In the Internet of Battlefield Things domain, optimal sensor placement is critical for both tactical and strategic considerations in military surveillance scenarios. Finding the optimal sensor positions for informed decision-making in critical and highly constrained environments is challenging. This paper formulates the problem and proposes a differential evolution algorithm to maximise a military base station's situational awareness by efficiently finding the optimal sensor positions, enabling timely identification and notification of potential enemy threats. The proposed algorithm also adopts heuristic initialisation and a repair method to improve performance. The approach is tested on 21 scenarios, each varying in the number of sensors, the number and size of obstacles, and the expected directions of enemy attacks. The study's results demonstrate the effectiveness of the newly introduced approach.

Addressing large-scale optimization problems with numerous variables and constraints poses difficulties. Ineffectively handling the constraints can result in solutions that are either not optimal or infeasible. In our research, we utilized the constraint-objective cooperative coevolution framework with the FDfar (Feasibility distance-far) method, which is a constraint consensus approach. Our proposed algorithm involves decomposing a complex problem into smaller, more manageable subproblems (subcomponents) using the Recursive Differential Grouping technique, which assigns interrelated variables to the same subcomponent. Then, the FDfar method is selectively applied to a randomly chosen solution to enhance its feasibility. Subsequently, the population is updated while considering the newly generated solution from the FDfar method. We then assess the impact of each subcomponent on both the objective function and the constraints to identify the most effective subcomponent for evolution. The chosen subcomponent then undergoes further evolution using Differential Evolution. We tested our algorithm on a set of 12 benchmark problems. The results from these tests consistently indicated that our approach outperforms other leading methods, not only in making solutions feasible but also in improving their overall quality.

Integrated decision-making regarding the selection and scheduling of a project portfolio, referred to as the project portfolio selection and scheduling problem (PPSSP), can contribute to the more favorable performance of many organizations. However, the optimization of large-scale PPSSP involving a large number of projects and complex constraints remains challenging. While exact solvers offer guaranteed optimal solutions, they are computationally intractable in large-scale PPSSP. On the contrary, metaheuristics search for approximated solutions within a reasonable time. This paper investigates the performance of a commercial exact solver and metaheuristics in addressing large- scale PPSSP within a limited time. In addition, hybrid approaches are proposed to combine the exact solver and metaheuristics in different ways to address PPSSP. Experiments are conducted on PPSSP instances with an increasing number of projects (up to 6000), demonstrating the superiority of metaheuristics in addressing large-scale PPSSP within a short time and the effectiveness of combining metaheuristics in Gurobi in facilitating the optimization process.

In recent decades, large-scale optimization has received significant research attention; however, most of these studies have not considered problems with functional constraints. The introduction of constraints significantly amplifies the difficulty of solving optimization problems. Given the preva-lence of high-dimensional constrained optimization problems in real-world applications, a critical need has emerged for an in-depth exploration of this research domain. This paper presents a novel framework that can tackle complex, large-scale constrained optimisation problems. The framework incorpo-rates a decomposition method that leverages interactions among decision variables, employing a contribution-based strategy to prioritize subproblems that have more substantial influence on enhancing solution quality. Furthermore, the framework integrates constraint consensus to mitigate constraint violations throughout the search process. The proposed algorithm is evaluated on a test suite of constrained overlapping problems, revealing its superior performance when compared to other state-of-the-art algorithms.

This paper considers a fleet of electric vehicles and drones that deliver goods collaboratively. To determine the optimal routes of this electric vehicle-drone routing problem, the problem is formulated as a mixed-integer linear program to minimize the total operational costs. To solve the model, we develop an adaptive memetic algorithm that employs a multi-operator concept with a Q-learning-based selection mechanism and a set of local search operators for exploring the complex search space of the problem. Using extensive numerical experiments, we prove the effectiveness of our proposal and reveal some interesting managerial insights.

The profitability of a supply chain (SC) is proportional to the stability of all its stakeholders as well as their consistent information sharing with an effective and efficient communication mechanism. Various inefficiencies, such as the bullwhip effect (BWE) and product unavailability, may be caused by a lack of coordination in an SC. The importance of sharing consumer demand has been quantified by comprehensive studies under the assumption that all SC participants will access the same information. However, only a few studies have studied the effect of minimal coordination or limited visibility of information while considering their effect on the overall efficiency of an SC. This work primarily leverages blockchain technology (BCT) to create a simulation model. To do this, an SC BWE-based model is initially developed. Following that, a blockchain-based robust information sharing system is simulated. Furthermore, information sharing is challenging, and SC stakeholders may not really trust each other and hence be reluctant to share sensitive information. Considering that, this paper propose an improved proof-of-authority (PoA) consensus algorithm that will increase trust in a decentralized SC model. Multiple experiments are carried out to demonstrate the effectiveness of our approach, and the simulation results clearly demonstrate the effectiveness of information sharing in a supply chain via blockchain, as well as that trust between partners tends to increase overall SC efficiency and reduce BWE.

In recent years, supply chains have evolved into huge ecosystems, demanding trust, provenance, and data privacy. Since blockchain technology (BCT) allows for the development of a distributed environment, it is ideal for supply chain management (SCM) applications. However, concerns regarding data privacy have impeded the development of blockchains. Despite the fact that some blockchains can restrict participants from reading and/or writing data, blockchain’s transparency makes protecting sensitive data challenging. To solve the data privacy challenge, this paper proposes a framework, AccessChain, that is an SCM access control framework that is based on an attribute-based access control (ABAC) model that restricts access to competing parties while allowing for network scalability. This proposed AccessChain model has two types of ledgers in its system: local and global. Local ledgers are used to store business contracts between stakeholders and the attribute-based access control model management, whereas the global ledger is used to record transaction data. AccessChain can enable decentralized, fine-grained and dynamic access control management in SCM when combined with the ABAC model and BCT. This paper’s experimental results illustrate that high throughput can be achieved in a large-scale request environment while maintaining data privacy and sustaining a scalable network.

Explicit and implicit averaging are two well-known strategies for noisy optimization. Both strategies can counteract the disruptive effect of noise; however, a critical question remains: which one is more efficient? This question has been raised in many studies, with conflicting preferences and, in some cases, findings. Nevertheless, theoretical findings on the noisy sphere problem with additive Gaussian noise supports the superiority of implicit averaging, which may have had a strong impact on the preference of implicit averaging in more recent evolutionary methods for noisy optimization. This study speculates that the analytically supported superiority of implicit averaging relies on specific features of the noisy sphere problem with additive noise, which cannot be generalized to other problems. It enumerates these features and designs controlled numerical experiments to investigate this potential reliance. Each experiment gradually suppresses one specific feature, and the progress rate is numerically calculated for different values of the sample size given a fixed evaluation budget. Our empirical results indicate that for a wide range of noise strength and evaluation budget per iteration, the more these specific features are suppressed, the more the optimal averaging strategy deviates from implicit toward explicit averaging, which confirms our speculations. Consequently, the optimal sample size, which is regarded as the tradeoff between implicit and explicit averaging, depends on the problem characteristics and should be learned during optimization for maximum efficiency.

Many practical decision-making problems involve changing data and parameters with time. Solving such problems requires a custom-designed algorithm that can efficiently handle the repeatedly changing problem, in fact, its changing search space. In this paper, we consider constrained optimisation problems where the coefficients of the objective function change. We propose a framework that adaptively deals with linear and nonlinear components by satisfying the constraints within a limited time. Furthermore, we introduce a new mechanism to identify the sensitivity of variables, determine the rate of changes in the coefficients of the decision variables, and propose a heuristic to update the population efficiently after every change. The experimental results demonstrate that the proposed approach is able to obtain better solutions than those without having these new components.

The coming era of widespread integration of Internet of Things (IoT) devices to all areas of society has facilitated a fundamental transformation of local and global communication networks, giving rise to novel issues relating to capacity planning, network administration, and cybersecurity. Accurate network traffic prediction is one of the key enablers for addressing these challenges. While there are methods for quantifying the complexity (predictability in timing, shape, and volume) of wide-scale aggregate traffic, they cannot be directly applied to IoT traffic as they do not account for the heterogeneity of IoT devices. Lacking an effective complexity characterization for IoT traffic, network traffic administrators are under-informed on the impacts of IoT device-type traffic on their networks. In this work, the complexity of IoT traffic is examined from two novel perspectives, the information-theoretic approach of Lempel–Ziv, a foundational algorithm in lossless data compression, and in the distribution of spectral components of the Fourier transform. Based on these perspectives, two new measures of IoT network traffic complexity are proposed. Furthermore, we introduce a novel mathematical framework to permit a formal comparison of new and existing methods. The new framework additionally verifies that the new metrics satisfy desirable properties for a measure of complexity. In a comprehensive empirical study, our results, when compared with existing approaches, exceed all others in behavioral resolution, convergence rate, physical interpretability, and algorithmic stability, under severely heterogeneous conditions. Benchmark experiments demonstrate substantial run-time improvements over existing approaches, creating a strong case for their use in online, real-time settings.

Existing solution approaches for handling disruptions in project scheduling use either proactive or reactive methods. However, both techniques suffer from some drawbacks that affect the performance of the optimization process in obtaining good quality schedules. Therefore, in this article, we develop an auto-configured multioperator evolutionary approach, with a novel pro-reactive scheme for handling disruptions in multimode resource-constrained project scheduling problems (MM-RCPSPs). In this article, our primary objective is to minimize the makespan of a project. However, we also have secondary objectives, such as maximizing the free resources (FRs) and minimizing the deviation of activity finishing time. As the existence of FR may lead to a suboptimal solution, we propose a new operator for the evolutionary approach and two new heuristics to enhance the algorithm's performance. The proposed methodology is tested and analyzed by solving a set of benchmark problems, with its results showing its superiority with respect to state-of-the-art algorithms in terms of the quality of the solutions obtained.

The covariance matrix self-adaptation evolution strategy with repelling subpopulations (RS-CMSA-ES) is one of the most successful multimodal optimization (MMO) methods currently available. However, some of its components may become inefficient in certain situations. This study introduces the second variant of this method, called RS-CMSA-ESII. It improves the adaptation schemes for the normalized taboo distances of the archived solutions and the covariance matrix of the subpopulation, the termination criteria for the subpopulations, and the way in which the infeasible solutions are treated. It also improves the time complexity of RS-CMSA-ES by updating the initialization procedure of a subpopulation and developing a more accurate metric for determining critical taboo regions. The effects of these modifications are illustrated by designing controlled numerical simulations. RS-CMSA-ESII is then compared with the most successful and recent niching methods for MMO on a widely adopted test suite. The results obtained reveal the superiority of RS-CMSA-ESII over these methods, including the winners of the competition on niching methods for MMO in previous years. Besides, this study extends RS-CMSA-ESII to dynamic MMO and compares it with a few recently proposed methods on the modified moving peak benchmark functions.

There has been a considerable amount of research on the development of metaheuristic methods for resource-constrained project scheduling problems. Early methods followed the building blocks and even the formulation of well-understood metaheuristic methods as well as simple but effective heuristics such as forward-backward improvement. In contrast, more recent methods employ less familiar, more complex (hybrid) metaheuristics and non-standard components and formulations. Although the former may provide better results on standard test problems, it is not easy to understand how each component has contributed to improving the results and why a deviation from well-established formulations, components and methods was necessary. This research advances our knowledge about the impact of different strategies and components of customized genetic algorithms (some of which have been proposed in this study) on the optimization results. This task is performed by developing a comprehensive genetic algorithm with several familiar and potentially effective components. A modular analysis is then performed in which one component is suppressed at a time, and the resultant performance decline is analyzed. With hindsight from the modular analysis, a simple method is suggested and the importance of each component is clarified. Thus, no further simplification can be performed without compromising efficiency. Our preliminary results reveal that this customized genetic algorithm outperforms many existing methods and can compete with the most successful ones, which, in many cases, are much more complex than our approach.

Big data optimization has become an important research topic in many disciplines. These optimization problems involve a large volume of data, from different sources, in different formats, that are generated at a high speed. For example, in the healthcare sector, electroencephalography (EEG), which is a method for monitoring brain signals and typically used to diagnose neurological disorders, generates a large amount of data which, however, is often captured with artifacts added from non-brain sources. Evolutionary algorithms are considered one of the most successful approaches for solving many such complex optimization problems. In this paper, a differential evolution algorithm is developed to remove artifacts from EEG signals of interest, by using the parallel computing ability of a Graphics Processing Unit. Two levels of parallelization, variable and individual, are implemented, with a gradient-based local search and adaptive control parameters incorporated in order to enhance a search's convergence. The proposed algorithm is tested using six single objective problems from the 2015 big data optimization competition problems with 1024, 3072 and 4864 decision variables, as both noise-free and with white noise. The results presented in this paper indicate that the proposed algorithm is capable of achieving high-quality solutions, and is up to 374.7 faster than the state-of-the-art algorithms.

A single quantitative measure for characterizing the complexity of Internet-of-Things (IoT) network traffic remains elusive. Such a quantifier holds value in distinguishing the relative complexities of IoT network traffic in an increasingly heterogeneous IoT device landscape, enabling network operators to anticipate and provision for, as well as manage existing network infrastructure. In this paper, we apply relevant contemporary techniques used to quantify the complexity of regular network traffic to a modern, comprehensive empirical IoT network traffic dataset. The results were interpreted to discover their merits and pitfalls. Based on our findings, we contend there is a need to develop new quantitative measures that can accommodate the diversity of IoT traffic.

This study develops an adaptive multilevel prediction (AMLP) method to detect and track multiple global optima over time. First, it formulates a multilevel prediction approach in which a higher level prediction improves the accuracy of the lower level prediction to reduce the prediction error, enabling it to capture more complex patterns in the changes. However, a higher level prediction is more sensitive to input errors and the randomness in the pattern of the change. To overcome this challenge, this study employs an adaptive mechanism which can determine the near-optimal prediction level at each time step. At the same time, AMLP calculates the strength of the diversity introduced after a change based on the estimated prediction error. A successful static multimodal optimizer is augmented with AMLP, for which AMLP determines the location and the mutation strength of the initialized subpopulations. An existing dynamic benchmark generator is improved so that it can generate dynamic test problems with more complex patterns in their changes. In particular, this dynamic benchmark generator allows for controlling the randomness of the pattern in the change to simulate dynamic problems with different degrees of predictability. A few controlled experiments are first performed to provide insight into different components of AMLP. Then, AMLP is compared with some of the most successful prediction methods when they are incorporated into the developed dynamic multimodal optimization method. Eleven dynamic cases with different change severity, change frequency, predictability, problem dimensionality, and the number of global minima are considered. The numerical results show the superiority of AMLP over other prediction methods.

Developing a Deep Convolutional Neural Network (DCNN) is a challenging task that involves deep learning with significant effort required to configure the network topology. The design of a 3D DCNN not only requires a good complicated structure but also a considerable number of appropriate parameters to run effectively. Evolutionary computation is an effective approach that can find an optimum network structure and/or its parameters automatically. Note that the Neuroevolution approach is computationally costly, even for developing 2D networks. As it is expected that it will require even more massive computation to develop 3D Neuroevolutionary networks, this research topic has not been investigated until now. In this article, in addition to developing 3D networks, we investigate the possibility of using 2D images and 2D Neuroevolutionary networks to develop 3D networks for 3D volume segmentation. In doing so, we propose to first establish new evolutionary 2D deep networks for medical image segmentation and then convert the 2D networks to 3D networks in order to obtain optimal evolutionary 3D deep convolutional neural networks. The proposed approach results in a massive saving in computational and processing time to develop 3D networks, while achieved high accuracy for 3D medical image segmentation of nine various datasets.

Differential evolution was mainly proposed for solving optimization problems with continuous decision variables because of its Euclidean distance-based learning concept. This made it unsuitable for many binary and discrete problems. However, several studies approved the applicability of differential evolution algorithm for effectively solving such problems. In this paper, a new design of differential evolution, which incorporates mapping and repairing methods, modified mutation operator and local searches, is proposed to solve the complex multicomponents traveling thief problems that are characterized by both binary and discrete parameters. Also, a novel initialization and repairing method, which enables differential evolution's operators to only evolve solutions of one component and optimally distribute/update the solutions of the other one with considering the inter-dependency between both components, is introduced. To judge the performance of the proposed algorithm, 13 strongly correlated instances of traveling thief problems have been solved and the results have been compared with those from 24 selfdesigned and state-of-the-art algorithms. Results demonstrated the competitive performance of the proposed algorithm in terms of the quality of obtained solutions and computational time.

Over the last few decades, many solution approaches have been developed for solving different variants of resourceconstrained project scheduling problems (RCPSPs). In most of them, it is assumed that a project consists of some homogeneous activities that require all types of resources over the entire project horizon. On the contrary, many real-world projects consist of heterogeneous activities that use different types of resources at different time instants during the project execution. The application of existing approaches, developed for RCPSPs with homogeneous activities, in solving RCPSPs with heterogeneous activities is computationally expensive. In this paper, we propose a heuristic embedded genetic algorithm to address RCPSPs with heterogeneous activities. Two heuristics are proposed to obtain high-quality feasible solutions. The first heuristic is based on priority rules while the second one based on a new neighbourhood swapping matrix. To evaluate the performance of the proposed algorithm, we solve a number of real-world and modified test problems, and the obtained results are compared with an existing algorithm. It is found that the proposed approach obtains highquality solutions with a significantly lower computational time compared to other algorithms.

Sentiment analysis is an important sub-task of Natural Language Processing that aims to determine the polarity of a review. Most of the work done on sentiment analysis is for the resource-rich languages of the world, but very limited work has been done on resource-poor languages. In this work, we focus on developing a Sentiment Analysis System for Roman Urdu, which is a resource-poor language. To this end, a dataset of 11,000 reviews has been gathered from six different domains. Comprehensive annotation guidelines were defined and the dataset was annotated using the multi-annotator methodology. Using the annotated dataset, state-of-the-art algorithms were used to build a sentiment analysis system. To improve the results of these algorithms, four different studies were carried out based on: word-level features, character level features, and feature union. The best results showed that we could reduce the error rate by 12% from the baseline (80.07%). Also, to see if the improvements are statistically significant, we applied t-test and Confidence Interval on the obtained results and found that the best results of each study are statistically significant from the baseline.

This study develops a prediction-based reinitialization approach that is comprised of three components for dynamic multiobjective optimization (DMO). The first component is a controlled translation of the population centroid, which analyzes the successive movement of the population Pareto optimal set (POS) at the end of each problem instance. The second and third components are directional and random variation. In addition, a metric to quantify the variation in the POS that does not fit in a simple translation is proposed. The rationale behind each component is explained and demonstrated in some carefully designed descriptive experiments. Different variants of the proposed strategy are assessed and compared with two recently proposed reinitialization strategies, on an accredited test suite for DMO. A comparison of the numerical results reveals that unlike the random variation, the directional variation operator significantly improves the performance. Overall, our proposed strategy considerably outperforms the other considered strategies, especially when the evaluation budget for each problem instance is limited.

Several research studies have been carried out on the integration of quantum operators and evolutionary algorithms. However, the performance of such integration remains questionable and needs further research for drawing a useful conclusion. Therefore, this paper takes a step forward to analyze the effect of integrating quantum entanglement and quantum NOT gate with the well-known differential evolution algorithm. The performance of different algorithm designs has been evaluated by solving a number of unconstrained real parameter single objective optimization problems. Although the integration of quantum entanglement helps to get competitive results, the overall experimental results with quantum operators are not convincing enough, especially when there are no inter-dependency among decision variables. This in turn opens up new research directions to deepen the knowledge in the design of quantum evolutionary algorithms.

Over the last few decades, project scheduling problems have been solved under a set of resource constraints, which are assumed fixed throughout the project horizon. However, in real-life applications, resources may change over time due to maintenance or because the resources are needed for another project. Therefore, this research introduces a hybrid evolutionary framework, based on two multi-operator evolutionary algorithms, and a heuristic technique, for a multi-mode project scheduling under irregular resources changes. The framework simultaneously considers both algorithms and self-adaptively emphasizes the one which performs comparatively better. The heuristic considers two variants of handling techniques for irregular resources. One is based on inserting buffer activities to characterize resources unavailable, and another is based on a modified serial generation scheme, that determines the best modes of the activities at each time period based on irregular resources. The framework is tested by solving a set of test problems, with the renewable resources considered irregular over the project horizon. The results demonstrate that the multi-method algorithm has some advantages for scheduling a project, under both regular and irregular resources.

The traveling salesman problem is a well-known combinatorial optimization problem with permutation-based variables, which has been proven to be an NP-complete problem. Over the last few decades, many evolutionary algorithms have been developed for solving it. In this study, a new design that uses the k-means clustering method, is proposed to be used as a repairing method for the individuals in the initial population. In addition, a new crossover operator is introduced to improve the evolving process of an evolutionary algorithm and hence its performance. To investigate the performance of the proposed mechanism, two popular evolutionary algorithms (genetic algorithm and differential evolution) have been implemented for solving 18 instances of traveling salesman problems and the results have been compared with those obtained from standard versions of GA and DE, and 3 other state-of-the-art algorithms. Results show that the proposed components can significantly improve the performance of EAs while solving TSPs with small, medium and large-sized problems.

The traditional differential evolution algorithm was originally, and still is mainly, used to solve continuous optimization problems. As a result, it has not commonly been considered as applicable for several real-world problems in the permutation-based domain. In this paper, a novel differential evolution algorithm, which incorporates several effective components, is introduced. These components increase search effectiveness by providing a good balance between exploration (discovering new solutions) and exploitation (further exploring current solutions) processes. Moreover, a dual representation of solutions, which has the capability to allow normal continuous handling of variables by differential evolution operators, and at same time provide binary variables for fitness measurement, is employed. To judge the performance of the proposed algorithm, 14 instances of 0-1 knapsack problems have been solved and the results have been compared with those obtained from 11 state-of-the-art algorithms. Results show that the proposed algorithm was able to outperform other algorithms in solving small and medium sized knapsack problems and is competitive in large-sized problems.

Although many evolutionary algorithms (EAs) have successfully solved different optimization problems, no single EA has consistently been the best for all these problems. During the last decade, to alleviate this limitation, many proposals which utilize multiple EAs in a single algorithmic framework, called multi-methods or multi-operators, have been introduced. However, there is still room to enhance their performance. In this paper, an improved variant of a united multi-operator algorithm is introduced with few improvements that are capable of providing a balance between diversification and intensification properties during the optimization. The proposed algorithm is tested on the CEC2017 unconstrained benchmark problems, with the results revealing that the proposed algorithm is capable of producing high quality solutions compared with those of state-of-the-art algorithms.

Over the last two decades, many different differential evolution (DE) variants have been developed for solving constrained optimization problems. However, none of them performs consistently when solving different types of problems. To deal with this drawback, multiple search operators are used under a single DE algorithm structure where a higher selection pressure is placed on the best performing operator during the evolutionary process. In this paper, we propose to use the landscape information of the problem in the design of the selection mechanism. The performance of this algorithm with the proposed selection mechanism is analysed by solving 10 real-world constrained optimization problems. The experimental results revealed that the proposed algorithm is capable of producing high quality solutions compared to those of state-of-the-art algorithms.

Many real-world decision problems involve uncertain parameters. The Resource Constrained Project Scheduling Problem (RCPSP) is one of those problems in which the activity durations are usually uncertain. Over the last decade, a good number of solution approaches have been developed to solve such problems, among them the population based algorithms received great attention. In the solution approaches, a large number of scenarios are usually evaluated which is computationally expensive. In this paper, as an attempt to reduce the computational time, we propose few alternative approaches and experiment them with an assumption that the uncertain parameters are random variables. For experimental study, these variables are generated using four different probability distributions. The proposed approaches are compared with the traditional scenario based approach by solving 10 well-known benchmark problems with 30 activities. The results revealed that it has advantages in terms of solution quality and computational time.

In Simulation Optimization, the computational cost, due to the huge number of simulation replications along with the optimization process cost, is considered as a key challenge. This encourages the investigation of the effect of the number of simulation replications on the performance of the optimization algorithm, in terms of the solution fidelity versus the computational cost. Existing simulation replication strategies with optimization algorithms have been proposed utilizing a single probability distribution to fit their parameter settings for solving stochastic simulation problems. In this paper, simulation replication strategies are developed by a proposed Strategy Design Technique using three distributions: Bimodal Gaussian, Exponential, and Poisson for involving discrete and continuous stochastic parameters. A Differential Evolution algorithm is hybridized with Monte-Carlo simulation to solve a set of stochastic, continuous and constrained problems, using the designed strategies. Several experiments are conducted, using modified IEEE-CEC'2006 test problems. Optimization results' fidelity is empirically assessed in terms of a proposed probability of correct final selection of the solution. It reflects the ability of the proposed simulation strategies to direct the Differential Evolutionary algorithm in the search space, even under different stochastic settings and low simulation budget. Additional experiments have been conducted to study the compromising between the simulation and the optimization budgets under different settings using the same total computational load. The results indicate that the proposed strategies obtain robust results with a remarkable reduction in the simulation budget, under different stochastic settings.

Over the last two decades, many different evolutionary algorithms (EAs) have been proposed for solving optimization problems. However, no single EA has consistently been the best for solving a wide range of them. In the literature, this drawback has been tackled by using multiple EAs in a single framework. In this paper, a new multi-method based EA that utilizes the search ability of multi-operator differential evolution algorithm (MODE) and covariance matrix adaptation evolution strategy CMA-ES algorithm in a single framework, has been presented, with the orthogonal experimental design (OED) and factor analysis (FA) used to select the proper combination of mutation strategies, control parameters adaptation strategies, and crossover operators. To judge the performance of this algorithm, 30 problems are solved from the CEC2017 competition and their results are analyzed.

Until now, numerous mutation strategies have been introduced as search operators within the differential evolution (DE) algorithm. These operators are designed mainly to improve fitness value while also maintaining diversity in the population, but they do not directly act to reduce constraint violations of constrained problems. Interestingly, the so-called constraint handling techniques, used with most evolutionary algorithms, are not a part of the actual search process. Instead, the constraint violations are only considered in the ranking and selection of individuals for participation in the search process. This paper introduces a new DE mutation operator that incorporates a mechanism, based on constraint consensus, that can directly help to reduce the constraint violations during the evolutionary search process. The proposed DE algorithm has been tested on a set of well-known constrained benchmark problems. The experimental results show that the proposed algorithm is able to obtain better solutions, compared to the standard DE algorithm, with significantly reduced computational effort. The algorithm also outperforms state-of-the-art algorithms.

Recently, the success history based parameter adaptation for differential evolution algorithm with linear population size reduction has been claimed to be a great algorithm for solving optimization problems. Neuro-dynamic is another recent approach that has shown remarkable convergence for certain problems, even for high dimensional cases. In this paper, we proposed a new algorithm by embedding the concept of neuro-dynamic into a modified success history based parameter adaptation for differential evolution with linear population size reduction. We have also proposed an adaptive mechanism for the appropriate use of the success history based parameter adaptation for differential evolution with linear population size reduction and neuro-dynamic during the search process. The new algorithm has been tested on the CEC'2015 single objective real-parameter competition problems. The experimental results show that the proposed algorithm is capable of producing good solutions that are clearly better than those obtained from the success history based parameter adaptation for differential evolution with linear population size reduction and a few of the other state-of-the-art algorithms considered in this paper.

Many infrastructures, such as those of finance and banking, transportation, military and telecommunications, are highly dependent on the Internet. However, as the Internet’s underlying structural protocols and governance can be disturbed by intruders, for its smooth operation, it is important to minimize such disturbances. Of the available techniques for achieving this, computational intelligence methodologies, such as evolutionary algorithms and swarm intelligence approaches, are popular and have been successfully applied to detect intrusions. In this paper, we present an overview of these techniques and related literature on intrusion detection, analyze their research contributions, compare their approaches and discuss new research directions which will provide useful insights for intrusion detection researchers and practitioners.

Multi-method and multi-operator evolutionary algorithms (EAs) have shown superiority to any single EAs with a single operator. To further improve the performance of such algorithms, in this research study, a united multi-operator EAs framework is proposed, in which two EAs, each with multiple search operators, are used. During the evolution process, the algorithm emphasizes on the best performing multi-operator EA, as well as the search operator. The proposed algorithm is tested on a well-known set of constrained problems with 10D and 30D. The results show that the proposed algorithm scales well and is superior to the-state-of-the-art algorithms, especially for the 30D test problems.

This paper puts forward a proposal for combining multi-operator evolutionary algorithms (EAs), in which three EAs, each with multiple search operators, are used. During the evolution process, the algorithm gradually emphasizes on the best performing multi-operator EA, as well as the search operator. The proposed algorithm is tested on the CEC2014 single objective real-parameter competition. The results show that the proposed algorithm has the ability to reach good solutions.

In the literature, a considerable number of mutation operators have been proposed, which are the key search operators in differential evolution algorithm for solving optimization problems. Although those operators were developed in the context of unconstrained optimization, they were widely used in constrained optimization. However, those operators did not contain any mechanism that would reduce the constraint violation in the search process. Therefore, in this paper, a new mutation operator based on the constraint consensus method is proposed, which can help infeasible points reach the feasible region quickly. The algorithm is tested on the CEC2010 constrained benchmark problems. The experimental results show that the proposed algorithm is able to obtain better solutions in comparison with the state-of-the-art algorithms.

The Permutation Flow Shop Scheduling Problem (PFSP) is considered to be one of the complex combinatorial optimization problems. For PFSPs, the schedule is produced under ideal conditions that usually ignore any type of process interruption. In practice, the production process is interrupted due to many different reasons, such as machine unavailability and breakdowns. In this paper, we propose a Genetic Algorithm (GA) based approach to deal with process interruptions at different points in time in Permutation Shop Floor scenarios. We have considered two types of process interruption events. The first one is predictive, where the interruption information is known well in advance, and the second one is reactive, where the interruption information is not known until the breakdown occurs. An extensive set of experiments has been carried out, which demonstrate the usefulness of the proposed approach.

Large scale constrained problems are complex problems due to their dimensionality, structure, in addition to their constraints. The performance of EAs decreases when the problem dimension increases. Decomposition-based EAs can overcome this drawback, but their performance would be affected if the interdependent variables were optimized in different subproblems. The use of EAs with variables interaction identification technique handles this issue by identifying better arrangements for decomposing a large problem into subproblems in a way that minimizes the interdependencies between them. The only technique in the literature that has been developed to identify the variables interdependency in constrained problems is the Variable Interaction Identification for Constrained problems (VIIC). This technique is tested in this paper on a real-world problem at three large dimensions which are large scale constrained optimization problems. The performance of the decomposition-based EA that uses VIIC is compared to Random Grouping approach for decomposition, for 5-Units, 10-Units, and 30-Units DED problems.

Many genetic algorithms variants have been introduced for solving different classes of optimization problems. The success of any GA depends on the design of its search operators, as well as its parameters. In this paper, we propose a new three-parent crossover. In addition, we design a diversity operator which works with an archive of selected individuals. The algorithm has been applied to solve all the CEC'2013 competition problems on real-parameter optimization. The solutions obtained are either optimal or very close to the known best solutions.

The Permutation Flow Shop Scheduling Problem (PFSP) is a well-known combinatorial optimization problem. In this paper, a Genetic Algorithm (GA) based approach has been developed to solve PFSP, with the objective of minimizing the makespan for a set of jobs. Two new priority rules; such as Gap Filling (GF) technique and Job Shifting (JS), have been introduced to enhance the performance of the GA. The algorithm has been used to solve a set of standard benchmark problems and the results have been compared with state-of-the-art algorithms. The comparison demonstrates that the overall performance of the algorithm is quite satisfactory.

Many real-world optimization problems are difficult to solve as they do not possess the nice mathematical properties required by the exact algorithms. Evolutionary algorithms are proven to be appropriate for such problems. In this paper, we propose an improved differential evolution algorithm that uses a mix of different mutation operators. In addition, the algorithm is empowered by a covariance adaptation matrix evolution strategy algorithm as a local search. To judge the performance of the algorithm, we have solved well-known benchmark as well as a variety of real-world optimization problems. The real-life problems were taken from different sources and disciplines. According to the results obtained, the algorithm shows a superior performance in comparison with other algorithms that also solved these problems.

Bringing the 2012 IEEE World Congress on Computational Intelligence (IEEE-WCCI 2012) for the first time to Australia has been a fulfilling journey of joy and honour. This premier event of the IEEE Computational Intelligence Society (IEEE-CIS) brings together three flagship conferences of the society in even years. It consisted of these conferences: the International Joint Conference on Neural Networks (IJCNN 2012), the IEEE International Conference on Fuzzy Systems (FUZZIEEE 2012) and the 2012 IEEE Congress on Evolutionary Computation (IEEE CEC 2012). This document presents the technical papers from the IEEE CEC 2012 conference, which had 758 submissions, of which, 482 were accepted.

During the last two decades, a considerable number of particle swarm variants have been introduced. However, no single variant consistently performed well over a range of test problems with different mathematical properties. In this paper, a memetic multi-topology particle swarm optimizer (MMTPSO) is introduced for solving constrained optimization problems. MMTPSO utilizes the strengths of two different particle swarm topologies and during the evolution process the algorithm is designed to emphasize the best performing topology. Moreover, to increase the convergence pattern of the proposed algorithm, a local search algorithm is periodically used. MMTPSO shows a superior performance to its independent variants, as well as other state-of-the-art algorithms, by solving 13 well-known test problems.

Over the last few decades, real world constrained optimization has become an important research topic in the evolutionary computation field. The Economic Load Dispatch is one of the well-known complex practical problems. The problem is usually represented by a non-convex constrained optimization model. In this paper, we propose to use an ensemble of three different Constraint Consensus (CC) methods within the Differential Evolution algorithm to solve the Economic Load Dispatch problem. During the evolution process, an adaptive mechanism is used to assign the infeasible solutions to each CC method with the emphasis on the best performing one. The experimental results show that the proposed algorithm is not only able to reach the 100% feasibility ratio, but that it is also able to obtain better solutions in comparison to the state-of-the-art algorithms.

Large scale optimization problems are very challenging problems. Most of the recently developed optimization algorithms lose their efficiency when the dimensionality of the problems increases. Decomposing a large scale problem into smaller subproblems overcomes this drawback. However, if the large scale optimization problem contains dependent variables, they should be grouped into one subproblem to avoid a decrease in performance. In this paper, the Dependency Identification with Memetic Algorithm (DIMA) model is proposed for solving large scale optimization problems. The Dependency Identification (DI) technique identifies the best arrangement to group the dependent variables into smaller scale subproblems. These subproblems are then evolved using a Memetic Algorithm (MA) with a proposed self-directed Local Search (LS). As the subproblems of a nonseparable large scale problem may contain interdependent variables, the proposed model, DIMA, uses an Information Exchange Mechanism to maintain one value for all the instances of any independent variable in the different subproblems. A newly designed test suite of problems has been developed to evaluate the performance of DIMA. The first evaluation shows that the DI technique is competitive to other decomposition techniques in the literature in terms of consuming less computational resources and better performance. Another evaluation shows that DI makes the optimization of a decomposed large scale problem using DIMA as powerful as the optimization of a complete large scale problem using MA. This makes DIMA a promising optimization model for optimization problems which can be 10 times larger (or more) than the large scale optimization problems under consideration in this paper.

An effective approach in the application of computational intelligence to mind-games is neuro-evolution. Neural networks are efficient at autonomous learning and pattern recognition tasks, which has led to many outstanding accomplishments in mind-games' playing ability. Neuro-evolution is a practical way that uses an evolutionary framework to train a neural network in a complicated context where credit assignment is hard. However, the neuro-evolution process may stagnate, or result in solutions with a limited quality. Potentially a cause for this problem are the limitations in understanding the neuro-activities as evolution progresses. A possible solution lies in unfolding the dynamics of the evolution process and the types of the strategies evolved as the evolution progresses; thus providing a diagnostic tool in real-time to identify neuro-dynamic causes of stagnation. Rule-extraction techniques are a notable solution to understanding the networks evolved. However, the extracted rules lack the necessary expressiveness to explain game-playing strategies. We call these rules a syntactic representation of the network that lacks semantic power. In this paper, we will present a methodology whereby a computational environment is used to unfold the evolution of a mind-game neuro-player; thus providing semantic power. Within this environment, we propose to extend the role of computer players to act as a “cognitive” functionality model, thus providing deeper kinds of explanations. We use the game of Go to demonstrate the functionality of the methodology. We then demonstrate that this methodology is successful in determining the types of strategies evolved in a neural Go player, and in monitoring the dynamics of the evolution.

In this paper, we have proposed a progressive alignment method using a genetic algorithm for multiple sequence alignment, named GAPAM. We have introduced two new mechanisms to generate an initial population: the first mechanism is to generate guide trees with randomly selected sequences and the second is shuffling the sequences inside such trees. Two different genetic operators have been implemented with GAPAM. To test the performance of our algorithm, we have compared it with existing well-known methods, such as PRRP, CLUSTALX, DIALIGN, HMMT, SB_PIMA, ML_PIMA, MULTALIGN, and PILEUP8, and also other methods, based on genetic algorithms (GA), such as SAGA, MSA-GA, and RBT-GA, by solving a number of benchmark datasets from BAliBase 2.0. To make a fairer comparison with the GA based algorithms such as MSA-GA and RBT-GA, we have performed further experiments covering all the datasets reported by those two algorithms. The experimental results showed that GAPAM achieved better solutions than the others for most of the cases, and also revealed that the overall performance of the proposed method outperformed the other methods mentioned above.

Over the last two decades, many Genetic Algorithms have been introduced for solving Constrained Optimization Problems (COPs). Due to the variability of the characteristics in different COPs, none of these algorithms performs consistently over a range of problems. In this paper, we introduce a Genetic Algorithm with a new multi-parent crossover for solving a variety of COPs. The proposed algorithm also uses a randomized operator instead of mutation and maintains an archive of good solutions. The algorithm has been tested by solving the 36 test instances, introduced in the CEC2010 constrained optimization competition session. The results show that the proposed algorithm performs better than the state-of-the-art algorithms.

Over the last two decades, many Genetic Algorithms have been introduced for solving optimization problems. Due to the variability of the characteristics in different optimization problems, none of these algorithms performs consistently over a range of problems. In this paper, we introduce a GA with a new multi-parent crossover for solving a variety of optimization problems. The proposed algorithm also uses both a randomized operator as mutation and maintains an archive of good solutions. The algorithm has been applied to solve the set of real world problems proposed for the IEEE-CEC2011 evolutionary algorithm competition.

Over the last two decades, many Differential Evolution (DE) strategies have been introduced for solving Optimization Problems. Due to the variability of the characteristics in optimization problems, no single DE algorithm performs consistently over a range of problems. In this paper, for a better coverage of problem characteristics, we introduce a DE algorithm framework that uses multiple search operators in each generation. The appropriate mix of the search operators, for any given problem, is determined adaptively. The proposed algorithm has been applied to solve the set of real world numerical optimization problems introduced for a special session of CEC2011.

Due to the variability of the characteristics of different Constrained Optimization Problems, no single Differential Evolution strategy, with no single constraint handling technique, performs consistently over a range of problems. In this paper, for a better coverage of the problem characteristics, we introduce a DE algorithm that uses multiple search operators and constraint handling techniques. In the proposed algorithm, initially each individual is assigned a random combination of operators. After a certain number of generations, the improvement made by each combination is recorded, and the best combination is then assigned to more and more individuals, while each of the other individuals are assigned a random combination. To accelerate the convergence of the proposed algorithm, a local search procedure is also applied to selected individuals. The algorithm has been tested by solving 18 test problems, with 10D and 30D. The results showed that the proposed algorithm is superior to state of the art algorithms.

Solving a Constrained Optimization Problem (COP) is much more challenging than its unconstrained counterpart. In solving COPs, the feasibility of a solution is a prime condition that requires the conversion of one or more infeasible individuals to feasible individuals. In this paper, to encourage the effective movement of infeasible individuals towards a feasible region, we introduce a Constraint Consensus (CC) method within the Differential Evolution (DE) algorithm for solving COPs. The algorithm has been tested by solving 13 well-known benchmark problems. The experimental results show that the solutions are competitive, if not better, as compared to the state of the art algorithms.

BACKGROUND: Many Bioinformatics studies begin with a multiple sequence alignment as the foundation for their research. This is because multiple sequence alignment can be a useful technique for studying molecular evolution and analyzing sequence structure relationships. RESULTS: In this paper, we have proposed a Vertical Decomposition with Genetic Algorithm (VDGA) for Multiple Sequence Alignment (MSA). In VDGA, we divide the sequences vertically into two or more subsequences, and then solve them individually using a guide tree approach. Finally, we combine all the subsequences to generate a new multiple sequence alignment. This technique is applied on the solutions of the initial generation and of each child generation within VDGA. We have used two mechanisms to generate an initial population in this research: the first mechanism is to generate guide trees with randomly selected sequences and the second is shuffling the sequences inside such trees. Two different genetic operators have been implemented with VDGA. To test the performance of our algorithm, we have compared it with existing well-known methods, namely PRRP, CLUSTALX, DIALIGN, HMMT, SB_PIMA, ML_PIMA, MULTALIGN, and PILEUP8, and also other methods, based on Genetic Algorithms (GA), such as SAGA, MSA-GA and RBT-GA, by solving a number of benchmark datasets from BAliBase 2.0. CONCLUSIONS: The experimental results showed that the VDGA with three vertical divisions was the most successful variant for most of the test cases in comparison to other divisions considered with VDGA. The experimental results also confirmed that VDGA outperformed the other methods considered in this research.

We investigate interactions between evolution, development and lifelong layered learning in a combination we call evolutionary developmental evaluation (EDE), using a specific implementation, developmental tree-adjoining grammar guided genetic programming (GP). The approach is consistent with the process of biological evolution and development in higher animals and plants, and is justifiable from the perspective of learning theory. In experiments, the combination is synergistic, outperforming algorithms using only some of these mechanisms. It is able to solve GP problems that lie well beyond the scaling capabilities of standard GP. The solutions it finds are simple, succinct, and highly structured. We conclude this paper with a number of proposals for further extension of EDE systems.

The job scheduling problem (JSP) is considered as one of the complex combinatorial optimization problems. In this paper, we have developed a hybrid Genetic Algorithm (HGA), which improves the performance of GAs when solving JSPs. We have also modified the developed algorithm to study JSPs under the machine unavailability condition. We have considered two types of machine unavailability. Firstly, where the unavailability information is available in advance (predictive) and, secondly, where the information is known after a real breakdown (reactive). We have shown that the revised schedule is mostly able to recover if the disruptions occur during the early stages of a schedule.

Multiple sequence alignment is one of the most important issues in molecular biology as it plays an important role such as in life saving drug design. In this paper, we divide given sequences into two or more subsequences and then combine them together in order to find better multiple sequence alignments by applying a new GA based approach to the combined sequences. We also introduce new ways of generating an initial population and of applying the genetic operators. We have carried out experiments for the BAliBASE benchmark database using the sum of pair objective function with the PAM250 score matrix. To evaluate our proposed approach, we have compared with well known methods such as T-Coffee, MUSCLE, MAFFT and ProbCons. The experimental results show that better multiple sequence alignments may be obtained with higher number of divisions, however the computation time increases with the number of decompositions. The overall performance of the proposed Decomposition with GA (DGA) method is better than the existing methods and the GA method (without decompositions).

This paper investigates the use of a framework of local models in the context of noisy evolutionary multi-objective optimization. Within this framework, the search space is explicitly divided into several nonoverlapping hyperspheres. A direction of improvement, which is related to the average performance of the spheres, is used for moving solutions within each sphere. This helps the local models to filter noise and increase the robustness of the evolutionary algorithm in the presence of noise. A wide range of noisy problems we used for testing and the experimental results demonstrate the ability of local models to better filter noise in comparison with that of global models.

Large scale constrained optimization problem solving is a challenging research topic in the optimization and computational intelligence domain. This paper examines the possible division of computational tasks, into smaller interacting components, in order to effectively solve constrained optimization problems in the continuous domain. In dividing the tasks, we propose problem decomposition, and the use of GAs as the solution approach. In this paper, we consider problems with block angular structure with or without overlapping variables. We decompose not only the problem but also the chromosome as suitable for different components of the problem. We also design a communication process for exchanging information between the components. The research shows an approach of dividing computation tasks, required in solving large scale optimization problems, which can be processed in parallel machines. A number of test problems have been solved to demonstrate the use of the proposed approach. The results are very encouraging.

The quality of individuals in the initial population influences the performance of evolutionary algorithms, especially when the feasible region of the constrained optimization problems is very tiny in comparison to the entire search space. Too much diversity of the population may cost huge processing time; on the other hand the algorithms may trap into local optima for lack of diversity. This paper proposes a simple method to improve the quality of randomly generated initial solutions by sacrificing very little in diversity of the population. We introduce the method of search space reduction technique (SSRT) which is tested using four different existing EAs by solving a number of state-of-the-art test problems and a real world case problem. The experimental results show SSRT improves the solution qualities as well as speeding up the performance of the algorithm.

In this paper, we show some experimental results using Incremental Evaluation with Tree Adjoining Grammar Guided Genetic Programming (DEVTAG) on two symbolic regression problems, a benchmark polynomial fitting problem in genetic programming, and a Fourier series problem (sawtooth problem). In our pilot study, we compare results with standard Genetic Programming (GP) and the original Tree Adjoining Grammar Guided Genetic Programming (TAG3P). Our results on the two problems are good, outperforming both standard GP and the original TAG3P.

In this paper, we describe a new test problem for genetic programming (GP), ORDERTREE. We argue that it is a natural analogue of ONEMAX, a popular GA test problem, and that it also avoids some of the known weaknesses of other benchmark problems for Genetic Programming. Through experiments, we show that the difficulty of the problem can be tuned not only by increasing the size of the problem, but also by increasing the non-linearity in the fitness structure.

Standard tree-based genetic programming suffers from a structural difficulty problem in that it is unable to search effectively for solutions requiring very full or very narrow trees. This deficiency has been variously explained as a consequence of restrictions imposed by the tree structure or as a result of the numerical distribution of tree shapes. We show that by using a different tree-based representation and local (insertion and deletion) structural modification operators, that this problem can be almost eliminated even with trivial (stochastic hill-climbing) search methods, thus eliminating the above explanations. We argue, instead, that structural difficulty is a consequence of the large step size of the operators in standard genetic programming, which is itself a consequence of the fixed-arity property embodied in its representation.

This paper compares the performance of anti-noise methods, particularly probabilistic and re-sampling methods, using NSGA2. It then proposes a computationally less expensive approach to counteracting noise using re-sampling and fitness inheritance. Six problems with different difficulties are used to test the methods. The results indicate that the probabilistic approach has better convergence to the Pareto optimal front, but it looses diversity quickly. However, methods based on re-sampling are more robust against noise but they are computationally very expensive to use. The proposed fitness inheritance approach is very competitive to re-sampling methods with much lower computational cost.

In evolutionary computation, genetic operators, such as mutation and crossover, are employed to perturb individuals to generate the next population. However these fixed, problem independent genetic operators may destroy the sub-solution, usually called building blocks, instead of discovering and preserving them. One way to overcome this problem is to build a model based on the good individuals, and sample this model to obtain the next population. There is a wide range of such work in genetic algorithms; but because of the complexity of the genetic programming (GP) tree representation, little work of this kind has been done in GP. In this paper, we propose a new method, grammar model-based program evolution (GMPE) to evolved GP program. We replace common GP genetic operators with a probabilistic context-free grammar (SCFG). In each generation, an SCFG is learnt, and a new population is generated by sampling this SCFG model. On two benchmark problems we have studied, GMPE significantly outperforms conventional GP, learning faster and more reliably.

In genetic programming (GP) and most other evolutionary computing approaches, the knowledge learned during the evolutionary processing is implicitly encoded in the population. A small family of approaches, known as estimation of distribution algorithms, learn this knowledge directly in the form of probability distributions. In this research, we proposed a new approach for program synthesis - program evolution with explicit learning (PEEL), belonging to this family. PEEL learns probability distributions from previous generations and stochastically generates new populations according to this distribution. PEEL is intrinsically different from GP systems because it abandons conventional GP genetic operators and does not maintain population. On the benchmark problems we have studied, this approach shows at least comparable performance to GP.

In this paper, we show some experimental results of tree-adjunct grammar-guided genetic programming (TAG3P) on the symbolic regression problem, a benchmark problem in genetic programming. We compare the results with genetic programming (GP) and grammar-guided genetic programming (GGGP). The results show that TAG3P significantly outperforms GP and GGGP on the target functions attempted in terms of the probability of success. Moreover, TAG3P still performed well when the structural complexity of the target function was scaled up.

The paper investigates the use of partial functions in genetic programming. Previous work (R.I. McKay, 2000), has shown that the convergent behaviour of populations of partial functions is very similar to that of populations of total functions. However the convergence rates of populations of partial functions have been slower. The results presented demonstrate a significant improvement in the rate of convergence of populations of partial functions, and indicate that partial functions represent a realistic alternative to total functions for a range of problems.