Code smells signal poor software design that can prevent maintainability and scalability. Identifying code smells is difficult because of the large volume of code, considerable detection expenses, and the substantial effort needed for manual tagging. Although current techniques perform well in within-project situations, they frequently struggle to adapt to cross-project environments that have varying data distributions. In this paper, we introduce CLADES (Cross-project Learning and Adaptation for Detection of Code Smells), a hybrid evolutionary approach consisting of three main modules: Initialization, Evolution, and Adaptation. The first module generates an initial population of decision tree detectors using labeled within-project data and evaluates their quality through fitness functions based on structural code metrics. The evolution module applies genetic operators (selection, crossover, and mutation) to create new offspring solutions. To handle cross-project scenarios, the adaptation module employs a clustering-based instance selection technique that identifies representative instances from new projects, which are added to the dataset and used to repair the decision trees through simulated annealing. These locally refined decision trees are then evolved using a genetic algorithm, thus enabling continuous adaptation to new project instances. The resulting optimized decision tree detectors are then employed to predict labels for the new unlabeled project instances. We assess CLADES across five open-source projects and we show that it has a better performance with respect to baseline techniques in terms of weighted F1-score and AUC-PR metrics. These results emphasize its capacity to effectively adjust to different project environments, facilitating precise and scalable detection of code smells while minimizing the need for manual review, contributing to more robust and maintainable software systems.

Supervised machine learning techniques include classification and regression. In regression, the objective is to map a real-valued output to a set of input features. The main challenge that existing methods for regression encounter is how to maintain an accuracy-simplicity balance. Since Regression Trees (RTs) are simple to interpret, many existing works have focused on proposing RT and Model Tree (MT) induction algorithms. MTs are RTs with a linear function at the leaf nodes rather than a numerical value are able to describe the relationship between the inputs and the output. Traditional RT induction algorithms are based on a top-down strategy which often leads to a local optimal solution. Other global approaches based on Evolutionary Algorithms (EAs) have been proposed to induce RTs but they can require an important calculation time which may affect the convergence of the algorithm to the solution. In this paper, we introduce a novel approach called Bi-level Evolutionary Model Tree Induction algorithm for regression, that we call BEMTI, and which is able to induce an MT in a bi-level design using an EA. The upper-level evolves a set of MTs using genetic operators while the lower-level optimizes the Linear Models (LMs) at the leaf nodes of each MT in order to fairly and precisely compute their fitness and obtain the optimal MT. The experimental study confirms the outperformance of our BEMTI compared to six existing tree induction algorithms on nineteen datasets.

Malicious apps use various methods to spread viruses, take control of computers and/or IoT devices, and steal sensitive data such as credit card numbers or other personal information. Despite the numerous existing means of intrusion detection, malware code is not easily detectable. The primary issue with current malware detection approaches is their inability to identify novel attacks and obfuscated malware, as they rely on static bases of malware examples, making them susceptible to new unseen malware behaviors. To address this, we propose a new method for malware recognition, which consists of two processes: the first process creates new instances of malware using a memetic algorithm, and the second process detects these new instances of attacks through solid detectors produced by an artificial immune system-based algorithm. Our new malware recognition method has proven its merits through thorough experiments on widely used datasets and evaluation metrics, and has been compared to prominent state-of-the-art methods.

Feature construction represents a crucial data preprocessing technique in machine learning applications because it ensures the creation of new informative features from the original ones. This fact leads to the improvement of the classification performance and the reduction of the problem dimensionality. Since many feature construction methods require discrete data, it is important to perform discretization in order to transform the constructed features given in continuous values into their corresponding discrete versions. To deal with this situation, the aim of this paper is to jointly perform feature construction and feature discretization in a synchronous manner in order to benefit from the advantages of each process. Thus, we propose here to model the discretization-based feature construction task as a bi-level optimization problem in which the constructed features are evaluated based on their optimized sequence of cut-points. The resulting algorithm is termed Discretization-Based Feature Construction (Bi-DFC) where the proposed model is solved using an improved version of an existing co-evolutionary algorithm, named I-CEMBA that ensures the variation of concatenation trees. Bi-DFC performs the selection of original attributes at the upper level and ensures the creation and the evaluation of constructed features at the upper level based on their optimal corresponding sequence of cut-points. The obtained experimental results on ten high-dimensional datasets illustrate the ability of Bi-DFC in outperforming relevant state-of-the-art approaches in terms of classification results.

Hierarchical decision-making can be observed in different research areas where two optimization levels define a bilevel optimization problem. For instance, in a supply chain production and distribution problem, two decision-makers control these processes respectively, where one company is dedicated only to the distribution of the products, and the other is dedicated to the production of these products. This kind of problem is considered challenging. This work is then on the solution of the Bilevel Multi-Depot Vehicle Routing Problem (BiMDVRP), in which multiple depots need to deliver cargo to cover the demand of many retailers subject to the production plants to meet the demand of each depot optimally. A hybrid genetic algorithm to solve the aforementioned bilevel planning problem is proposed in this work. We use the available information on the problem to implement heuristic mechanisms to improve the results reported by state-of-the-art algorithms. We propose a representation based on groups for the feasible configuration of each depot, due to constraints related to a depot being satisfied. The experimental results show that group-based coding quickly obtains high-quality solutions for the set of instances used in our experimentation setup.

Discretization-based feature selection (DBFS) approaches have shown interesting results when using several metaheuristic algorithms, such as particle swarm optimization (PSO), genetic algorithm (GA), ant colony optimization (ACO), etc. However, these methods share the same shortcoming which consists in encoding the problem solution as a sequence of cut-points. From this cut-points vector, the decision of deleting or selecting any feature is induced. Indeed, the number of generated cut-points varies from one feature to another. Thus, the higher the number of cut-points, the higher the probability of selecting the considered feature; and vice versa. This fact leads to the deletion of possibly important features having a single or a low number of cut-points, such as the infection rate, the glycemia level, and the blood pressure. In order to solve the issue of the dependency relation between the feature selection (or removal) event and the number of its generated potential cut-points, we propose to model the DBFS task as a bilevel optimization problem and then solve it using an improved version of an existing co-evolutionary algorithm, named I-CEMBA. The latter ensures the variation of the number of features during the migration process in order to deal with the multimodality aspect. The resulting algorithm, termed bilevel discretization-based feature selection (Bi-DFS), performs selection at the upper level while discretization is done at the lower level. The experimental results on several high-dimensional datasets show that Bi-DFS outperforms relevant state-of-the-art methods in terms of classification accuracy, generalization ability, and feature selection bias.

Cost-sensitive learning is one of the most adopted approaches to deal with data imbalance in classification. Unfortunately, the manual definition of misclassification costs is still a very complicated task, especially with the lack of domain knowledge. To deal with the issue of costs' uncertainty, some researchers proposed the use of intervals instead of scalar values. This way, each cost would be delimited by two bounds. Nevertheless, the definition of these bounds remains as a very complicated and challenging task. Recently, some researches proposed the use of genetic programming to simultaneously build classification trees and search for optimal costs' bounds. As for any classification tree there is a whole search space of costs' bounds, we propose in this paper a bi-level evolutionary approach for interval-based cost-sensitive classification tree induction where the trees are constructed at the upper level while misclassification costs intervals bounds are optimized at the lower level. This ensures not only a precise evaluation of each tree but also an effective approximation of optimal costs intervals bounds. The performance and merits of our proposal are shown through a detailed comparative experimental study on commonly used imbalanced benchmark data sets with respect to several existing works.

To offer innovative malware evolution techniques, it is appealing to integrate approaches that handle imperfect data and knowledge.In fact, malware writers tend to target some precise features within the app's code to camouflage the malicious content.Those features may sometimes present conflictual information about the true nature of the content of the app (malicious/benign).In this paper, we show how the Variable Precision Rough Set (VPRS) model can be combined with optimization techniques, in particular Bilevel-Optimization-Problems (BLOPs), in order to establish a detection model capable of following the crazy race of malware evolution initiated among malware-developers.We propose a new malware detection technique, based on such hybridization, named Variable Precision Rough set Malware Detection (ProRSDet), that offers robust detection rules capable of revealing the new nature of a given app.ProRSDet attains encouraging results when tested against various state-of-the-art malware detection systems using common evaluation metrics.

Like the case of any software, Web Services (WSs) developers could introduce anti-patterns due to the lack of experience and badly-planned changes. During the last decade, search-based approaches have shown their outperformance over other approaches mainly thanks to their global search ability. Unfortunately, these approaches do not consider the uncertainty of class labels. In fact, two experts could be uncertain about the smelliness of a particular WS interface but also about the smell type. Currently, existing works reject uncertain data that correspond to WSs interfaces with doubtful labels. Motivated by this observation and the good performance of the possibilistic K-NN classifier in handling uncertain data, we propose a new evolutionary detection approach, named Web Services Anti-patterns Detection and Identification using Possibilistic Optimized K-NNs (WS-ADIPOK), which can cope with the uncertainty based on the Possibility Theory. The obtained experimental results reveal the merits of our proposal regarding four relevant state-of-the-art approaches.

A code smells detection rule is a combination of metrics with their corresponding crisp thresholds and labels. The goal of this paper is to deal with metrics' thresholds uncertainty; as usually such thresholds could not be exactly determined to judge the smelliness of a particular software class. To deal with this issue, we first propose to encode each metric value into a binary possibility distribution with respect to a threshold computed from a discretization technique; using the Possibilistic C-means classifier. Then, we propose ADIPOK-UMT as an evolutionary algorithm that evolves a population of PK-NN classifiers for the detection of smells under thresholds' uncertainty. The experimental results reveal that the possibility distribution-based encoding allows the implicit weighting of software metrics (features) with respect to their computed discretization thresholds. Moreover, ADIPOK-UMT is shown to outperform four relevant state-of-art approaches on a set of commonly adopted benchmark software systems.

Feature selection and construction are important pre-processing techniques in data mining. They allow not only dimensionality reduction but also classification accuracy and efficiency improvement. While feature selection consists in selecting a subset of relevant features from the original feature set, feature construction corresponds to the generation of new high-level features, called constructed features, where each one of them is a combination of a subset of original features. However, different features can have different abilities to distinguish different classes. Therefore, it may be more difficult to construct a better discriminating feature when combining features that are relevant to different classes. Based on these definitions, feature construction could be seen as a BLOP (Bi-Level optimization Problem) where the feature subset should be defined in the upper level and the feature construction is applied in the lower level by performing mutliple followers, each of which generates a set class dependent constructed features. In this paper, we propose a new bi-level evolutionary approach for feature construction called BCDFC that constructs multiple features which focuses on distinguishing one class from other classes using Genetic Programming (GP). A detailed experimental study has been conducted on six high-dimensional datasets. The statistical analysis of the obtained results shows the competitiveness and the outperformance of our bi-level feature construction approach with respect to many state-of-art algorithms.

Decomposition-based evolutionary algorithms using predefined reference points have shown good performance in many-objective optimization. Unfortunately, almost all experimental studies have focused on problems having regular Pareto fronts (PFs). Recently, it has been shown that the performance of such algorithms is deteriorated when facing irregular PFs, such as degenerate, discontinuous, inverted, strongly convex, and/or strongly concave fronts. The main issue is that the predefined reference points may not all intersect with the PF. Therefore, many researchers have proposed to update the reference points with the aim of adapting them to the discovered Pareto shape. Unfortunately, the adaptive update does not really solve the issue for two main reasons. On the one hand, there is a considerable difficulty to set the time and the frequency of updates. On the other hand, it is not easy to define how to update the search directions for an unknown PF shape. This article proposes to approximate irregular PFs using a set of predefined normal-boundary intersection (NBI) directions. The main motivation behind this article is that when using a set of well-distributed NBI directions, all these directions intersect with the PF regardless of its shape, except for the case of discontinuous and/or degenerate fronts. To handle the latter cases, a simple interaction mechanism between the decision maker (DM) and the algorithm is used. In fact, the DM is asked if the number of NBI directions needs to be increased in some stages of the evolutionary process. If so, the resolution of the NBI directions that intersect the PF is increased to properly cover discontinuous and/or degenerate PFs. Our experimental results on benchmark problems with regular and irregular PFs, having up to fifteen objectives, show the merits of our algorithm when compared to eight of the most representative state-of-the-art algorithms.

Bi-clustering is one of the main tasks in data mining with several application domains. It consists in partitioning a data set based on both rows and columns simultaneously. One of the main difficulties in bi-clustering is the issue of finding the number of bi-clusters, which is usually a user-specified parameter. Recently, in 2017, a new multi-objective evolutionary clustering algorithm, called MOCK-II, has shown its effectiveness in data clustering while automatically determining the number of clusters. Motivated by the promising results of MOCK-II, we propose in this paper a hybrid extension of this algorithm for the case of bi-clustering. Our new algorithm, called MOBICK, uses an efficient solution encoding, an effective crossover operator, and a heuristic mutation strategy. Similarly to MOCK-II, MOBICK is able to find automatically the number of bi-clusters. The outperformance of our algorithm is shown on a set of real gene expression data sets against several existing state-of-the-art works. Moreover, to be able to compare MOBICK to MOCK-I and MOCK-II, we have designed two basic extensions of MOCK-I and MOCK-II for the case of bi-clustering that we named B-MOCK-I and B-MOCK-II. Again, the experimental results confirm the merits of our proposal.

Feature selection and construction are important pre-processing techniques in machine learning and data mining. They may allow not only dimensionality reduction but also classifier accuracy and efficiency improvement. Feature selection aims at selecting relevant features from the original feature set, which could be less informative to achieve good performance. Feature construction may work well as it creates new highlevel features, but these features do not have the same degree of importance, which makes the use of weighted-features construction a very challenging topic. In this paper, we propose a bi-level evolutionary approach for efficient feature selection and simultaneous feature construction and feature weighting, called Bi-level Weighted-Features Construction (BWFC). The basic idea of our BWFC is to exploit the bi-level model for performing feature selection and weighted-features construction with the aim of finding an optimal subset of features combinations. Our approach has been assessed on six high-dimensional datasets and compared against three existing approaches, using three different classifiers for accuracy evaluation. Experimental results show that our proposed algorithm gives competitive and better results with respect to the state-of-the-art algorithms.

Classification of imbalanced data is a challenging issue in the interpretation of remote sensing images. In a majority class (negatives), there are much more pixels than in a minority class (positives). This imbalanced data makes the classification extremely difficult to produce higher accuracy. The sampling technique is one of techniques, which work well for many pattern data, but not for remote sensing images. The Fast Box algorithm (FBA) which uses the clustering algorithm was then proposed to characterize and discriminate the minority class from the majority class by determining the decision boundaries of the minority data. The FBA performs well in most pattern datasets; however, it fails to recognize the minority class properly in remote sensing images. In this study, we propose a new Constrained Box Algorithm (CBA), which can effectively detect the minority class within remote sensing images. The FBA often misclassifies negatives as positives, CBA eliminates this issue by restricting the maximum number of allowed positives within a box. Our new algorithm finds the minority class by an iterative process of discovering appropriate boundaries using clustering and eliminating majority instances from initial boundaries. A threshold is used to guide the search process to find acceptable boundaries. The set of accepted boundaries are then used to discover the minority class. Experimental results demonstrates that the minority class was correctly detected in satellite images.

Feature selection and construction are important pre-processing techniques in data mining. They may allow not only dimensionality reduction but also classifier accuracy and efficiency improvement. These two techniques are of great importance especially for the case of high-dimensional data. Feature construction for high-dimensional data is still a very challenging topic. This can be explained by the large search space of feature combinations, whose size is a function of the number of features. Recently, researchers have used Genetic Programming (GP) for feature construction and the obtained results were promising. Unfortunately, the wrapper evaluation of each feature subset, where a feature can be constructed by a combination of features, is computationally intensive since such evaluation requires running the classifier on the data sets. Motivated by this observation, we propose, in this paper, a hybrid multiobjective evolutionary approach for efficient feature construction and selection. Our approach uses two filter objectives and one wrapper objective corresponding to the accuracy. In fact, the whole population is evaluated using two filter objectives. However, only non-dominated (best) feature subsets are improved using an indicator-based local search that optimizes the three objectives simultaneously. Our approach has been assessed on six high-dimensional datasets and compared with two existing prominent GP approaches, using three different classifiers for accuracy evaluation. Based on the obtained results, our approach is shown to provide competitive and better results compared with two competitor GP algorithms tested in this study.

Multiobjective evolutionary algorithms (MOEAs) have proven their effectiveness and efficiency in solving problems with two or three objectives. However, recent studies show that MOEAs face many difficulties when tackling problems involving a larger number of objectives as their behavior becomes similar to a random walk in the search space since most individuals are nondominated with respect to each other. Motivated by the interesting results of decomposition-based approaches and preference-based ones, we propose in this paper a new decomposition-based dominance relation to deal with many-objective optimization problems and a new diversity factor based on the penalty-based boundary intersection method. Our reference point-based dominance (RP-dominance), has the ability to create a strict partial order on the set of nondominated solutions using a set of well-distributed reference points. The RP-dominance is subsequently used to substitute the Pareto dominance in nondominated sorting genetic algorithm-II (NSGA-II). The augmented MOEA, labeled as RP-dominance-based NSGA-II, has been statistically demonstrated to provide competitive and oftentimes better results when compared against four recently proposed decomposition-based MOEAs on commonly-used benchmark problems involving up to 20 objectives. In addition, the efficacy of the algorithm on a realistic water management problem is showcased.

During the few past years, decomposition has shown a high performance in solving Multi-objective Optimization Problems (MOPs) involving more than three objectives, called as Many-objective Optimization Problems (MaOPs). The performance of most of the existing decomposition-based algorithms has been assessed on the widely used DTLZ and WFG unconstrained test problems. However, the number of works that have been devoted to tackle the problematic of constrained many-objective optimization is relatively very small when compared to the number of works handling the unconstrained case. Recently there has been some interest to exploit infeasible isolated solutions when solving Constrained MaOPs (CMaOPs). Motivated by this observation, we firstly propose an IS-update procedure (Isolated Solution-based update procedure) that has the ability to: (1) handle CMaOPs characterized by various types of difficulties and (2) favor the selection of not only infeasible solutions associated to isolated sub-regions but also infeasible solutions with smaller Constraint Violation (CV) values. The IS-update procedure is subsequently embedded within the Multi-Objective Evolutionary Algorithm-based on Decomposition (MOEA/D). The new obtained algorithm, named ISC-MOEA/D (Isolated Solution-based Constrained MOEA/D), has been shown to provide competitive and better results when compared against three recent works on the CDTLZ benchmark problems.

Bi-level optimization problems (BOPs) are a class of challenging problems with two levels of optimization tasks. The main goal is to optimize the upper level problem which has another optimization problem as a constraint. In these problems, the optimal solutions to the lower level problem become possible feasible candidates to the upper level one. Such a requirement makes the optimization problem difficult to solve, and has kept the researchers busy towards devising methodologies, which can efficiently handle the problem. Recently, a new research field, called EBO (Evolutionary Bi-Level Optimization) has appeared thanks to the promising results obtained by the use of EAs (Evolutionary Algorithms) to solve such kind of problems. However, most of these promising results are restricted to the continuous case. The number of existing EBO works for the discrete (combinatorial case) bi-level problems is relatively small when compared to the field of evolutionary continuous BOP. Motivated by this observation, we have recently proposed a Co-evolutionary Decomposition-Based Algorithm (CODBA) to solve combinatorial bi-level problems. The recently proposed approach applies a Genetic Algorithm to handle BOPs. Besides, a new recently proposed meta-heuristic called CRO has been successfully applied to several practical NP-hard problems. To this end, we propose in this work a CODBA-CRO (CODBA with Chemical Reaction Optimization) to solve BOP. The experimental comparisons against other works within this research area on a variety of benchmark problems involving various difficulties show the effectiveness and the efficiency of our proposal.

Bi-level optimization problems are a class of challenging optimization problems, that contain two levels of optimization tasks. In these problems, the optimal solutions to the lower level problem become possible feasible candidates to the upper level problem. Such a requirement makes the optimization problem difficult to solve, and has kept the researchers busy towards devising methodologies, which can efficiently handle the problem. In recent decades, it is observed that many efficient optimizations using modern advanced EAs have been achieved via the incorporation of domain specific knowledge. In such a way, the embedment of domain knowledge about an underlying problem into the search algorithms can enhance properly the evolutionary search performance. Motivated by this issue, we present in this paper a Memetic Evolutionary Algorithm for Bi-level Combinatorial Optimization (M-CODBA) based on a new recently proposed CODBA algorithm with transfer learning to enhance future bi-level evolutionary search. A realization of the proposed scheme is investigated on the Bi-CVRP and Bi-MDVRP problems. The experimental studies on well established benchmarks are presented to assess and validate the benefits of incorporating knowledge memes on bi-level evolutionary search. Most notably, the results emphasize the advantage of our proposal over the original scheme and demonstrate its capability to accelerate the convergence of the algorithm.

In parallel to optimizing energy consumption within houses, users' comfort is increasingly considered as an essential success criterion for automated smart home solutions. From the user perspective, balancing trade-offs between energy consumption and users' comfort when scheduling home appliances is a challenging task mainly within dynamic context (energy price, budget, user preferences, energy source, etc). To address this challenge, this paper has modeled appliances scheduling as a dynamic constrained multi-objective optimization problem and have leveraged a recently introduced dynamic evolutionary algorithm for the problem resolution. Moreover, there are typically multiple inhabitants in the same home who often share context-aware applications with various individual preferences which are likely to be conflicting. We propose a new comfort function to support multi-user conflictual preferences. Our experimental results have shown that our approach has a confirmed advantage on the user comfort while coping dynamically with the context changes.

Several optimization problems encountered in practice have two levels of optimization instead of a single one. These BLOPs (Bi-Level Optimization Problems) are very computationally expensive to solve since the evaluation of each upper level solution requires finding an optimal solution for the lower level. Recently, a new research field, called EBO (Evolutionary Bi-Level Optimization) has appeared thanks to the promising results obtained by the use of EAs (Evolutionary Algorithms) to solve such kind of problems. Most of these promising results are restricted to the continuous case. Motivated by this observation, we propose a new bi-level algorithm, called CODBA (CO-Evolutionary Decomposition based Bi-level Algorithm), to tackle combinatorial BLOPs. The basic idea of our CODBA is to exploit decomposition, parallelism, and co-evolution within the lower level in order to cope with the high computational cost. CODBA is assessed on a set of instances of the bi-level MDVRP (MultiDepot Vehicle Routing Problem) and is confronted to two recently proposed bi-level algorithms. The statistical analysis of the obtained results shows the merits of CODBA from effectiveness and efficiency viewpoints.

Dynamic Multi-objective Optimization (DMO) is a challenging research topic since the objective functions, constraints, and problem parameters may change over time. Several evolutionary algorithms have been proposed to deal with DMO problems. Nevertheless, they were restricted to unconstrained or domain constrained problems. In this work, we focus on the dynamicty of problem constraints along with time-varying objective functions. As this is a very recent research area, we have observed a lack of benchmarks that simultaneously take into account these characteristics. To fill this gap, we propose a set of test problems that extend a suite of static constrained multi-objective problems. Moreover, we propose a new version of the Dynamic Non dominated Sorting Genetic Algorithm II to deal with dynamic constraints by replacing the used constraint-handling mechanism by a more elaborated and self-adaptive penalty function. Empirical results show that our proposal is able to: (1) handle dynamic environments and track the changing Pareto front and (2) handle infeasible solutions in an effective and efficient manner which allows avoiding premature convergence. Moreover, the statistical analysis of the obtained results emphasize the advantages of our proposal over the original algorithm on both aspects of convergence and diversity on most test problems.

Recently, a new metaheuristic called chemical reaction optimization was proposed. This search algorithm, inspired by chemical reactions launched during collisions, inherits several features from other metaheuristics such as simulated annealing and particle swarm optimization. This fact has made it, nowadays, one of the most powerful search algorithms in solving mono-objective optimization problems. In this paper, we propose a multiobjective variant of chemical reaction optimization, called nondominated sorting chemical reaction optimization, in an attempt to exploit chemical reaction optimization features in tackling problems involving multiple conflicting criteria. Since our approach is based on nondominated sorting, one of the main contributions of this paper is the proposal of a new quasi-linear average time complexity quick nondominated sorting algorithm; thereby making our multiobjective algorithm efficient from a computational cost viewpoint. The experimental comparisons against several other multiobjective algorithms on a variety of benchmark problems involving various difficulties show the effectiveness and the efficiency of this multiobjective version in providing a well-converged and well-diversified approximation of the Pareto front.

Software systems nowadays are complex and difficult to maintain due to continuous changes and bad design choices. To handle the complexity of systems, software products are, in general, decomposed in terms of packages/modules containing classes that are dependent. However, it is challenging to automatically remodularize systems to improve their maintainability. The majority of existing remodularization work mainly satisfy one objective which is improving the structure of packages by optimizing coupling and cohesion. In addition, most of existing studies are limited to only few operation types such as move class and split packages. Many other objectives, such as the design semantics, reducing the number of changes and maximizing the consistency with development change history, are important to improve the quality of the software by remodularizing it. In this article, we propose a novel many-objective search-based approach using NSGA-III. The process aims at finding the optimal remodularization solutions that improve the structure of packages, minimize the number of changes, preserve semantics coherence, and reuse the history of changes. We evaluate the efficiency of our approach using four different open-source systems and one automotive industry project, provided by our industrial partner, through a quantitative and qualitative study conducted with software engineers.

Dynamic multi-objective optimization problems involve the simultaneous optimization of several competing objectives where the objective functions and/or constraints may change over time. Evolutionary algorithms have been considered as popular approaches to solve such problems. Despite the considerable number of studies reported in evolutionary optimization in dynamic environments, most of them are restricted to the single objective case. Moreover, the majority of dynamic multi-objective optimization algorithms are based on the use of some techniques to detect or predict changes which is sometimes difficult or even impossible. In this work, we address the problem of dynamic multi-objective optimization with undetectable changes. To achieve this task, we propose a new algorithm called Multiple Reference Point-based Multi-Objective Evolutionary Algorithm (MRP-MOEA) which does not need to detect changes. Our algorithm uses a new reference point-based dominance relation ensuring the guidance of the search towards the Pareto optimal front. The performance of our proposed method is assessed using various benchmark problems. Furthermore, the comparative experiments show that MRP-MOEA outperforms serveral dynamic multi-objective optimization algorithms not only in tracking the Pareto front but also in maintainig diversity over time albeit the changes are undetectable.

Several engineering problems involve simultaneously several objective functions where at least one of them is expensive to evaluate. This fact has yielded to a new class of Multi-Objective Problems (MOPs) called expensive MOPs. Several attempts have been conducted in the literature with the goal to minimize the number of expensive evaluations by using surrogate models stemming from the machine learning field. Usually, researchers substitute the expensive objective function evaluation by an estimation drawn from the used surrogate. In this paper, we propose a new way to tackle expensive MOPs. The main idea is to use Neural Networks (NNs) within the Indicator-Based Evolutionary Algorithm (IBEA) in order to estimate the contribution of each generated offspring in terms of hypervolume. After that, only fit individuals with respect to the estimations are exactly evaluated. Our proposed algorithm called NN-SS-IBEA (Neural Networks assisted Steady State IBEA) have been demonstrated to provide good performance with a low number of function evaluations when compared against the original IBEA and MOEA/D-RBF on a set of benchmark problems in addition to the airfoil design problem.

There is a growing need for scalable search-based software engineering approaches that address software engineering problems where a large number of objectives are to be optimized. Software refactoring is one of these problems where a refactoring sequence is sought that optimizes several software metrics. Most of the existing refactoring work uses a large set of quality metrics to evaluate the software design after applying refactoring operations, but current search-based software engineering approaches are limited to using a maximum of five metrics. We propose for the first time a scalable search-based software engineering approach based on a newly proposed evolutionary optimization method NSGA-III where there are 15 different objectives to be optimized. In our approach, automated refactoring solutions are evaluated using a set of 15 distinct quality metrics. We evaluated this approach on seven large open source systems and found that, on average, more than 92% of code smells were corrected. Statistical analysis of our experiments over 31 runs shows that NSGA-III performed significantly better than two other many-objective techniques (IBEA and MOEA/D), a multi-objective algorithm (NSGA-II) and two mono-objective approaches, hence demonstrating that our NSGA-III approach represents the new state of the art in fully-automated refactoring.

We propose a novel recommendation tool for software refactoring that dynamically adapts and suggests refactorings to developers interactively based on their feedback and introduced code changes. Our approach starts by finding upfront a set of non-dominated refactoring solutions using NSGA-II to improve software quality, reduce the number of refactorings and increase semantic coherence. The generated non-dominated refactoring solutions are analyzed using our innovization component to extract some interesting common features between them. Based on this analysis, the suggested refactorings are ranked and suggested to the developer one by one. The developer can approve, modify or reject each suggested refactoring, and this feedback is used to update the ranking of the suggested refactorings. After a number of introduced code changes, a local search is performed to update and adapt the set of refactoring solutions suggested by NSGA-II. We evaluated this tool on four large open source systems and one industrial project provided by our partner. Statistical analysis of our experiments over 31 runs shows that the dynamic refactoring approach performed significantly better than three other search-based refactoring techniques, manual refactorings, and one refactoring tool not based on heuristic search.

Code smells represent design situations that can affect the maintenance and evolution of software. They make the system difficult to evolve. Code smells are detected, in general, using quality metrics that represent some symptoms. However, the selection of suitable quality metrics is challenging due to the absence of consensus in identifying some code smells based on a set of symptoms and also the high calibration effort in determining manually the threshold value for each metric. In this article, we propose treating the generation of code-smell detection rules as a bilevel optimization problem. Bilevel optimization problems represent a class of challenging optimization problems, which contain two levels of optimization tasks. In these problems, only the optimal solutions to the lower-level problem become possible feasible candidates to the upper-level problem. In this sense, the code-smell detection problem can be treated as a bilevel optimization problem, but due to lack of suitable solution techniques, it has been attempted to be solved as a single-level optimization problem in the past. In our adaptation here, the upper-level problem generates a set of detection rules, a combination of quality metrics, which maximizes the coverage of the base of code-smell examples and artificial code smells generated by the lower level. The lower level maximizes the number of generated artificial code smells that cannot be detected by the rules produced by the upper level. The main advantage of our bilevel formulation is that the generation of detection rules is not limited to some code-smell examples identified manually by developers that are difficult to collect, but it allows the prediction of new code-smell behavior that is different from those of the base of examples. The statistical analysis of our experiments over 31 runs on nine open-source systems and one industrial project shows that seven types of code smells were detected with an average of more than 86% in terms of precision and recall. The results confirm the outperformance of our bilevel proposal compared to state-of-art code-smell detection techniques. The evaluation performed by software engineers also confirms the relevance of detected code smells to improve the quality of software systems.

We propose in this paper to consider code-smells detection as a distributed optimization problem. The idea is that different methods are combined in parallel during the optimization process to find a consensus regarding the detection of code-smells. To this end, we used Parallel Evolutionary algorithms (P-EA) where many evolutionary algorithms with different adaptations (fitness functions, solution representations, and change operators) are executed, in a parallel cooperative manner, to solve a common goal which is the detection of code-smells. An empirical evaluation to compare the implementation of our cooperative P-EA approach with random search, two single population-based approaches and two code-smells detection techniques that are not based on meta-heuristics search. The statistical analysis of the obtained results provides evidence to support the claim that cooperative P-EA is more efficient and effective than state of the art detection approaches based on a benchmark of nine large open source systems where more than 85 percent of precision and recall scores are obtained on a variety of eight different types of code-smells.

Autonomous software agents are increasingly used in a wide range of applications. Thus, testing these entities is extremely crucial. However, testing autonomous agents is still a hard task since they may react in different manners for the same input over time. To address this problem, Nguyen et al. [6] have introduced the first approach that uses evolutionary optimization to search for challenging test cases. In this paper, we extend this work by studying experimentally the effect of the number of objectives on the obtained test cases. This is achieved by proposing five additional objectives and solving the new obtained problem by means of a Preference-based Many-Objective Evolutionary Testing (P-MOET) method. The obtained results show that the hardness of test cases increases with the rise of the number of objectives.

During the two last decades, evolutionary algorithms have been successfully used to solve multiobjective optimization problems. Several works have been established to improve convergence and diversity. Recently, several multiobjective artificial immune systems have shown their ability to solve multiobjective optimization problems. However, in reality, decision makers are not interested with the whole optimal Pareto front rather than the portion of the Pareto front that matches at most their preferences, i.e., the region of interest. In this paper, we propose a new dominance relation inspired from several ideas of the danger theory, called Danger Zone-based dominance (DZ-dominance), which guides the search process towards the preferred part of the Pareto front. The DZ-dominance is incorporated within the Nondominated Neighbor Immune Algorithm (NNIA). The new preference-based algorithm, named DZ-NNIA, has demonstrated its ability to guide the search based on decision maker's preferences. Moreover, comparative experiments show that our algorithm outperforms the most recent preference-based immune algorithm HMIA and the preference-based multiobjective evolutionary algorithm g-NSGA-II.

Recent studies on Evolutionary Multi-objective Optimization (EMO) aim at focusing the search only on those portions of the front which satisfy the preferences of the Decision Maker (DM), i.e., the Regions Of Interest (ROIs), rather than approximating the whole Pareto front. Most studies assume the uniqueness of the DM which is not the case for several decision making situations. In this study, we address this problematic by providing the DMs with an agent-based negotiation support system to aggregate their conflicting preferences before the beginning of the evolutionary process. This negotiation system helps the DMs to confront and adjust their preferences through a number of negotiation rounds. The system output is a set of social preferences which will be injected subsequently in a preference-based EMO Algorithm (EMOA) in order to guide the search towards a satisfying social ROI. The usefulness of the proposed system is demonstrated through a case study.

Nadir point represents important information to multi-objective optimization practitioners. Along with the ideal point, the nadir point: (1) provides information about the ranges of the objectives at the Pareto optimality stage, (2) helps the decision maker to easily state his/her preferences, (3) facilitates the visualization of Pareto optimal solutions for highly dimension multi-objective problems, etc. Contrary to the ideal point which can be easily computed by optimizing each objective individually over the search space, the nadir point is constructed from worst objective function values of Pareto optimal solutions which makes the accurate estimation of the nadir objective values a difficult task especially when the number of objective functions increases. In this paper, we propose a new memetic preference-based multi-objective evolutionary algorithm, termed MR-NSGA-IIN, to estimate the nadir point. The basic idea is to use extreme solutions from the best non-dominated front as mobile reference points. The mobile reference points are updated in every generation by means of a gradient-based local search procedure in order to speed up the convergence towards the Pareto optimal extreme solutions. The performance assessment of MR-NSGA-IINis carried out on a set of three-to twenty-objective unconstrained/constrained linear/non-linear problems. The proposed approach has shown competitive and better results when compared to other recently proposed nadir point estimation approaches.

Evolutionary multiobjective optimization (EMO) methodologies have gained popularity in finding a representative set of Pareto optimal solutions in the past decade and beyond. Several techniques have been proposed in the specialized literature to ensure good convergence and diversity of the obtained solutions. However, in real world applications, the decision maker is not interested in the overall Pareto optimal front since the final decision is a unique solution. Recently, there has been an increased emphasis in addressing the decision-making task in searching for the most preferred alternatives. In this paper, we introduce a new variant of the Pareto dominance relation, called r-dominance, which has the ability to create a strict partial order among Pareto-equivalent solutions. This fact makes such a relation able to guide the search toward the interesting parts of the Pareto optimal region based on the decision maker's preferences expressed as a set of aspiration levels. After integrating the new dominance relation in the NSGA-II methodology, the efficacy and the usefulness of the modified procedure are assessed through two to ten-objective test problems a priori and interactively. Moreover, the proposed approach provides competitive and better results when compared to other recently proposed preference-based EMO approaches.

We introduce in this paper a new multi-objective memetic algorithm. This algorithm is a result of hybridization of the NSGA-II algorithm with a new designed local search procedure that we named Pareto Hill Climbing. Verification of our novel algorithm is carried out by testing it on two sets of multi-objective test problems and comparing it to other multi-objective evolutionary algorithms (MOEAs) and other multi-criterion memetic algorithms (MMAs). Simulation results show the algorithm ability in tackling continuous multi-objective problems in terms of convergence and diversity. Our hybrid algorithm (1) outperforms pure MOEAs, (2) is competent with other gradient based MMAs, and (3) can solve non differentiable problems.