Data augmentation is crucial for addressing insufficient training data, especially for augmenting positive samples. However, existing methods mostly rely on neural network-based feedback for data augmentation and often overlook the optimization of feature distribution. In this study, we present a practical, distribution-preserving data augmentation pipeline that augments positive samples by optimizing a feature indicator (e.g., two-dimensional entropy), aiming to maintain alignment with the original data distribution. Inspired by the manifold hypothesis, we propose a Manifold Heuristic Optimization Algorithm (MHOA), which augments positive samples by exploring the low-dimensional Euclidean space around object contour pixels instead of the entire decision space. Guided by a "distribution-preservation-first" perspective, our approach explicitly optimizes fidelity to the original data manifold and only retains augmented samples whose feature statistics (e.g., mean, variance) align with the source class. It significantly improves image classification accuracy across neural networks, outperforming state-of-the-art data augmentation methods-especially when the dataset's feature indicator follows a Gaussian distribution. The algorithm's search space, focused on neighborhoods of key feature pixels, is the core driver of its superior performance.

ABSTRACT Objective The task of code generation aims to transform natural language descriptions into corresponding target code. Among the various approaches, syntax‐aware code generation has emerged as a significant approach that strives to generate code by directly modeling the underlying syntactic rules. However, existing works typically adopt an autoregressive approach to sequentially generate each abstract syntax rule, which inevitably neglects the rich structural semantic information inherent within the syntax rules. To address this issue, we propose an enhanced architecture of structure semantics based on Graph Neural Network for code generation. Methods Our approach explicitly models the internal structure of syntactic rules by treating them as graph data, thereby enabling the extraction of deeper structural semantics. Furthermore, we jointly model both the sequential semantics and structural semantics of syntactic rules, effectively addressing the limitations of solely sequence‐based approaches in capturing the inherent structural semantics of code. Results Experimental results on two widely used code generation datasets demonstrate that the proposed model consistently outperforms strong baselines, with gains of up to 2.14 BLEU points and 2.02 CodeBLEU points, highlighting the effectiveness of our structural‐semantic modeling approach for code generation.

Constraint-handling techniques and genetic operators are two crucial components in constrained multi-objective evolutionary algorithms (CMOEAs). Recent research in most of CMOEAs has primarily focused on adaptive designs of these components to address various constrained multi-objective optimization problems (CMOPs). However, the evolutionary process of solving a CMOP can involve various characteristics, such as continuity, discreteness, degeneracy, or some combination thereof, necessitating the tailored selection of constraint-handling techniques and genetic operators across different generations. This study conceptualizes these selections as a temporal sequence of constrained handling selection, where the time means the generation number. We argue that discovering the systematic patterns within the sequence based on the historical data of applying different selections significantly improves the performance of CMOEAs in finding Pareto optimal solutions. Based on this conceptualization, we propose a CMOEA with a deep reinforcement learning model for solving CMOPs. Specifically, the deep reinforcement learning model dynamically refines the selection of constraint-handling techniques and genetic operators for upcoming generations by learning from the performance of previous selections, thereby enhancing the predictive accuracy for subsequent selections. Experiments are conducted to validate the performance of the proposed algorithm against nine CMOEAs on thirty-seven benchmark problems and an unmanned aerial vehicle path planning problem. Experimental results show that the proposed algorithm substantially outperforms the compared algorithms regarding the obtained Pareto optimal solutions. Additionally, the results verify that discovering the systematic patterns within the sequence for CMOEAs has a positive impact on solving CMOPs in terms of objective optimization and constraint satisfaction.

Fine-tuning has emerged as a popular technique in the field of transfer learning, demonstrating remarkable achievements in various data-scarce tasks. The performance of fine-tuning in deep convolutional neural networks depends on the selection of which parameters to fine-tune and freeze. However, it is difficult to determine which parameters in the pre-trained model need to be fine-tuned for a new task. This article proposes a filter-level discrete optimization model to identify the filter subset for fine-tuning, a core step of filter selection coding optimization. Due to the huge search space of the filter fine-tuning problem, we propose a filter interactivity decomposition strategy to find a valid search subspace (a smaller search subspace containing the optimal solution) by dividing the entire filter fine-tuning problem into multiple suboptimization problems. Based on the decomposition strategy, we design a microscale-searching transfer optimization algorithm, which solves each subproblem by searching the valid search subspace instead of the original search space of the filter fine-tuning problem. To verify the validity of the proposed algorithm, extensive experiments are conducted on seven publicly available image classification datasets: Stanford Dogs, MIT Indoors, Caltech 256-30, Caltech 256-60, Aircraft, UCF-101, and Omniglot. Experimental results show that the proposed method significantly improves the fine-tuning accuracy while effectively reducing the filter fine-tuning problem scale. Moreover, the proposed algorithm outperforms the state-of-the-art fine-tuning methods on the fine-tuning problem for transfer learning.

Symbolic regression is a powerful technique for discovering mathematical expressions that best fit observed data.While neural symbolic regression methods based on large-scale pretrained models perform well on simple tasks, the reliance on fixed parametric knowledge typically limits their generalization to complex and diverse data distributions.To address this challenge, we propose a syntax-aware retrieval-augmented mechanism that leverages the syntactic structure of symbolic expressions to perform context-aware retrieval from a preconstructed token datastore during inference.This mechanism enables the model to incorporate highly relevant non-parametric prior information to assist in expression generation.Additionally, we design an entropy-based confidence network that dynamically adjusts the fusion strength between neural and retrieved components by estimating predictive uncertainty.Extensive experiments on multiple symbolic regression benchmarks demonstrate that the proposed method significantly outperforms representative baselines, validating the effectiveness of retrieval augmentation in enhancing the generalization performance of neural symbolic regression models.

Natural image matting is a widely used image processing technique that extracts foreground by predicting the alpha values of the unknown region based on the alpha values of the known foreground and background regions. However, existing image matting methods may not yield the most optimal results when applied to images containing transparent objects because the known foreground region is small or even absent. To address this shortcoming, in this paper, we propose a novel method named Transparent Object Matting using Predicted Definite Foreground and Background (TOM-PDFB), which can explore and utilize the definite foreground and background in the unknown region. For this purpose, a newly developed foreground-background confidence estimator is applied to predict the confidence level of the definite foreground and the definite background, thus providing the priors required for transparent object matting. Next, foreground-background guided progressive refinement network developed as a part of this work is adopted to incorporate the estimated definite foreground and background into the alpha matte refinement process. Extensive experimental results demonstrate that the TOM-PDFB outperforms state-of-the-art methods when applied to transparent objects. Project page:https://github.com/yihuiliang/TOM-PDFB.

High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. Project page: https://github.com/yexianmin/HRAMR-Matting.

Neural architecture search (NAS) is crucial for text representation in natural language processing (NLP); however, much less work on NAS for text classification has been proposed compared with NAS for computer vision. Similar to NAS for vision tasks, most existing work rely on a manually designed search space defined by a directed acyclic graph (DAG), resulting in limited generalization capability and high computational complexity. In text classification, the topological order of the NAS operators is essential for enhancing generalization, which cannot be accurately represented by a DAG. To address this issue, we propose a bipartite graph-based NAS (BGNAS) for text classification, which converts a DAG into a dual graph and then into a bipartite graph. This transformation makes it possible to accurately capture the topological order using multi-bigraph matching. In addition, we formulate NAS as a problem of identifying the lower bound of a submodular function, theoretically ensuring that optimal architectures in a bipartite graph-based search space can be identified using fewer search operators. Reduction of the search space is achieved by eliminating ineffective associated matching rules among search operators with a pruning strategy. As a result, the bipartite graph-based search space becomes more compact and less dependent on complex contextual semantics of text data. Experimental results on public benchmark problems demonstrate that BGNAS achieves better performance than the state-of-the-art NAS algorithms and is computationally more efficient. We also demonstrate that the bipartite graph search space can more effectively capture contextual semantics, thereby enhancing the generalization capability.

Legal text retrieval holds significant importance in the audit field, posing a challenge as a semantic matching problem. Despite the success of text semantic matching methods, particularly with the advent of large language models, these approaches face challenges when applied to domain-specific tasks, like legal text retrieval. Specifically, issues arise due to the concentrated distribution of data within the specific domain and the insufficient number of training samples. To address these challenges, this paper introduces a text semantic matching model tailored for the task of legal text retrieval, leveraging contrastive learning and evolutionary algorithms. A contrastive learning-based embedding model, which learns semantic representations in a feature space, is used to minimize the distance between matched text pairs and maximize the distance between unmatched text pairs. Additionally, an evolutionary algorithm-based sample augmentation model is introduced to augment the sample set and enhance the representational capabilities of the samples. The efficacy of the proposed method is evaluated in the context of legal text retrieval in the auditing field, and the experimental results reveal promising outcomes, with the proposed method achieving a Hits@l accuracy of 53.09%, a 2.99% improvement over the best baseline model. The Hits@20 accuracy reaches 75.15%, representing a 2.69% enhancement compared to the state-of-the-art methods.

Automated test case generation based on path coverage is not only a large-scale black-box optimization problem , but also a key scientific problem in software automatic testing technology. Evolutionary algorithms and other search-based algorithms are representative methods for this problem. However, existing research mainly focuses on the multi-function case, where generating test cases for multiple functions is difficult due to the combinatorial explosion of the path number. In this paper, we propose a multi-task collaborative method based on manifold optimization by considering the topological manifold relationship between the test case space (decision space) and the program path space (target space). This method achieves the goal of collaborative optimization for different function coverage tasks by coordinating the allocation of computing resources and knowledge transfer mechanisms among them. To verify the effectiveness of the proposed method, we compare it with general solution methods for single-function automated test case generation based on path coverage, such as the manifold-inspired search-based algorithm. The experimental results show that the proposed method outperforms the compared single-function optimization algorithms especially on programs with strong coding similarities. This study verifies the feasibility of collaborative optimization methods for solving large-scale black-box optimization problems, such as the automated test case generation based on path coverage, and expands their application scenarios.

Constrained optimization is an active research topic in evolutionary computation. It challenges evolutionary algorithms in allocating fitness evaluations to the minimization of constraint violations and the optimization of objectives. Most existing evolutionary algorithms implement fixed allocation schemes by using non-priority, priority, or priority-complete comparison criteria. This paper argues that different constrained optimization problems should be solved by algorithms with a dynamic allocation scheme, and the key to adjusting the allocation scheme is a judgement on whether the objective optimization or the constraint violation minimization is beneficial to finding the optimum. In this paper, correlations between objectives and constraints are measured for the judgement. Based on the correlations, a dynamic allocation scheme for fitness evaluations is proposed for constrained evolutionary algorithms. The objective priority criterion or the objective priority-complete criterion is dynamically selected to allocate more fitness evaluations to the objective optimization if the optimization of objectives is beneficial. Otherwise, the constraint priority criterion or the constraint priority-complete criterion is selected to allocate fitness evaluations. Experimental results show that algorithms with the selected criterion significantly outperform state-of-the-art algorithms in terms of attaining feasible solutions with better objective values. Furthermore, algorithms with the dynamic allocation scheme have the advantage of consistently finding feasible solutions with better objective values than algorithms based on non-beneficial, fixed, and randomly selected schemes. The results demonstrate the positive impact of the correlation-based dynamic allocation scheme on evolutionary algorithms for solving constrained optimization problems.

Consensus representation learning is one of the most popular approaches in the field of multi-view clustering. However, most of the existing methods cannot learn discriminative representations with a clustering-friendly structure since these methods ignore the separation among clusters and the compactness within each cluster. To tackle this issue, we propose a new deep multi-view clustering network with a dual contrastive mechanism to learn clustering-friendly representations. Specifically, our method employs dual contrasting losses: a dynamic cluster diffusion loss to maximize the distance between different clusters and a reliable neighbor-guided positive alignment loss to enhance compactness within each cluster. Our approach includes several key components: view-specific encoders to extract high-level features from each view, and an adaptive feature fusion strategy to obtain consensus representations across multiple views. The dynamic cluster diffusion module ensures inter-cluster separation by maximizing distances between different clusters in the consensus feature space. Simultaneously, the reliable neighbor-guided positive alignment module improves within-cluster compactness through a pseudo-label and nearest neighbor structure-driven contrastive loss. Experimental results on several datasets show that our method can acquire clustering-friendly representations with both good properties of inter-cluster separation and within-cluster compactness, and outperforms the existing state-of-the-art approaches in clustering performance. Our source code is available at https://github.com/tweety1028/DCMVC.

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.

A Software Product Line (SPL) is a set of software products that are built from a variability model. Real-world SPLs typically involve a vast number of valid products, making it impossible to individually test each of them. This arises the need for automated test suite generation, which was previously modeled as either a single-objective or a multi-objective optimization problem considering only objective functions. This article provides a completely different mathematical model by exploiting the benefits of Quality-Diversity (QD) optimization that is composed of not only an objective function (e.g., t -wise coverage or test suite diversity) but also a user-defined behavior space (e.g., the space with test suite size as its dimension). We argue that the new model is more suitable and generic than the two alternatives because it provides at a time a large set of diverse (measured in the behavior space) and high-performing solutions that can ease the decision-making process. We apply MAP-Elites, one of the most popular QD algorithms, to solve the model. The results of the evaluation, on both realistic and artificial SPLs, are promising, with MAP-Elites significantly and substantially outperforming both single- and multi-objective approaches, and also several state-of-the-art SPL testing tools. In summary, this article provides a new and promising perspective on the test suite generation for SPLs.

Zero-shot multi-label text classification has become a hot topic recently and has a wide range of applications, including assigning legal concepts to legislation, category information to goods, and disease information to patient records. Existing approaches employ a series of neural networks to represent the text and labels separately by relying on artificial experience, which can not achieve good performance. To effectively represent text data and multi-label data together, it is critical to aggregate the neighboring information with graph structure information in zero-shot multi-label text classification. To solve this problem, we propose a neural architecture search (NAS) approach with heterogeneous representation learning for the representation of text data and labels data together. We split the original search space of NAS into two heterogeneous search spaces and reformulated NAS with heterogeneous representation learning to aggregate neighboring information better and reduce unnecessary search. Besides, we design an alternating search strategy to search for suitable neural architectures for zero-shot multi-label text classification. We conduct neural architecture search and retraining experiments on ERULEX57K dataset. The results demonstrate that our method outperforms previous zero-capable methods and improves the normalized discounted cumulative gain at the top 5 predicted labels (nDCG@5) by 3.0%, 2.4%, 18.9% and 1.0% for overall, frequent, few-shot, and zero-shot labels, respectively.

Automated tuning can significantly improve productivity and save the costs of manual operation in the microwave filter manufacturing industry. This article proposes a mathematical model of scattering data optimization to find the accurate coupling matrix for multiple-version microwave filters, a core step of automated microwave filter tuning. For the large-scale problem of coupling coefficient combination, we propose a decision set decomposition strategy that evenly divides the entire frequency interval into several subintervals according to the correlation between scattering data. With this strategy, we design a microscale (small-size subsets of the decomposed decision set) searching algorithm, which solves each suboptimization problem by searching the decision subset instead of the entire decision set. To verify the validity of the proposed algorithm for multiple-version microwave filters, experiments are conducted on three versions of microwave filters from a real-world production line, including the two-port eighth-order, ninth-order, and tenth-order microwave filters. Experimental results show that the proposed model is feasible within the industrial error for the multiversion microwave filter tuning problem. Besides, the proposed algorithm outperforms the state-of-the-art optimization algorithms in the coupling matrix optimization problem.

Scheduling is significant in improving the production efficiency and reducing delivery delays for manufacturing enterprises. Unlike the flexible job-shop scheduling problem, two special constraints are encountered in real-world power supply manufacturing systems: 1) periodic maintenance and 2) mandatory outsourcing. As the characteristics of these constraints are not considered in existing scheduling algorithms, schedules generated by most existing approaches are not optimal or even conflict with these constraints. In this article, a self-organizing neural scheduler (SoNS) is proposed to overcome this limitation. A long short-term memory encoder is developed to transform the variable-length structural information into fixed-length feature vectors. Moreover, the reinforcement learning model is proposed to automatically select policies for improving candidate schedules. To validate the effectiveness of the proposed algorithm, extensive experiments are conducted on over 300 problem instances. The nonparametric Kruskal-Wallis tests confirm that the proposed algorithm outperforms several state-of-the-art methods in terms of effectiveness and robustness within a limited computational budget. It demonstrates that the proposed SoNS can solve scheduling problems with the periodic maintenance and mandatory outsourcing constraints effectively.

Constrained multiobjective optimization problems widely exist in real-world applications. To handle them, the balance between constraints and objectives is crucial, but remains challenging due to non-negligible impacts of problem types. In our context, the problem types refer particularly to those determined by the relationship between the constrained Pareto-optimal front (PF) and the unconstrained PF. Unfortunately, there has been little awareness on how to achieve this balance when faced with different types of problems. In this article, we propose a new constraint handling technique (CHT) by taking into account potential problem types. Specifically, inspired by the prior work, problems are classified into three primary types: 1) I; 2) II; and 3) III, with the constrained PF being made up of the entire, part and none of the unconstrained counterpart, respectively. Clearly, any problem must be one of the three types. For each possible type, there exists a tailored mechanism being used to handle the relationships between constraints and objectives (i.e., constraint priority, objective priority, or the switch between them). It is worth mentioning that exact problem types are not required because we just consider their possibilities in the new CHT. Conceptually, we show that the new CHT can make a tradeoff among different types of problems. This argument is confirmed by experimental studies performed on 38 benchmark problems, whose types are known, and a real-world problem (with unknown types) in search-based software engineering. Results demonstrate that within both decomposition-based and nondecomposition-based frameworks, the new CHT can indeed achieve a good tradeoff among different problem types, being better than several state-of-the-art CHTs.

Decomposition-based multiobjective evolutionary algorithms (MOEAs) transform a multiobjective optimization problem (MOP) into a set of subproblems and then optimize them collaboratively. When two adjacent objective vectors are similar but the difference in the corresponding decision vectors is large, it is difficult to transfer from a solution of one subproblem to solutions of its neighboring subproblems. In this article, we argue that the key to overcoming this difficulty is the evaluation assignment for different subproblems based on local density and global utility. We propose a local-density measurement model to estimate the solution density around each subproblem. Based on the model, a local-diversity evaluation assignment strategy for the decomposition-based MOEA is designed to assign fitness evaluations among different subproblems. Two discrete MOPs are selected as test instances for experiments because they satisfy the premise that the difference in the corresponding decision vectors of adjacent objective vectors is large. Experimental results indicate that the proposed strategy enhances the population diversity. Besides, the combination of the proposed strategy and the evaluation assignment for high global utility subproblems can overcome the difficulty in transferring from a solution of one subproblem to solutions of its neighboring subproblems. The results also verify that the proposed algorithm significantly outperforms the state-of-the-art evaluation assignment MOEAs regarding the inverted generational distance and the hypervolume metrics.

Real-world software product lines (SPLs) often encompass enormous valid configurations that are impossible to enumerate. To understand properties of the space formed by all valid configurations, a feasible way is to select a small and valid sample set. Even though a number of sampling strategies have been proposed, they either fail to produce diverse samples with respect to the number of selected features (an important property to characterize behaviors of configurations), or achieve diverse sampling but with limited scalability (the handleable configuration space size is limited to 1013). To resolve this dilemma, we propose a scalable diverse sampling strategy, which uses a distance metric in combination with the novelty search algorithm to produce diverse samples in an incremental way. The distance metric is carefully designed to measure similarities between configurations, and further diversity of a sample set. The novelty search incrementally improves diversity of samples through the search for novel configurations. We evaluate our sampling algorithm on 39 real-world SPLs. It is able to generate the required number of samples for all the SPLs, including those which cannot be counted by sharpSAT, a state-of-the-art model counting solver. Moreover, it performs better than or at least competitively to state-of-the-art samplers regarding diversity of the sample set. Experimental results suggest that only the proposed sampler (among all the tested ones) achieves scalable diverse sampling.

Two-echelon vehicle routing problem (2E-VRP) is an NP-hard combinatorial optimization problem and a basic mathematical model of modern city logistics. While it is difficult to obtain the optimal solution of 2E-VRP, this study finds a breakthrough that the structure of the optimal route planning for 2E-VRP is usually an embedded Hamiltonian graph. In the graph, routes can be drawn in a planar graph as Hamiltonian circuits without intersections. Based on this finding, an embedded Hamiltonian graph-guided heuristic algorithm is proposed to solve 2E-VRP. As a crucial part of the algorithm, an initialization scheme is designed to search for the farthest vertices from each route and insert the rest of the vertices. In the satellite-adjustment process, a dynamic adjustment for satellites scheme is proposed to adjust the state of satellites. The two schemes aim to construct Hamiltonian circuits with few intersections. Experiments have been conducted on 207 instances to demonstrate the effect of the proposed algorithm on solving 2E-VRP. Experimental results show that the proposed algorithm can obtain more solutions of 2E-VRP with significantly smaller objective-function values. Furthermore, the number of intersections in routes generated by the proposed algorithm is much less than those obtained by the compared algorithms. With the use of the two schemes, the embedded Hamiltonian graph-guided heuristic algorithm significantly outperforms the compared algorithms for 2E-VRP.

Testing software product lines (SPLs) is difficult due to a huge number of possible products to be tested. Recently, there has been a growing interest in similarity-based testing of SPLs, where similarity is used as a surrogate metric for the$t$-wise coverage. In this context, one of the primary goals is to sample, by optimizing similarity metrics using search-based algorithms, a small subset of test cases (i.e., products) as dissimilar as possible, thus potentially making more$t$-wise combinations covered. Prior work has shown, by means of empirical studies, the great potential of current similarity-based testing approaches. However, the rationale of this testing technique deserves a more rigorous exploration. To this end, we perform correlation analyses to investigate how similarity metrics are correlated with the$t$-wise coverage. We find that similarity metrics generally have significantly positive correlations with the$t$-wise coverage. This well explains why similarity-based testing works, as the improvement on similarity metrics will potentially increase the$t$-wise coverage. Moreover, we explore, for the first time, the use of the novelty search (NS) algorithm for similarity-based SPL testing. The algorithm rewards “novel” individuals, i.e., those being different from individuals discovered previously, and this well matches the goal of similarity-based SPL testing. We find that the novelty score used in NS has (much) stronger positive correlations with the$t$-wise coverage than previous approaches relying on a genetic algorithm (GA) with a similarity-based fitness function. Experimental results on 31 software product lines validate the superiority of NS over GA, as well as other state-of-the-art approaches, concerning both$t$-wise coverage and fault detection capacity. Finally, we investigate whether it is useful to combine two satisfiability solvers when generating new individuals in NS, and how the performance of NS is affected by its key parameters. In summary, looking for novelty provides a promising way of sampling diverse test cases for SPLs.

This paper addresses a class of optimization problems in which either part of the objective function is differentiable while the rest is nondifferentiable or the objective function is differentiable in only part of the domain. Accordingly, we propose a dual-decomposition-based approach that includes both objective decomposition and domain decomposition. In the former, the original objective function is decomposed into several relatively simple subobjectives to isolate the nondifferentiable part of the objective function, and the problem is consequently formulated as a multiobjective optimization problem (MOP). In the latter decomposition, we decompose the domain into two subdomains, that is, the differentiable and nondifferentiable domains, to isolate the nondifferentiable domain of the nondifferentiable subobjective. Subsequently, the problem can be optimized with different schemes in the different subdomains. We propose a population-based optimization algorithm, called the simulated water-stream algorithm (SWA), for solving this MOP. The SWA is inspired by the natural phenomenon of water streams moving toward a basin, which is analogous to the process of searching for the minimal solutions of an optimization problem. The proposed SWA combines the deterministic search and heuristic search in a single framework. Experiments show that the SWA yields promising results compared with its existing counterparts.

Running time analysis is a fundamental problem of critical importance in evolutionary computation. However, the analysis results have rarely been applied to advanced evolutionary algorithms (EAs) in practice, let alone their variants for continuous optimization. In this paper, an experimental method is proposed for analyzing the running time of EAs that are widely used for solving continuous optimization problems. Based on Glivenko-Cantelli theorem, the proposed method simulates the distribution of gain, which is introduced by average gain model to characterize progress during the optimization process. Data fitting techniques are subsequently adopted to obtain a desired function for further analyses. To verify the validity of the proposed method, experiments were conducted to estimate the upper bounds on expected first hitting time of various evolutionary strategies, such as (1, $\lambda $ ) evolution strategy, standard evolution strategy, covariance matrix adaptation evolution strategy, and its improved variants. The results suggest that all estimated upper bounds are correct. Backed up by the proposed method, state-of-the-art EAs for continuous optimization will have identical results about the running time as simplified schemes, which will bridge the gap between theoretical foundation and applications of evolutionary computation.

This paper integrates an estimation of distribution (EoD)-based update operator into decomposition-based multiobjective evolutionary algorithms for binary optimization. The probabilistic model in the update operator is a probability vector, which is adaptively learned from historical information of each subproblem. We show that this update operator can significantly enhance decomposition-based algorithms on a number of benchmark problems. Moreover, we apply the enhanced algorithms to the constrained optimal software product selection (OSPS) problem in the field of search-based software engineering. For this real-world problem, we give its formal definition and then develop a new repair operator based on satisfiability solvers. It is demonstrated by the experimental results that the algorithms equipped with the EoD operator are effective in dealing with this practical problem, particularly for large-scale instances. The interdisciplinary studies in this paper provide a new real-world application scenario for constrained multiobjective binary optimizers and also offer valuable techniques for software engineers in handling the OSPS problem.

We propose a new many-objective evolutionary algorithm with Pareto-adaptive reference points. In this algorithm, the shape of the Pareto-optimal front (PF) is estimated based on a ratio of Euclidean distances. If the estimated shape is likely to be convex, the nadir point is used as the reference point to calculate the convergence and diversity indicators for individuals. Otherwise, the reference point is set to the ideal point. In addition, the estimation of the nadir point is different from what was widely used in the literature. The nadir point, together with the ideal point, provides a feasible way to deal with dominance resistant solutions, which are difficult to be detected and eliminated in Pareto-based algorithms. The proposed algorithm is compared with the state-of-the-art many-objective optimization algorithms on a number of unconstrained and constrained test problems with up to 15 objectives. The experimental results show that it performs better than other algorithms in most of the test instances. Moreover, the new algorithm shows good performance on problems whose PFs are irregular (being discontinuous, degenerated, bent, or mixed). The observed high performance and inherent good properties (such as being free of weight vectors and control parameters) make the new proposal a promising tool for other similar problems.

Two-echelon vehicle routing problem (2E-VRP) is a challenging problem that involves both the strategic and tactical planning decisions on both echelons. The satellite locations and the customer distribution affect the cost of different components on the second echelon, thus the possibilities of satellite-to-customer assignment complicates the problem. In this paper, we propose a graph-based fuzzy evolutionary algorithm for solving 2E-VRP. The proposed method integrates a graph-based fuzzy assignment scheme into an iteratively evolutionary learning process to minimize the total cost. To resolve the possibilities of the satellite-to-customer assignment, graph-based fuzzy operator is used to take advantage of population evolution and avoid excessive fitness evaluations of unpromising moves in different satellites. Each offspring is produced via graph-based fuzzy assignment procedure out of an assignment graph from parent individuals, and fuzzy local search procedure is used to further improve the offspring. The experimental results on the public test sets demonstrate the competitiveness of the proposed method.

Periodic vehicle routing problem with time windows (PVRPTWs) is an important combinatorial optimization problem that can be applied in different fields. It is essentially a multiobjective optimization problem due to the problem nature. In this paper, a typical multiobjective PVRPTW with five objectives is first defined and new nonsymmetric real-world multiobjective PVRPTW instances are generated. Then, a hybrid multiobjective memetic algorithm is proposed for solving multiobjective PVRPTW. In the proposed algorithm, a two-phase strategy is devised to improve the comprehensive performance in terms of the convergence and diversity. In this strategy, several extreme solutions near an approximate Pareto front (PF) are identified at Phase I, and then the approximate PF is extended at Phase II. The proposed algorithm is extensively tested on both real-world instances and traditional instances. Experiment results show that the proposed algorithm outperforms two representative competitor algorithms on most of the instances. The effectiveness of the two-phase strategy is also confirmed.

The surprisingly popular decision in social science fields is a wisdom of the crowd technique that taps into the expert minority opinion within a crowd, which has been demonstrated to be remarkably effective for multiple questions. Most of the existing PSO variants construct the exemplars by solely using fitness, which could be viewed as the democratic approaches or methods. However, the democratic methods tend to highlight the most popular opinion, not necessarily the most correct, which might lead the population into a local trapping region in the scenarios of swarm intelligent computing and evolutionary computation. This paper proposes a method to implement the surprisingly popular decision in PSO to facilitate the exemplar construction, cooperating with the dynamic topology maintenance. The proposed PSO variant is called the Surprisingly Popular Algorithm-based Comprehensive Adaptive Topology Learning Particle Swarm Optimization (SPA-CatlePSO). By using the dynamic topological connection and surprisingly popular decision strategy, the proposed SPA-CatlePSO could adjust the degree of small world topology, mimicking the mechanism of knowledge conversion in the crowd, and guide the direction of the exploitation by constructing exemplars with the largest surprisingly popular degree. We evaluate the proposed SPA-CatlePSO on the full CEC2014 benchmark suite and compare its validity with OLPSO, TSLPSO, ASDPSO, HCLPSO, OptBees and L-shade. The experimental results show that the SPA-CatlePSO algorithm is competitive with the most advanced swarm-based intelligent algorithms.

The pigeon-inspired optimization (PIO) algorithm is a novel swarm intelligence optimizer inspired by the homing behaviors of pigeons. Although PIO has demonstrated effectiveness and superiority in numerous fields, there are few results about the theoretical foundation of PIO. This paper employs the average gain model to estimate the upper bound for the expected first hitting time of PIO in continuous optimization. The case study and experiment result indicate that our theoretical analysis is applicable to the general case where the population size and problem size are both larger than 1, which is close to the practical situation.

Image retrieval in complicated scene is a challenging task that requires the comprehensive understanding of an image. In this paper, we propose a scene graph based image retrieval framework that combines the scene graph generation with image retrieval and fine tuning the searching results via a dialogue mechanism. Specifically, we proposed an image retrieval oriented scene graph generation model that takes an image and a text describing the image as inputs. The additional text input is used to control the generated scene graph. It provides information for a newly introduced attributes head to better predict the attributes and helps constructing an adjacency matrix at the same time. Graph Convolutional Network is further used to gather information among nodes for precise relation estimation. Moreover, modification on the scene graph can be done by changing the text. Our proposed approach achieves the state-of-the-art performances in both scene graph based image retrieval and scene graph generation in the Visual Genome dataset.

Image matting is evolving for a wide range of applications including image/video editing. Sampling-based image matting aims to estimate the opacity of foreground objects by properly selecting a pair of foreground and background pixels for every unknown pixel. Sampling-based image matting is essentially an uncertain multicriteria optimization problem (UMCOP). It shows unique advantages in parallelization and handling spatially disconnected regions. However, sampling-based approaches encounter difficulty in accurately evaluating pixel pairs and efficiently optimizing the large-scale UMCOP. To address these two problems, a fuzzy multicriteria evaluation (FMCE) and a multiobjective evolutionary algorithm based on multicriteria decomposition (MOEA-MCD) are proposed. We model three fuzzy membership functions for three selection criteria and aggregate them by Einstein and averaging operators providing FMCE for pixel pairs. MOEA-MCD uses the heuristic information for each criterion by multicriteria decomposition that divides the single objective into multiple objectives and optimizes them simultaneously using a multiobjective optimizer with neighborhood grouping strategy. Experimental results show that FMCE accurately evaluates pixel pairs even in uncertain cases with low satisfaction degree of some evaluation criteria, and the heuristic information for each criterion enhances the population diversity of MOEA-MCD. MOEA-MCD outperforms state-of-the-art large-scale optimization approaches and sampling-based image matting approaches.

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.

In sampling-based matting methods, the alpha is estimated by choosing the best pair of foreground and background color samples. The lack of true samples is the major obstacle in obtaining high-quality alpha mattes. Regrettably, several proposed approaches did not address the conflicts among multiple sampling criteria and the effects of incomplete sample spaces. To address this issue, we propose a pixel-level discrete multiobjective sampling (PDMS) method. The color sampling process at each unknown pixel is formalized as a multiobjective optimization problem (MOP). The strength of PDMS includes its ability to minimize both color difference and spatial distance between unknown and known pixels, and its capacity to adaptively make trade-offs among conflicting sampling criteria. To mitigate the effects of incomplete sample spaces, the sample space is extended to complete known regions in PDMS, which means that the colors of all known pixels can be sampled, instead of mean colors of superpixels. Our experimental results show that PDMS collects a small set of samples while achieving smaller minimum absolute difference in alpha estimation. Moreover, PDMS implements pixel-level sampling by using the proposed multiobjective optimization algorithm to efficiently solve sampling MOPs. The PDMS-based matting method provides high-quality alpha mattes with sharp boundaries and thus outperforms those prior image matting methods in terms of gradient error.

In this paper, a video abstract system based on spatial-temporal neighborhood trajectory analysis algorithm which is mainly used to process surveillance videos is proposed. The algorithm uses the spatial adjacency of foreground targets and tracks the spatial-temporal neighboring moving targets to get their whole trajectories in order to meet the requirement of processing speed and accuracy. The indicators consist of trajectory detection rate, trajectory tracking average continuity and video abstract processing speed are used to evaluate the effectiveness of the system. We compare the algorithm with the other three algorithms, and the results show that spatial-temporal neighborhood trajectory analysis algorithm has sufficient trajectory detection rate and processing speed for surveillance video abstraction.

Fog computing plays an important role in industrial and information process. The programs in fog computing, such as iFogSim toolkit, usually contain some infeasible paths (paths that cannot be covered), which makes it impossible to compare algorithm in models that require covering all paths. In this paper, we proposed a mathematical model to build automated test case generation based on path coverage (ATCG-PC) in fog computing programs as a single-objective problem. Single objective helps to reduce the cost of evaluation functions, which is proportional to the number of test cases. When infeasible paths are contained in tested programs, algorithms can also be compared in this model. In this paper, classical differential evolution (DE) is used to solve the ATCG-PC. However, it is difficult for DE to use generated test cases covering remaining paths in the ATCG-PC of fog computing. Therefore, we proposed a test-case-path relationship matrix to empower DE (RP-DE). Experiment results show that RP-DE uses significantly less test cases and achieves higher path coverage rate than compared state-of-the-art algorithms.

Software testing is an important process of software development. One of the challenges in testing software is to generate test cases which help to reveal errors. Automated software test data generation problem is hard because it needs to search the whole feasible area to find test cases covering all possible paths under acceptable time consumption. In this paper, evolutionary algorithm with convergence speed controller (EA-CSC) is presented for using the least test case overhead in solving automated test case generation problem. EA-CSC is designed as a framework which have fast convergence speed and capability to jump out of the local optimal solution over a range of problems. There are two critical steps in EA-CSC. The adaptive step size searching method accelerates the convergence speed of EA. The mutation operator can disrupt the population distribution and slows down the convergence process of EA. Moreover, the EA-CSC results are compared to the algorithms tested on the same benchmark problems, showing strong competitive.

This paper presents a human-computer cooperative brain storm optimization algorithm, which is based on an improved brain storm optimization algorithm with human intelligence in computer game. In our algorithm, the initial population is provided with some better ideas obtained by computer game. Moreover, converging operation and diverging operation also employ the solutions from different players to generate ideas during evolution process. With the help of human-machine cooperation, our algorithm, integrating strategy development capabilities of players with brain storm optimization algorithm, is applied to solve some complex optimized problems. We apply the proposed method to two-echelon vehicle routing problem to verify its effectiveness and usefulness.

Nurse Rostering Problem (NRP) is one of NP - hard combinatorial optimization problems about the distribution of medical resources. In the past, there have been several proposed methods like heuristic algorithms and algorithms based on establishing rigorous mathematical models. Especially, the hybrid algorithm combined integer programming and evolutionary algorithm (IP+EA) have been proved to be effective for NRP. However, these methods are not efficient in dealing with large-scale NPR instances, like Chinese NRP. In order to overcome the premature convergence of IP+EA, we propose a hybrid evolutionary algorithm based on scout bee global search strategy. Inspired by the behavior of scouts in artificial bee colony algorithms, the global search is integrated into EA, which can lead the algorithm to escape from local optima. The experimental results indicate that, our proposed approach is more effective than several existing algorithms to solve the Chinese NRP.

Particle swarm optimization (PSO) has been shown as an effective tool for solving single objective optimization problems. However, premature convergence is the major obstacle for PSO. So far, many PSO variants have been proposed to prevent premature convergence. Nonetheless, even though some strategies have been adopted for avoiding premature convergence, PSO variants could not achieve all great performance. In this paper, we introduce an adaptive general framework to enhance the performance of PSO variants, convergence speed controller with an adaptive diversity control strategy (CSC-ADCS). With the aim to maintain the convergence speed and prevent premature convergence, CSC will conditionally detect the status of Swarm. And ADCS is introduced so that the conditions are adaptive on the basis of the diversity of swarm. Once the CSC framework detects that premature convergence occurs, two rules would help the swarm to get rid of the abnormal status. The experimental results conducted on CEC'2013 benchmark functions show that with the help of adaptive CSC framework, PSO variants with CSC-ADCS will get better results than ones without CSC-ADCS.

Differential Evolution (DE) has been widely used as a continuous optimization technique for several problems like electromagnetic optimization, bioprocess system optimization and so on. However, during the optimization process, DE's population may stagnate local optima where the algorithm has to spend a large number of function evaluations to get rid of them. This paper presents an improved DE algorithm (denoted as RSDE) which combines two Replacement Strategies (RS). The motivation of RS is that replacing an unimproved individual and replacing a premature population using RS which can enhance the DE exploitation performance and exploration performance respectively. We tested the RSDE performance using the newly Single Objective Real-Parameter Numerical Optimization problems provided by the CEC 2014 Special Session and Competition. Moreover, computational results, convergence figures and the performance of these two RS will be presented to discuss the feature of RSDE.

Ant colony optimization (ACO) has widely been applied to solve combinatorial optimization problems in recent years. There are few studies, however, on its convergence time, which reflects how many iteration times ACO algorithms spend in converging to the optimal solution. Based on the absorbing Markov chain model, we analyze the ACO convergence time in this paper. First, we present a general result for the estimation of convergence time to reveal the relationship between convergence time and pheromone rate. This general result is then extended to a two-step analysis of the convergence time, which includes the following: 1) the iteration time that the pheromone rate spends on reaching the objective value and 2) the convergence time that is calculated with the objective pheromone rate in expectation. Furthermore, four brief ACO algorithms are investigated by using the proposed theoretical results as case studies. Finally, the conclusions of the case studies that the pheromone rate and its deviation determine the expected convergence time are numerically verified with the experiment results of four one-ant ACO algorithms and four ten-ant ACO algorithms.