation maintenance (formation integrity increased by 34%). Furthermore, physical robot experiments demonstrate that even in the presence of unknown external disturbances (such as ground slippage) and robot positioning errors (±0.1 m, ±5°), the proposed algorithm still exhibits excellent robustness.

Effective infrastructure health monitoring is crucial within transportation cyber-physical systems, where accurate road health detection is vital for ensuring road safety and the stability of intelligent transportation systems. To address the challenges of identifying pavement subsurface objects using 3D ground penetrating radar (GPR) data, we propose a multi-perspective cascading recognition method that integrates B-scan and C-scan images. This method is built on a lightweight dual-stream semantic segmentation model called AttnGPRNet, developed in this work to improve feature extraction through attention mechanisms and enhance subsurface object recognition. Initially, the model segments B-scan images to identify potential target regions, followed by more precise segmentation of 3L-C-scan images based on preliminary results. Additionally, we constructed a multi-view dataset using 3D GPR scans from over 100 kilometers of urban roads and evaluated the effectiveness of the proposed method through experiments. Experimental results show that our model outperforms existing advanced methods, achieving mIoU of 78.80% and 83.96% on B-scan and 3L-C-scan, and F1 scores of 87.65% and 91.07%, respectively. Moreover, the method has been deployed in Xiaoning Road GPR image intelligent recognition system and verified through on-site drilling, demonstrating its practical potential for road health monitoring.

Real-world production scenarios often involve multiobjective optimization problems with intricate constraints. Although there has been a growing interest in multiobjective problems with complex constraints, such as the vehicle routing problem with time windows, existing multiobjective evolutionary optimization techniques still face significant challenges, particularly when addressing the fragmented and narrow feasible regions that arise from these constraints. Our research introduces a refined framework tailored for complex constrained multiobjective evolutionary optimization. The methodology conducts an initial strong-weak analysis to categorize constraints and merges each strong constraint with all weak constraints to form subsets. Each subset, combined with the original objective functions, defines a subproblem. Independent optimization of the original problem and subproblems is carried out by utilizing multiple populations. Information acquired from the subproblems’ populations is transferred into the population of the original issue, thereby expediting the detection of the feasible region and simplifying the resolution of the original problem. The efficacy of our innovative algorithm, when benchmarked against traditional constrained multiobjective evolutionary algorithms across 72 test functions, has demonstrated superior convergence, diversity, and competitiveness.

In the field of drilling engineering, the design and optimization of well trajectories are crucial. This study focuses on optimizing key aspects such as the length of the well trajectory, drill string torque, the energy of the well-profile, and accuracy in reaching the target. This problem encompasses eleven complex nonlinear constraints and four conflicting objectives, presenting challenges for traditional mathematical programming methods. To tackle this problem, we introduce a novel constrained many-objective optimization algorithm, named PPS-NSGA-III. The proposed algorithm partitions the objective space into subspaces, using NSGA-III to find Pareto optimal solutions in each, enhancing diversity. The push-and-pull search framework is employed to overcome local optima in each subproblem, accelerating overall convergence. Through a comparative analysis with some evolutionary algorithms, PPS-NSGA-III has shown superior performance. It delivers more effective design solutions with lower risk, reduced cost, and a higher drilling encounter rate in the proposed well trajectory optimization model.

Due to high expense of human labor, one major challenge for semantic segmentation in real-world scenarios is the lack of sufficient pixel-level labels, which is more serious when processing video data. To exploit unlabeled data for model training, semi-supervised learning methods attempt to construct pseudo labels or various auxiliary constraints as supervision signals. However, most of them just process video data as a set of independent images in a per-frame manner. The rich temporal relationships are ignored, which can serve as valuable clues for representation learning. Besides, this per-frame recognition paradigm is quite different from that of humans. Actually, benefited from the internal temporal relevance of video data, human would wisely use the distinguished semantic concepts in historical frames to aid the recognition of the current frame. Motivated by this observation, we propose a novel temporally-dependent classifier (TDC) to mimic the human-like recognition procedure. Comparing to the conventional classifier, TDC can guide the model to learn a group of temporally-consistent semantic concepts across frames, which essentially provides an implicit and effective constraint. We conduct extensive experiments on Cityscapes and Cam Vid, and the results demonstrate the superiority of our proposed method to previous state-of-the-art methods. The code is available at https://github.com/jfzhuang/TDC.

Deep convolutional neural networks (CNNs) have been widely used for fundus image classification and have achieved very impressive performance. However, the explainability of CNNs is poor because of their black-box nature, which limits their application in clinical practice. In this paper, we propose a novel method to search for discriminative regions to increase the confidence of CNNs in the classification of features in specific category, thereby helping users understand which regions in an image are important for a CNN to make a particular prediction. In the proposed method, a set of superpixels is selected in an evolutionary process, such that discriminative regions can be found automatically. Many experiments are conducted to verify the effectiveness of the proposed method. The average drop and average increase obtained with the proposed method are 0 and 77.8%, respectively, in fundus image classification, indicating that the proposed method is very effective in identifying discriminative regions. Additionally, several interesting findings are reported: 1) Some superpixels, which contain the evidence used by humans to make a certain decision in practice, can be identified as discriminative regions via the proposed method; 2) The superpixels identified as discriminative regions are distributed in different locations in an image rather than focusing on regions with a specific instance; and 3) The number of discriminative superpixels obtained via the proposed method is relatively small. In other words, a CNN model can employ a small portion of the pixels in an image to increase the confidence for a specific category.

Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.

Cracks are among the most common, most likely, and earliest of all pavement distresses. Detecting and repairing cracks as early as possible can help extend the service life of pavements. However, Detecting cracks with precision can be challenging due to their varied structural characteristics and complex background interference. In this paper, a new convolutional neural network architecture, OUR-Net, is designed to more efficiently treat both high-and low-frequency visual image features. An Ocatve Convolution is incorporated into the proposed network as an enhancement to conventional convolution. In particular, an Octave Convolution Residual Block (OCRB) is embedded in the encoder to replace the convolutional layer of the classical encoder. Moerover, we propose Octave Max Unpooling (OMU) as the upsampling operation of the decoder, enabling the neural network to learn how to decode multi-spatial frequency features. Compared with models using traditional convolution, OUR-Net has better capability of processing multi-scale information, thus simultaneously improving model performance while saving computational costs by reducing spatial redundancy. We evaluate the superiority of the proposed method by comparing it to state-of-the-art crack segmentation methods on four public datasets (CrackLS315, CFD, Crack200, DeepCrack), which encompass cracks of various widths. Comprehensive experimental results reveal that the proposed method performs excellently, which achieves F1-score and mIoU of 0.9112, 0.9271, 0.8106, 0.9318, and 0.8369, 0.8644, 0.6815, 0.8723, respectively, on the four datasets. A lightweight version of the proposed network is constructed using depthwise separable convolution that achieves excellent performance with only 0.88M parameters.

In real-world applications, there are some constrained multi-objective problems where the evaluation of objectives is expensive and the evaluation of constraints is cheap. Currently, few studies have focused on solving expensive constrained multi-objective optimization problems (ECMOPs), and they usually assume that the constraints of ECMOPs are also expensive. In this paper, we propose a surrogate-ensemble assisted coevolutionary algorithm (SEACoEA) for ECMOPs with inexpensive constraint evaluation. First, a feasible sampling strategy is designed to initialize the population in the feasible regions. Next, two populations are set to optimize the original ECMOP and the problem without considering constraints, respectively. To improve the search efficiency, we redesigned the objective function of the surrogate-ensemble model. Finally, a new infill strategy is proposed to select candidate individuals from each population for real evaluation. Experimental results show that the proposed algorithm performs significantly better on most MW problems compared to several state-of-the-art algorithms.

The dynamic multi-objective optimization problems (DMOPs) have brought great challenges to the traditional evolutionary optimization algorithms because of their constantly changing Pareto set(PS) and Pareto front(PF). In order to track the change of PS and PF quickly and keep the diversity of population, prediction-based methods have shown great prospects. However, most of the current methods utilize linear models to predict the changing PS. When the PS between different environments has nonlinear relationship, this kind of method can not accurately predict the PS at a new environment. In this paper, a dynamic multi-objective evolutionary optimization algorithm based on long short-term memory network (LSTM) prediction is proposed. In this algorithm, The first step is to calculate the center point of the obtained PS. The center points at different time form a time series. Then the LSTM model is trained by using the time series as training samples. Moreover, the center of the new PS are predicted by the obtained model. Because LSTM can make full use of historical information and fit the nonlinear relationship between the PS, the prediction accuracy can be guaranteed. Finally, a population generation strategy is used to generate an initialized population with both convergence and diversity. The proposed algorithm is tested on DF benchmark function. Experiments results show that the proposed algorithm can effectively handle DMOPs and has shown its superiorityin comparison with state-of-the-art algorithms.

Image dehazing can improve image clarity and visual effect, which plays a pivotal role in many computer vision tasks. Existing dehazing methods are mostly based on a single feature stream and tend to ignore the low-frequency characteristics of haze. In this paper, we propose a dual stream network for image dehazing. To enhance the edge information and texture detail of the image, we construct a frequency stream based on attention octave convolution. We decompose the features into high and low-frequency branches in the frequency stream to obtain different structural information. By adding a residual channel attention block, the attention octave convolution can extract frequency features more efficiently and effectively. Due to the lower resolution of low-frequency features in the frequency stream, the frequency stream features alone are insufficient for recovering the overall content of the image. Therefore, a content stream was added to compensate for the information lost in the frequency stream. By fusing the outputs of two feature streams, the network achieves an enhanced dehazing performance. The results show that our method is superior to other state-of-the-art algorithms in quantitative evaluation and visual impact.

Hand-eye calibration methods for surgical robots are employed to derive a transformation between the robot's base motor and visual coordinate systems. Accurately completing hand-eye calibration procedures provides an important guarantee that a surgical robot will exhibit positioning and execution accuracy sufficient for assisting surgeons in successfully completing surgical procedures. To improve the accuracy of robot hand-eye calibration methods based on backpropagation neural network (BPNN) models, we propose a modified BP neural network optimized using the sparrow search algorithm for hand-eye calibration model (TSSABPNN), which can enhance population initialization by applying tent mapping. Furthermore, we also design a new sliding 3D calibration tool. The sparrow search algorithm exhibits good local exploration ability, and we introduce a tent map with ergodic characteristics to initialize the sparrow population information, which further improves the network's global search ability and convergence rate. Finally, we experimentally analyze four calibration models: TSSABP NN model, a BP NN model optimized using a genetic algorithm of simulated annealing (GASABPNN), an unoptimized BP NN model, and the traditional singular value decomposition method. The results indicate that the proposed TSSABP NN model exhibits the maximum calibration precision and best robustness and iteratively converges faster.

Online path planning for multiple unmanned aerial vehicle (multi-UAV) systems is considered a challenging task. It needs to ensure collision-free path planning in real-time, especially when the multi-UAV systems can become very crowded on certain occasions. In this paper, we presented a vision-based decentralized collision-avoidance policy learning method for multi-UAV systems. The policy takes depth images and inertial measurements as sensory inputs and outputs UAV's steering commands, and it is trained together with the latent representation of depth images using a policy gradient-based reinforcement learning algorithm and autoencoder in the multi-UAV three-dimensional workspaces. Each UAV follows the same trained policy and acts independently to reach the goal without colliding or communicating with other UAVs. We validate our method in various simulated scenarios. The experimental results show that our learned policy can guarantee fully autonomous collision-free navigation for multi-UAV in three-dimensional workspaces, and its navigation performance will not be greatly affected by the increase in the number of UAVs.

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net.

Optimization modeling of real-world application problems usually involves noise from various sources. Noisy optimization imposes challenges to optimization methods since the objective values can be different for multiple evaluations. In this article, we propose a novel online population size learning (OPL) technique of evolution strategies for handling noisy optimization problems. By re-evaluating a fraction of the candidates, we measure the strength of noise level of the re-evaluated candidate solutions and adapt the population size according to the noise level. The proposed OPL combines the advantages of both explicit averaging by re-evaluations and the implicit averaging by large population size and overcomes their limitations. We incorporate it with the covariance matrix adaptation evolution strategy (CMA-ES) and obtain OPL-CMA-ES. Compared with the existing noise handling technique, the proposed OPL is much simpler in both concepts and computation. We conduct comprehensive experiments to evaluate the algorithm’s performance on standard problems with Gaussian noise. We further evaluate the performance of OPL-CMA-ES on the black-box optimization benchmarks (BBOBs) noisy testbed, which is a standard platform for comparing black-box optimization algorithms, compared with the state-of-the-art noise-handling algorithms. The experimental results show that OPL-CMA-ES achieves remarkable performance and outperforms the compared variants.

The gate assignment problem (GAP) aims at assigning gates to aircraft considering operational efficiency of airport and satisfaction of passengers. Unlike the existing works, we model the GAP as a bi-objective constrained optimization problem. The total walking distance of passengers and the total robust cost of the gate assignment are the two objectives to be optimized, while satisfying the constraints regarding the limited number of flights assigned to apron, as well as three types of compatibility. A set of real instances is then constructed based on the data obtained from the Baiyun airport (CAN) in Guangzhou, China. A two-phase large neighborhood search (2PLNS) is proposed, which accommodates a greedy and stochastic strategy (GSS) for the large neighborhood search; both to speed up its convergence and to avoid local optima. The empirical analysis and results on both the synthetic instances and the constructed real-world instances show a better performance for the proposed 2PLNS as compared to many state-of-the-art algorithms in literature. An efficient way of choosing the tradeoff from a large number of nondominated solutions is also discussed in this article.

Constrained optimization problem is a common issue in science and engineering. The key to solve this problem is to balance the relationship between constraints and objectives. Therefore, this paper proposes an s-shape constraint-handling method in push and pull search (SLSHADE-PPS), which divides the whole evolutionary process into two phases, called push search phase and pull search phase respectively. The push search phase mainly focuses on the value of the objective function and uses LSHADE to push the population into the optimal region of the objective function. In the pull search phase, the s-shape constraint handling technique is combined with LSHADE to pull the infeasible individuals back to feasible region. The s-shape function makes the violation tolerance maintain high level at the start stage and strictly limits the solutions to reside in the feasible region at the end stage of pull phase. SLSHADE-PPS shows significant advantages over the state-of-the-art constraint algorithms on the 28 benchmark test functions from IEEE CEC2017.

Multiobjective evolutionary algorithms (MOEAs) have progressed significantly in recent decades, but most of them are designed to solve unconstrained multiobjective optimization problems. In fact, many real-world multiobjective problems contain a number of constraints. To promote research on constrained multiobjective optimization, we first propose a problem classification scheme with three primary types of difficulty, which reflect various types of challenges presented by real-world optimization problems, in order to characterize the constraint functions in constrained multiobjective optimization problems (CMOPs). These are feasibility-hardness, convergence-hardness, and diversity-hardness. We then develop a general toolkit to construct difficulty adjustable and scalable CMOPs (DAS-CMOPs, or DAS-CMaOPs when the number of objectives is greater than three) with three types of parameterized constraint functions developed to capture the three proposed types of difficulty. In fact, the combination of the three primary constraint functions with different parameters allows the construction of a large variety of CMOPs, with difficulty that can be defined by a triplet, with each of its parameters specifying the level of one of the types of primary difficulty. Furthermore, the number of objectives in this toolkit can be scaled beyond three. Based on this toolkit, we suggest nine difficulty adjustable and scalable CMOPs and nine CMaOPs, to be called DAS-CMOP1-9 and DAS-CMaOP1-9, respectively. To evaluate the proposed test problems, two popular CMOEAs-MOEA/D-CDP (MOEA/D with constraint dominance principle) and NSGA-II-CDP (NSGA-II with constraint dominance principle) and two popular constrained many-objective evolutionary algorithms (CMaOEAs)-C-MOEA/DD and C-NSGA-III-are used to compare performance on DAS-CMOP1-9 and DAS-CMaOP1-9 with a variety of difficulty triplets, respectively. The experimental results reveal that mechanisms in MOEA/D-CDP may be more effective in solving convergence-hard DAS-CMOPs, while mechanisms of NSGA-II-CDP may be more effective in solving DAS-CMOPs with simultaneous diversity-, feasibility-, and convergence-hardness. Mechanisms in C-NSGA-III may be more effective in solving feasibility-hard CMaOPs, while mechanisms of C-MOEA/DD may be more effective in solving CMaOPs with convergence-hardness. In addition, none of them can solve these problems efficiently, which stimulates us to continue to develop new CMOEAs and CMaOEAs to solve the suggested DAS-CMOPs and DAS-CMaOPs.

In this article, we propose a novel approach to reduce hardware resource consumption when neural networks (NNs) are deployed on field-programmable gate array (FPGA) boards. Rather than using a classical approach with lookup tables (LUTs) to approximate the activation functions of an NN, the proposed solution is based on a twofold LUT (t-LUT) architecture, which comprises an error-LUT (e-LUT) and a data-LUT (d-LUT), in order to achieve high precision and speed as well as low hardware resource consumption. The efficiency of the proposed approach was tested against multiple earlier approaches. Our solution showed that the compressibility of the previously referenced works, which were based on single LUTs, could be improved by up to 94.44% and those that were based on a range addressable LUT (RALUT) by up to 6.35% in the examined case of a hyperbolic tangent (tanh) activation function. Moreover, when RALUT and our architecture were combined, it improved the compressibility of the RALUT-based result by up to additional 10.21% for a tanh activation function. The designed architecture had an initial latency of 39.721 ns, when tested with a 50-MHz clock, to simultaneously retrieve data from the d-LUT and t-LUTs.

In this paper, a hierarchical image matting model is proposed to extract blood vessels from fundus images. More specifically, a hierarchical strategy is integrated into the image matting model for blood vessel segmentation. Normally the matting models require a user specified trimap, which separates the input image into three regions: the foreground, background and unknown regions. However, creating a user specified trimap is laborious for vessel segmentation tasks. In this paper, we propose a method that first generates trimap automatically by utilizing region features of blood vessels, then applies a hierarchical image matting model to extract the vessel pixels from the unknown regions. The proposed method has low calculation time and outperforms many other state-of-art supervised and unsupervised methods. It achieves a vessel segmentation accuracy of 96.0%, 95.7% and 95.1% in an average time of 10.72s, 15.74s and 50.71s on images from three publicly available fundus image datasets DRIVE, STARE, and CHASE DB1, respectively.

Optical Coherence Tomography (OCT) is beco-ming one of the most important modalities for the noninvasive assessment of retinal eye diseases. As the number of acquired OCT volumes increases, automating the OCT image analysis is becoming increasingly relevant. In this paper, we propose a surrogate-assisted classification method to classify retinal OCT images automatically based on convolutional neural networks (CNNs). Image denoising is first performed to reduce the noise. Thresholding and morphological dilation are applied to extract the masks. The denoised images and the masks are then employed to generate a lot of surrogate images, which are used to train the CNN model. Finally, the prediction for a test image is determined by the average of the outputs from the trained CNN model on the surrogate images. The proposed method has been evaluated on different databases. The results (AUC of 0.9783 in the local database and AUC of 0.9856 in the Duke database) show that the proposed method is a very promising tool for classifying the retinal OCT images automatically.

This paper proposes an improved$\epsilon$constrained handling method (IEpsilon) for solving constrained single-objective optimization problems (CSOPs). The IEpsilon method adaptively adjusts the value of$\epsilon$according to the proportion of feasible solutions in the current population, which has an ability to balance the search between feasible regions and infeasible regions during the evolutionary process. The proposed constrained handling method is embedded to the differential evolutionary algorithm LSHADE44 to solve CSOPs. Furthermore, a new mutation operator DE/randr1*/1 is proposed in the LSHADE44-IEpsilon. In this paper, twenty-eight CSOPs given by “Problem Definitions and Evaluation Criteria for the CEC 2017 Competition on Constrained Real-Parameter Optimization” are tested by the LSHADE44-IEpsilon and four other differential evolution algorithms CAL-SHADE, LSHADE44+IDE, LSHADE44 and UDE. The experimental results show that the LSHADE44-IEpsilon outperforms these compared algorithms, which indicates that the IEpsilon is an effective constraint-handling method to solve the CEC2017 benchmarks.

Decomposition-based multiobjective evolutionary algorithm has shown its advantage in addressing many-objective optimization problem (MaOP). To further improve its convergence on MaOPs and its diversity for MaOPs with irregular Pareto fronts (PFs, e.g., degenerate and disconnected ones), we proposed a decomposition-based many-objective evolutionary algorithm with two types of adjustments for the direction vectors (MaOEA/D-2ADV). At the very beginning, search is only conducted along the boundary direction vectors to achieve fast convergence, followed by the increase of the number of the direction vectors for approximating a more complete PF. After that, a Pareto-dominance-based mechanism is used to detect the effectiveness of each direction vector and the positions of ineffective direction vectors are adjusted to better fit the shape of irregular PFs. The extensive experimental studies have been conducted to validate the efficiency of MaOEA/D-2ADV on many-objective optimization benchmark problems. The effects of each component in MaOEA/D-2ADV are also investigated in detail.

Decomposition-based multiobjective evolutionary algorithms (MOEAs) decompose a multiobjective optimization problem (MOP) into a set of scalar objective subproblems and solve them in a collaborative way. Commonly used decomposition approaches originate from mathematical programming and the direct use of them may not suit MOEAs due to their population-based property. For instance, these decomposition approaches used in MOEAs may cause the loss of diversity and/or be very sensitive to the shapes of Pareto fronts (PFs). This paper proposes a constrained decomposition with grids (CDG) that can better address these two issues thus more suitable for MOEAs. In addition, different subproblems in CDG defined by the constrained decomposition constitute a grid system. The grids have an inherent property of reflecting the information of neighborhood structures among the solutions, which is a desirable property for restricted mating selection in MOEAs. Based on CDG, a constrained decomposition MOEA with grid (CDG-MOEA) is further proposed. Extensive experiments are conducted to compare CDG-MOEA with the domination-based, indicator-based, and state-of-the-art decomposition-based MOEAs. The experimental results show that CDG-MOEA outperforms the compared algorithms in terms of both the convergence and diversity. More importantly, it is robust to the shapes of PFs and can still be very effective on MOPs with complex PFs (e.g., extremely convex, or with disparately scaled objectives).

Automated optic disk (OD) detection plays an important role in developing a computer aided system for eye diseases. In this paper, we propose an algorithm for the OD detection based on structured learning. A classifier model is trained based on structured learning. Then, we use the model to achieve the edge map of OD. Thresholding is performed on the edge map, thus a binary image of the OD is obtained. Finally, circle Hough transform is carried out to approximate the boundary of OD by a circle. The proposed algorithm has been evaluated on three public datasets and obtained promising results. The results (an area overlap and Dices coefficients of 0.8605 and 0.9181, respectively, an accuracy of 0.9777, and a true positive and false positive fraction of 0.9183 and 0.0102) show that the proposed method is very competitive with the state-of-the-art methods and is a reliable tool for the segmentation of OD.

Solving constrained multi-objective optimization problems is a difficult task, it needs to simultaneously optimize multiple conflicting objectives and a number of constraints. This paper first reviews a number of popular constrained multi-objective evolutionary algorithms (CMOEAs) and twenty-three widely used constrained multi-objective optimization problems (CMOPs) (including CF1-10, CTP1-8, BNH, CONSTR, OSY, SRN and TNK problems). Then eight popular CMOEAs with simulated binary crossover (SBX) and differential evolution (DE) operators are selected to test their performance on the twenty-three CMOPs. The eight CMOEAs can be classified into domination-based CMOEAs (including ATM, IDEA, NSGA-II-CDP and SP) and decomposition-based CMOEAs (including CMOEA/D, MOEA/D-CDP, MOEA/D-SR and MOEA/D-IEpsilon). The comprehensive experimental results indicate that IDEA has the best performance in the domination-based CMOEAs and MOEA/D-IEpsilon has the best performance in the decomposition-based CMOEAs. Among the eight CMOEAs, MOEA/D-IEpsilon with both SBX and DE operators has the best performance on the twenty-three test problems.

Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility.

Multiobjective evolutionary algorithm based on decomposition (MOEA/D) decomposes a multiobjective optimization problem (MOP) into a number of scalar optimization subproblems and then solves them in parallel. In many MOEA/D variants, each subproblem is associated with one and only one solution. An underlying assumption is that each subproblem has a different Pareto-optimal solution, which may not be held, for irregular Pareto fronts (PFs), e.g., disconnected and degenerate ones. In this paper, we propose a new variant of MOEA/D with sorting-and-selection (MOEA/D-SAS). Different from other selection schemes, the balance between convergence and diversity is achieved by two distinctive components, decomposition-based-sorting (DBS) and angle-based-selection (ABS). DBS only sorts L closest solutions to each subproblem to control the convergence and reduce the computational cost. The parameter L has been made adaptive based on the evolutionary process. ABS takes use of angle information between solutions in the objective space to maintain a more fine-grained diversity. In MOEA/D-SAS, different solutions can be associated with the same subproblems; and some subproblems are allowed to have no associated solution, more flexible to MOPs or many-objective optimization problems (MaOPs) with different shapes of PFs. Comprehensive experimental studies have shown that MOEA/D-SAS outperforms other approaches; and is especially effective on MOPs or MaOPs with irregular PFs. Moreover, the computational efficiency of DBS and the effects of ABS in MOEA/D-SAS are also investigated and discussed in detail.

Multi-objective evolutionary algorithms (MOEAs) have been widely used in solving multi-objective optimization problems. A great number of the-state-of-art MOEAs have been proposed. These MOEAs can be classified into the following categories: decomposition-based, domination-based, indicator-based, and probability-based methods. Among them, the first four categories belong to non-model based methods, while the fifth one is considered to be model-based method, in which machine learning techniques are often used to build the models. Recently, embedding machine learning mechanisms into MOEAs is becoming popular and promising. In this paper, a relatively thorough review on both traditional MOEAs and those equipped with machine learning mechanisms are made, with the aim of shedding light on the future development of this emerging research field.

This paper proposes a new constraint handling method named Angle-based Constrained Dominance Principle (ACDP). Unlike the original Constrained Dominance Principle (CDP), this approach adopts the angle information of the objective functions to enhance the population's diversity in the infeasible region. To be more specific, given two infeasible solutions, if the angle of the solutions is greater than a given threshold, they are considered to be non-dominated by each other. For a feasible solution and an infeasible solution, if the angle of the solutions is less than a given threshold, the feasible solution is better, otherwise they are non-dominated. To verify the proposed constraint handling approach ACDP, eight test problems CMOP1 to CMOP8 are introduced. The suggested algorithm MOEA/D-ACDP is compared with MOEA/D-CDP and NSGA-II-CDP on CMOP1 to CMOP8. The experimental results demonstrate that ACDP performs better than CDP in the framework of MOEA/D, and MOEA/D-ACDP is significantly better than NSGA-II-CDP, especially on the test instances with the very low ratio of feasible region against the whole objective space.

In this paper, a multi-phase strategy for dynamic resource allocation is proposed for some special optimization problems where the evolutionary process cannot be explicitly divided into two phases, under the decomposition-based multiobjective evolutionary optimization framework. Based on the evolutionary status, a switching mechanism is adopted to adaptively use either convergence or diversity information in the external archive, to guide the evolutionary search in the working population. The proposed algorithm is compared with six well-known multiobjective evolutionary algorithms on multiobjective travelling salesman problem (MOTSP). Experimental results show that our proposed algorithm performs better than other compared algorithms.

In this paper, we proposed a two-phase many-objective evolutionary algorithm to tackle many objective optimization problems. In the first phase, the algorithm focuses on achieving good convergence towards the boundary Pareto optimal solutions. In the second phase, it maintains a good balance between convergence and diversity by using a set of widely spread reference lines. In addition, a penalty based adjustment for reference line has been adopted to handle many objective optimization problems with incomplete PFs. The performance of our proposed algorithm is validated and compared with four state-of-the-art many objective evolutionary algorithms on DTLZ problems. The results show that our proposed algorithm is very competitive with other compared algorithms.

At Intensive Care Unit (ICU), acute hypotensive episode (AHE) can cause serious consequences. It can make the organs broken, or even the patient dead. Generally AHE is predicted by the doctor clinically. In order to forecast the AHE automatically, this paper proposes an algorithm based on the genetic programming (GP) and random forest (RF). The algorithm obtains features of the signal through the Intrinsic Mode Function (IMF) signal produced by applying empirical mode decomposition (EMD) to the arterial blood pressure (MAP) signal. Then the feature sets and the data sets are grouped to evolve decision functions via GP. Finally, a random forest is formed and the classification result is obtained by voting. The achieved accuracy of the proposed method is 77.55%, the sensitivity is 80.55% and specificity is 75.14% after the five-fold cross-validation.

Domination-based sorting and decomposition are two basic strategies used in multiobjective evolutionary optimization. This paper proposes a hybrid multiobjective evolutionary algorithm integrating these two different strategies for combinatorial optimization problems with two or three objectives. The proposed algorithm works with an internal (working) population and an external archive. It uses a decomposition-based strategy for evolving its working population and uses a domination-based sorting for maintaining the external archive. Information extracted from the external archive is used to decide which search regions should be searched at each generation. In such a way, the domination-based sorting and the decomposition strategy can complement each other. In our experimental studies, the proposed algorithm is compared with a domination-based approach, a decomposition-based one, and one of its enhanced variants on two well-known multiobjective combinatorial optimization problems. Experimental results show that our proposed algorithm outperforms other approaches. The effects of the external archive in the proposed algorithm are also investigated and discussed.

In this paper, we propose a decomposition based multiobjective evolutionary algorithm that extracts information from an external archive to guide the evolutionary search for continuous optimization problem. The proposed algorithm used a mechanism to identify the promising regions(subproblems) through learning information from the external archive to guide evolutionary search process. In order to demonstrate the performance of the algorithm, we conduct experiments to compare it with other decomposition based approaches. The results validate that our proposed algorithm is very competitive.

This paper investigates the issue of evolutionary design of open-ended plants for hybrid dynamical systems, i.e., both their topologies and parameters. Hybrid bond graphs (HBGs) are used to represent dynamical systems involving both continuous and discrete system dynamics. Genetic programming, with some special mechanisms incorporated, is used as a search tool to explore the open-ended design space of hybrid bond graphs. Combination of these two tools, i.e., HBGs and genetic programming, leads to an approach called HBGGP that can automatically generate viable design candidates of hybrid dynamical systems that fulfill predefined design specifications. A comprehensive investigation of a case study of DC-DC converter design demonstrates the feasibility and effectiveness of the HBGGP approach. Important characteristics of the approach are also discussed, with some future research directions pointed out.

This paper introduces a multi-objective optimization approach for layout synthesis of MEMS components. A case study of layout synthesis of a comb-driven micro-resonator shows that the approach proposed in this paper can lead to design results accommodating two design objectives, i.e. simultaneous minimization of size and power input of a MEMS device, while investigating optimum geometrical configuration as the main concern. The major contribution of this paper is the application of memetic computing in MEMS design. An evolutionary multiobjective optimization (EMO) technique, in particular non dominated sorting genetic algorithm (NSGA-II), has been applied to find multiple trade-off solutions followed by a gradient-based local search, i.e. sequential quadratic programming (SQP), to improve the convergence of the obtained Pareto-optimal front. In order to reduce the number of function evaluations in the local search procedure, the obtained non-dominated solutions are clustered in the objective space and consequently, a post optimality study is manually performed to find out some common design principles among those solutions. Finally, two reasonable design choices have been offered based on manufacturability issues.

This paper focuses on the mobile robot localization problems: pose tracking, global localization and robot kidnap. Differential Evolution (DE) applied to extend Monte Carlo Localization (MCL) was investigated to better solve localization problem by increasing localization reliability and speed. In addition, a novel mechanism for effective robot kidnap detection was proposed. Experiments were performed using computer simulations based on the odometer data and laser range finder measurements collected in advance by a robot in real-life. Experimental results showed that integrating DE enables MCL to provide more accurate robot pose estimations in shorter time while using fewer particles.

This paper presents a new method for mapping multi-floor buildings. The method combines laser range sensor for metric mapping and barometric pressure sensor for detecting floor transitions and map segmentation. We exploit the fact that the barometric pressure is a function of the elevation, and it varies between different floors. The method is tested with a real robot in a typical indoor environment, and the results show that physically consistent multi5floor representations are achievable.

This paper presents a comparison of an evolutionary methodology for evolving finite state controller to the lookahead controller for hybrid system. To illustrate the advantages and disadvantages of both controllers two case studies, namely a two-tanks system and a single-input double-output DC-DC converter circuit, are used for comparison.

This video presents a practical navigation scheme for indoor mobile robots using hybrid maps. The method makes use of metric maps for local navigation and a topological map for global path planning. Metric maps are generated as occupancy grids by a laser range finder to represent local information about partial areas. The global topological map is used to indicate the connectivity of the `places-of-interests' in the environment and the interconnectivity of the local maps. Visual tags on the ceiling to be detected by the robot provide valuable information and contribute to reliable localization. The navigation scheme based on the hybrid metric-topological maps saves memory space and is also scalable and adaptable since new local maps can be easily added to the global topology, and the method can be deployed with minimum amount of modification if new areas are to be explored. The video demonstrated that the method is implemented successfully on physical robot in a hospital environment, which provides a practical solution for indoor navigation.

Bed allocation is a crucial issue in hospital management. This paper proposes a multi-objective comprehensive learning particle swarm optimization with a representation scheme based on binary search (BS-MOCLPSO) to deal with this problem in general hospital. The bed allocation problem (BAP) is first modeled as an M/PH/c queue. Based on the queuing theory, the mathematical forms of admission rates and bed occupancy rate is deduced for each department of the hospital. Taking the maximization of both rates as objectives, the BS-MOCLPSO generates a set of non-dominated optimal allocation decisions for the hospital manager to select. The proposed algorithm introduces a novel binary search-based representation scheme, which transforms a particle's position into a feasible allocation scheme through binary search. Simulation results on real hospital data show that the proposed algorithm can offer allocation decisions that lead to higher service level and better resource utilization.

In this paper, we propose a methodology to improve the performance of the standard Differential Evolution (DE) in constraint optimization applications, in terms of accelerating its search speed, and improving the success rate. One critical mechanism embedded in the approach is applying Stochastic Ranking (SR) to rank the whole population of individuals with both objective value and constraint violation to be compared. The ranked population is then in a better shape to provide useful information e.g. direction to guide the search process. The strength of utilizing the directional information can be further controlled by a parameter - population partitioning factor, which is adjusted according to the evolution stage and generations. Because the adaptive adjustment of the parameter is predefined and does not need user input, the resulting algorithm is free of definition of this extra parameter and easier to implement. The performance of the proposed approach, which we call SRaDE (Stochastic Ranking based Adaptive Differential Evolution) is investigated and compared with standard DE. The experimental results show that SRDE significantly outperforms, or at least is comparable with standard DE in all the tested benchmark functions. We also conducted an experiment to compare SRaDE with SRDE - a variant of Stochastic Ranking based Differential Evolution without adaptive adjustment of the population partitioning factor. Experimental results show that SRaDE can also achieve improved performance over SRDE.

In the recent decades much research has been performed in order to allow better control of arc welding processes, but the success has been limited, and the vast majority of the industrial structural welding work is therefore still being made manually. Closed-loop and nearly-closed-loop control of the processes requires the extraction of characteristic parameters of the welding groove close to the molten pool, i.e. in an environment dominated by the very intense light emission from the welding arc. The typical industrial solution today is a laser-scanner containing a camera as well as a laser source illuminating the groove by a light curtain and thus allowing details of the groove geometry to be extracted by triangulation. This solution is relatively expensive and must act several centimetres ahead of the molten pool. In addition laser-scanners often show problems when dealing with shiny surfaces. It is highly desirable to extract groove features closer to the arc and thus facilitate for a nearly-closed-loop control situation. On the other hand, for performing seam tracking and nearly-closed-loop control it is not necessary to obtain very detailed information about the molten pool area as long as some important features are obtained, e.g. the groove position and gap width. To obtain these features without external illumination, a new image analysis scheme based on active contour models was proposed and verified by experimental results.

This paper describes the use of a genetic algorithm (GA) in tuning a double-level modular fuzzy logic controller (DLMFLC), which can expand its control working zone to a larger spectrum than a single-level FLC. The first-level FLCs are tuned by a GA so that the input parameters of their membership functions and fuzzy rules are optimized according to their individual working zones. The second-level FLC is then used to adjust contributions of the first-level FLCs to the final output signal of the whole controller, i.e., DLMFLC, so that it can function in a wider spectrum covering all individual working zones of the first-level FLCs. The second-level FLC is again optimized by a GA. An inverted pendulum system (IPS) is used to demonstrate the feasibility of the approach.

This paper aims at investigating and characterizing force behavior and mechanical properties of living drosophila embryos using an in situ modeled PVDF (polyvinylidene fluoride) piezoelectric microforce sensing tool with a resolution in the range of sub-muN. Drosophila embryo is one of the most studied organisms in biological research, medical research, genetics and developmental biology, and has implications in the cure of human diseases. In order to achieve high efficiency and accuracy during microinjection of genetic material into a drosophila embryo, it is absolutely necessary to allow close monitoring of the magnitude and direction of microinjection forces acting on the embryo during injection. In this paper, a microrobotic biomanipulation platform integrating a two-axis (2-D) modeled PVDF micro-force sensor is used to implement force sensing during microinjection of living drosophila embryos. Micro injection forces and membrane deformation of embryos in different stages of embryogenesis are found. Ultimately, the technology will provide a critical and major step towards the development of automated biomanipuation for batch microinjection of living embryos in genetics

Many current Evolutionary Algorithms (EAs) suffer from a tendency to converge prematurely or stagnate without progress for complex problems. This may be due to the loss of or failure to discover certain valuable genetic material or the loss of the capability to discover new genetic material before convergence has limited the algorithm's ability to search widely. In this paper, the Hierarchical Fair Competition (HFC) model, including several variants, is proposed as a generic framework for sustainable evolutionary search by transforming the convergent nature of the current EA framework into a non-convergent search process. That is, the structure of HFC does not allow the convergence of the population to the vicinity of any set of optimal or locally optimal solutions. The sustainable search capability of HFC is achieved by ensuring a continuous supply and the incorporation of genetic material in a hierarchical manner, and by culturing and maintaining, but continually renewing, populations of individuals of intermediate fitness levels. HFC employs an assembly-line structure in which subpopulations are hierarchically organized into different fitness levels, reducing the selection pressure within each subpopulation while maintaining the global selection pressure to help ensure the exploitation of the good genetic material found. Three EAs based on the HFC principle are tested - two on the even-10-parity genetic programming benchmark problem and a real-world analog circuit synthesis problem, and another on the HIFF genetic algorithm (GA) benchmark problem. The significant gain in robustness, scalability and efficiency by HFC, with little additional computing effort, and its tolerance of small population sizes, demonstrates its effectiveness on these problems and shows promise of its potential for improving other existing EAs for difficult problems. A paradigm shift from that of most EAs is proposed: rather than trying to escape from local optima or delay convergence at a local optimum, HFC allows the emergence of new optima continually in a bottom-up manner, maintaining low local selection pressure at all fitness levels, while fostering exploitation of high-fitness individuals through promotion to higher levels.

This paper describes a unified network synthesis approach for the conceptual stage of mechatronic systems design using bond graphs. It facilitates knowledge interaction with evolutionary computation significantly by encoding the structure of a bond graph in a genetic programming tree representation. On the one hand, since bond graphs provide a succinct set of basic design primitives for mechatronic systems modeling, it is possible to extract useful modular design knowledge discovered during the evolutionary process for design creativity and reusability. On the other hand, design knowledge gained from experience can be incorporated into the evolutionary process to improve the topologically open-ended search capability of genetic programming for enhanced search efficiency and design feasibility. This integrated knowledge-based design approach is demonstrated in a quarter-car suspension control system synthesis and a MEMS bandpass filter design application.

We discuss the hierarchy that is involved in a typical MEMS design and how evolutionary approaches can be used to automate the hierarchical design and synthesis process for MEMS. At the system level, the approach combining bond graphs and genetic programming can lead to satisfactory design candidates of system level models that meet the predefined behavioral specifications for designers to tradeoff. At the physical layout synthesis level, the selection of geometric parameters for component devices is formulated as a constrained optimization problem and addressed using a constrained GA approach. A multiple-resonator microsystem design is used to illustrate the integrated design automation idea using evolutionary approaches.