Search

Nowadays time series clustering is of great importance in manufacturing industries. Meanwhile, it is considerably challenging to achieve explainable solution as well as significant performance due to computation complexity and variable diversity. To efficaciously handle the difficulty, this paper presents a novel metaheuristic-based time series clustering method which can improve the effectiveness and logicality of existing clustering approaches. The proposed method collects candidate cluster references from hierarchical and partitional clustering through shape-based distance measure as well as dynamic time warping (DTW) on manufacturing time series data. By applying metaheuristics highlighting estimation of distribution algorithms (EDA), such as extended compact genetic algorithm (ECGA), on the collected candidate clusters, advanced cluster centroid combinations with minimal distances can be achieved. ECGA employs the least complicated and the most closely related probabilistic model structure regarding population space during generation cycle. This feature strengthens the comprehension of clustering results in how such optimal solutions were achieved. The proposed method was tested on real-world time series data, open to the public, from manufacturing industry, and showed noticeable performances compared to well-established methods. Accordingly, this paper demonstrates that obtaining both comprehensible result as well as prominent performance is feasible by employing metaheuristic techniques to time series data clustering methods. [ABSTRACT FROM AUTHOR]

Economic dispatch is an important issue in the management of power systems and is the current focus of specialists. In this paper, a new metaheuristic optimization algorithm is proposed, named Social Small Group Optimization (SSGO), inspired by the psychosocial processes that occur between members of small groups to solve real-life problems. The starting point of the SSGO algorithm is a philosophical conception similar to that of the social group optimization (SGO) algorithm. The novelty lies in the introduction of the small group concept and the modeling of individuals' evolution based on the social influence between two or more members of the small group. This conceptual framework has been mathematically mapped through a set of heuristics that are used to update the solutions, and the best solutions are retained by employing a greedy selection strategy. SSGO has been applied to solve the economic dispatch problem by considering some practical aspects, such as valve-point loading effects, sources with multiple fuel options, prohibited operating zones, and transmission line losses. The efficiency of the SSGO algorithm was tested on several mathematical functions (unimodal, multimodal, expanded, and composition functions) and on power systems of varying sizes (ranging from 10-units to 1280-units). The SSGO algorithm was compared with SGO and other algorithms belonging to various categories (such as: evolution-based, swarm-based, human behavior-based, hybrid algorithms, etc.), and the results indicated that SSGO outperforms other algorithms applied to solve the economic dispatch problem in terms of quality and stability of the solutions, as well as computation time. [ABSTRACT FROM AUTHOR]

In the dynamic smart grid landscape, accurate probabilistic forecasting of electric load is critical. This paper presents a novel 24-hour-ahead probabilistic load forecasting model by integrating quantile regression with a parallel convolutional neural network (CNN) and bidirectional gated recurrent unit (BiGRU) architecture. Carefully tuning hyperparameters can enhance model performance and generalization capability. Consequently, we propose an improved whale optimization algorithm for automatic hyperparameter tuning of the forecasting model. Case studies demonstrate the proposed method's superior performance over benchmark models in terms of average interval score and pinball loss. In addition, it exhibits valid coverage and tight interval bandwidths. The model provides precise short-term load forecasts to support robust smart grid planning and operations. [ABSTRACT FROM AUTHOR]

This paper studied the multilevel threshold image segmentation-based metaheuristics optimization methods and their applications. Image segmentation is a common problem in the image processing domain, and it is an essential process in image analysis, directly impacting image analysis results. Thresholding is one of the most manageable and extensively utilized methods for handling image segmentation problems. In this paper, four main parts are given; (1) We present the main procedures and definitions of the multilevel threshold image segmentation problem. The standard fitness function and the evaluation criteria are also given to facilitate the problem representation for the new researchers in this domain. (2) All the related works that have used optimization methods in solving the multilevel threshold image segmentation problems are presented in more detail, focusing on the image segmentation problem and its solutions. The given related works are outlined according to the used algorithms. (3) Comprehensive results and analysis of several well-known optimization algorithms are conducted to solve the multilevel threshold image segmentation problems. These comparative methods include Aquila Optimizer (AO), Whale Optimization Algorithm (WOA), Salp Swarm Algorithm (SSA), Arithmetic Optimization Algorithm (AOA), Particle Swarm Optimizer (PSO), Marine Predators Algorithm (MPA), Krill Herd Algorithm (KHA), Multi-verse Optimizer (MVO), and Gray Wolf Optimizer (GWO). Eight standard benchmark images are used to test the comparative methods. The results are evaluated using three standard measures: fitness function, PeakSignal-to-Noise Ratio (PSNR), and the Structural Similarity Index (SSIM). (4) Discussion, open challenging, and new trends are given to help the scholars in future research get near the common problems and defect in that domain. The collected data in this review has been taken from google scholar using the stander search method. The main keywords that have been used in the search are multilevel, threshold, image, segmentation, optimization, and algorithm. We covered all the published papers in detail according to the given information, focusing on finding the common problems that still need further investigation. Furthermore, future research directions based on recently evolving designs are outlined, which should undoubtedly aid current researchers and practitioners and pave the way for new researchers interested in multilevel threshold image segmentation to seek their research in the field. [ABSTRACT FROM AUTHOR]

Quantum-behaved Particle Swarm Optimization (QPSO) is a meta-heuristic optimization algorithm, which is widely used in many research fields and practical problems due to its flexibility and low computational cost. However, the existing QPSO algorithms and their variants still have problems such as insufficient search capabilities, lack of adaptivity, and prone to stagnation. This paper proposes a novel ensemble algorithm, ACQPSOW-HGS, based on Quantum-behaved Particle Swarm Optimization (QPSO) and Hunger Games Search (HGS). By combining three improvements and introducing three hybrid strategies, our algorithm has made a comprehensive development, effectively improving the stability and solution accuracy in a large number of test functions and the parameter identification application, which is superior compared with many existing algorithms. First, we design the Weibull distribution random number generation operator, the distance-guided adaptive control technique, and the chaotic update mechanism to deal with the weak randomness, insufficient adaptability, and susceptibility to stagnation of the original QPSO algorithm, respectively. Integrating the above improvements, ACQPSOW is proposed as an improved variant of QPSO. Second, the proposed ensemble algorithm ACQPSOW-HGS is built on ACQPSOW and HGS and combined with specific hybrid strategies to add population diversity and improve search efficiency, including the Selection-Crossover-Mutation mechanism, the elite local search mechanism, and the information exchange mechanism. Finally, the experiments, on 23 benchmark functions and the IEEE CEC 2017 test suite, demonstrate that ACQPSOW-HGS outperforms comparison algorithms in terms of convergence speed and solution accuracy through non-parametric statistical tests. Moreover, ACQPSOW-HGS was applied to the fractional-order hyper-chaotic financial system for parameter identification to illustrate the applicability and robustness in solving real-world problems. [ABSTRACT FROM AUTHOR]

Due to the lack of language analysis and understanding algorithms for kinematics problems, researches on automatic algorithms for tutorial systems are mainly concentrated on mathematics and physical circuits, and these algorithms are still represented by frame solution and semantic analysis. Additionally, these methods need to design rule templates to understand the complex text, which leads to the low efficiency of solving. Although deep learning (DL) have be applied to machine answers, but it is difficult to achieve the integration of problem understanding, reasoning, and solving through a generic framework. Therefore, this paper proposes a high-performance algorithm to understand and solve kinematics problems. By dividing solving kinematics problems into two stages: understanding and solving, we propose a unified framework for solving kinematic problems. Firstly, we transform understanding into relation extraction (RE), and propose a RE algorithm combining named entity recognition (NER) and first order logic (FOL) based on a novel tagging schema to extract overlapping relation in kinematics texts. For the solving stage, a backward chain reasoning algorithm based on meta-information is presented to solve kinematics problems. Additionally, three levels of comprehension and two conditions for measuring levels of comprehension are proposed to evaluate the performance of the proposed system. Finally, based on the evaluation metrics proposed in this paper, verification experiments are carried out on a dataset of kinematic problems from an authoritative source. And the results show that the proposed algorithm successfully solves 92.52% of the kinematic problems, which is higher than the baseline algorithms. [ABSTRACT FROM AUTHOR]

The uncapacitated facility location problem (UFLP) is a well-known combinatorial optimization problem that finds practical applications in several fields, such as logistics and telecommunication networks. While the existing literature primarily focuses on the deterministic version of the problem, real-life scenarios often involve uncertainties like fluctuating customer demands or service costs. This paper presents a novel algorithm for addressing the UFLP under uncertainty. Our approach combines a tabu search metaheuristic with path-relinking to obtain near-optimal solutions in short computational times for the determinisitic version of the problem. The algorithm is further enhanced by integrating it with simulation techniques to solve the UFLP with random service costs. A set of computational experiments is run to illustrate the effectiveness of the solving method. [ABSTRACT FROM AUTHOR]

This work explores the effectiveness and robustness of quantum computing by conjoining the principles of quantum computing with the conventional computational paradigm for the automatic clustering of colour images. In order to develop such a computationally efficient algorithm, two population-based meta-heuristic algorithms, viz., Particle Swarm Optimization (PSO) algorithm and Enhanced Particle Swarm Optimization (EPSO) algorithm have been consolidated with the quantum computing framework to yield the Quantum Inspired Particle Swarm Optimization (QIPSO) algorithm and the Quantum Inspired Enhanced Particle Swarm Optimization (QIEPSO) algorithm, respectively. This paper also presents a comparison between the proposed quantum inspired algorithms with their corresponding classical counterparts and also with three other evolutionary algorithms, viz., Artificial Bee Colony (ABC), Differential Evolution (DE) and Covariance Matrix Adaption Evolution Strategies (CMA-ES). In this paper, twenty different sized colour images have been used for conducting the experiments. Among these twenty images, ten are Berkeley images and ten are real life colour images. Three cluster validity indices, viz., PBM, CS-Measure (CSM) and Dunn index (DI) have been used as objective functions for measuring the effectiveness of clustering. In addition, in order to improve the performance of the proposed algorithms, some participating parameters have been adjusted using the Sobol's sensitivity analysis test. Four segmentation evaluation metrics have been used for quantitative evaluation of the proposed algorithms. The effectiveness and efficiency of the proposed quantum inspired algorithms have been established over their conventional counterparts and the three other competitive algorithms with regards to optimal computational time, convergence rate and robustness. [ABSTRACT FROM AUTHOR]

Ontology, presentation of the world clearly, is a conceptualized and formalized model of knowledge. Knowledge interpretation is subjective, organizations or individuals have different expressions the same knowledge, i.e., ontology heterogeneity. It has arisen as a challenge on the Semantic Web (SW). Ontology meta-matching (OMM) technology can map two body of knowledge in the same domain effectively, and then ontology heterogeneity is addressed. The OMM is generally considered as a nonlinear global optimization problem to achieve alignment. As one of the meta-heuristic algorithms, fireworks algorithm (FA) has a distinct advantage in convergence speed and optimization precision. However, the population size of FA is usually not fixed during the exploitation and exploration process. The sparks are generated by the interaction and cooperation between fireworks, and are larger than the number of fireworks. This search behavior leads that the computational memory is costly. In paper, a novel compact fireworks algorithm (CFA) is proposed to reduce the memory consumption of FA. In CFA the distribution of populations is represented by a probabilistic model, i.e., virtual populations, and two operators are proposed to simulate the process of fireworks explosion and update disturbance vector respectively. The initialization has a great influence on the exploitation and exploration of meta-heuristic algorithm. In addition, a group of high quality initialization can often improve the optimization ability of the algorithm. In paper a novel heuristic initialization strategy (HIS) is designed to obtain a better set of initial population by introducing concept of accurateness, pseudo-weight and barycenter. In addition, HIS is more suitable for higher dimensional decision space of ontology meta-matching by a more convenient coding scheme. Finally, a non-reference matching optimization model, maximal confidence alignment model (MCAM), is proposed to evaluate the quality of alignment. In the experiment, the benchmark track of Ontology Alignment Evaluation Initiative (OAEI) is used. Experimental results demonstrate the effectiveness of the proposed methods, and the memory consumption of CFA reduces by 52.5% than FA. [ABSTRACT FROM AUTHOR]

Over the years, there have been many variations of the Vehicle Routing Problem created to fit the actual needs of society, one of which is the Electric Vehicle Routing Problem (EVRP). EVRP is a more complex and challenging combinatorial optimization than the conventional vehicle routing problem. This paper considers a specific model for the tram routing problem and proposes a clustering-inspired greedy search algorithm GS. GS algorithm aims to cluster charging routes and greedily search charging stations for the optimal route output. In this paper, we purposely implement GS into a meta-heuristic genetic algorithm GA to utilize GA's finding a globally optimal, leading to the formulation of the GSGA algorithm. To evaluate performance, we use a benchmark dataset found in the CEC-12 Tram Routing Problem CEC-12 Competition at the World Congress on Computational Intelligence (WCCI) 2020. The experiment evaluates GS's effectiveness when applied to other algorithms such as genetic algorithms and simulated annealing. The experiments results show that our proposed algorithm has better solution quality than previous algorithms. [ABSTRACT FROM AUTHOR]

Meta-heuristic algorithms have been extensively utilized in feature selection tasks because they can obtain the global optimal solution. However, the meta-heuristic algorithm will take too much time in the face of a large number of samples. Although most of the studies compromise to approximate optimal solutions for avoiding time-consuming problems, a new problem with reduced classification performance, especially classification stability, is then generated. Aiming to above problems, this paper proposes a new feature selection framework. First, this framework exploits a voting ensemble strategy to improve classification stability by reducing the impact of misclassified labels on the overall classification results. Second, the framework uses a data perturbation strategy to enhance classification accuracy. In particular, the data perturbation strategy is able to generate more neighborhood relationships in the dataset, which could reveal the distribution of various features of the samples. A voting ensemble of different feature distributions is capable of extracting more information from the dataset, then the initially misclassified samples are more likely to be returned to the correct classification. Third, the framework takes a random sampling accelerator into account to solve the problem of excessive time consumption by reducing the size of the search sample space. Finally, for the sake of verifying the effectiveness of the proposed framework, four meta-heuristic feature selection methods based on a neighborhood rough set are compared on 20 datasets. The experimental results indicate that our framework could improve classification performance and accelerate feature selection, particularly in confronting large sample sizes. [ABSTRACT FROM AUTHOR]

Facility location models involve identifying locations for facilities that provide services to the customers which are also called demand points. The p-median problem is a facility location problem which deals with locating p facilities in such a way that the sumtotal of demand-weighted distances between each demand point and its respective closest facility is minimized. The p-median problem does not take into account the possibility of failure of the facilities, but rather considers that the facilities once located will always be available to serve the customers or demand points. But, in reality, some of the facilities may face unpredicted disruptions, thereby forcing the customers to seek services from other functioning facilities. The reliability p-median problem (RpMP) concerns with locating facilities which minimize the cost while considering the cost of facility failures. In this paper, we have proposed a hyper-heuristic approach with naive Bayes classifier for the RpMP and compared its performance on standard benchmark instances with two best performing approaches for RpMP, viz. a genetic algorithm and a scatter search approach available in the literature. The results show the effectiveness of our approach in terms of the solution quality. [ABSTRACT FROM AUTHOR]

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable, they should not be used in critical or high-risk applications. To address this issue, researchers and businesses have been focusing on finding ways to improve the explainability of complex ML systems, and several such methods have been developed. Indeed, there are so many developed techniques that it is difficult for practitioners to choose the best among them for their applications, even when using evaluation metrics. As a result, the demand for a selection tool, a meta-explanation technique based on a high-quality evaluation metric, is apparent. In this paper, we present a local meta-explanation technique which builds on top of the truthfulness metric, which is a faithfulness-based metric. We demonstrate the effectiveness of both the technique and the metric by concretely defining all the concepts and through experimentation. [ABSTRACT FROM AUTHOR]

Over recent decades, research in Artificial Intelligence (AI) has developed a broad range of approaches and methods that can be utilized or adapted to address complex optimization problems. As real-world problems get increasingly complicated, this requires an effective optimization method. Various meta-heuristic algorithms have been developed and applied in the optimization domain. This paper used and ameliorated a promising meta-heuristic approach named Crow Search Algorithm (CSA) to address numerical optimization problems. Although CSA can efficiently optimize many problems, it needs more searchability and early convergence. Its positioning updating process was improved by supporting two adaptive parameters: flight length (fl) and awareness probability (AP) to tackle these curbs. This is to manage the exploration and exploitation conducts of CSA in the search space. This process takes advantage of the randomization of crows in CSA and the adoption of well-known growth functions. These functions were recognized as exponential, power, and S-shaped functions to develop three different improved versions of CSA, referred to as Exponential CSA (ECSA), Power CSA (PCSA), and S-shaped CSA (SCSA). In each of these variants, two different functions were used to amend the values of fl and AP. A new dominant parameter was added to the positioning updating process of these algorithms to enhance exploration and exploitation behaviors further. The reliability of the proposed algorithms was evaluated on 67 benchmark functions, and their performance was quantified using relevant assessment criteria. The functionality of these algorithms was illustrated by tackling four engineering design problems. A comparative study was made to explore the efficacy of the proposed algorithms over the standard one and other methods. Overall results showed that ECSA, PCSA, and SCSA have convincing merits with superior performance compared to the others. [ABSTRACT FROM AUTHOR]

The classical influence maximization (IM) in social network analysis aims at selecting a group of influential nodes as seed so that the number of nodes activated by the set is maximized when the spreading process completes. The single stage seeding problem would ignite all the seeds at the very beginning of the diffusion and let the influence diffuses passively with no additional supervision. However, the effect of scheduled seeding activation operations on improving the marginal profit tends to be ignored. More importantly, the practical scenarios that need external seeding activities can not be well depicted. In this paper, seed activation strategies are investigated for the adaptive influence maximization (AIM) problem under general feedback models. A novel bio-inspired meta-heuristic policy named discrete scheduled particle swarm optimization (DSPSO) is proposed to tackle the intractable problem confronted by AIM, i.e., which nodes need to be ignited at the right time during the process of influence spreading? Following the framework, the proposed policy selects optimal size of nodes into the seed set in each round to ensure the continuation of the spreading process. Dynamic encoding mechanism for the particle individuals is constructed. To make a full exploration of the solution space, a local search strategy specifically for the discrete network topology is implemented on the historical best individuals of the swarm. Extensive experiments on four social networks under different activation feedback models demonstrate the advantage of the scheduled seeding mechanism over the single stage seeding approaches, and show that the proposed DSPSO outperforms the existing greedy strategy as well as the topological heuristics. [ABSTRACT FROM AUTHOR]

Millions of affected people and thousands of victims are consequences of earthquakes, every year. Therefore, it is necessary to prepare a proper preparedness and response planning. The objectives of this paper are i) minimizing the expected value of the total costs of relief supply chain, ii) minimizing the maximum number of unsatisfied demands for relief staff and iii) minimizing the total probability of unsuccessful evacuation in routes. In this paper, a scenario based stochastic multi-objective location-allocation-routing model is proposed for a real humanitarian relief logistics problem which focused on both pre- and post-disaster situations in presence of uncertainty. To cope with demand uncertainty, a simulation approach is used. The proposed model integrates these two phases simultaneously. Then, both strategic and operational decisions (pre-disaster and post-disaster), fairness in the evacuation, and relief item distribution including commodities and relief workers, victim evacuation including injured people, corpses and homeless people are also considered simultaneously in this paper. The presented model is solved utilizing the Epsilon-constraint method for small- and medium-scale problems and using three metaheuristic algorithms for the large-scale problem (case study). Empirical results illustrate that the model can be used to locate the shelters and relief distribution centers, determine appropriate routes and allocate resources in uncertain and real-life disaster situations. [ABSTRACT FROM AUTHOR]

This paper provides an in-depth literature review of the Black Hole Algorithm (BHA) which is considered as a recent metaheuristic. BHA has been proven to be very efficient in different applications. There has been several modifications and variants of this algorithm in the literature, so this work reviews various variants of the BHA. The applications of BHA in engineering problems, clustering, task scheduling, image processing, etc. have been thoroughly reviewed as well. This review article sheds lights on the pros and cons of this algorithm and enables finding a right variant of this algorithm for a certain application area. The paper concludes with an in-depth future direction. [ABSTRACT FROM AUTHOR]

Back propagation (BP) is widely used for parameter search of fully-connected layers in many neural networks. Although BP has the potential of quickly converging to a solution, due to its gradient-based nature, it tends to fall into a local optimum. Metaheuristics such as evolutionary computation (EC) techniques, as gradient-free methods, may have excellent global search capability due to their stochastic nature. However, these techniques tend to perform worse than BP in terms of convergence speed. In this paper, a hybrid gradient descent search algorithm (HGDSA) is proposed for training the parameters in fully-connected neural networks. HGDSA initially searches the space extensively by means of an ensemble of gradient descent strategies in the early stage and then uses BP as an exploitative local search operator. Moreover, a self-adaptive method which selects strategies and updates the learning rates of strategies has been designed and embedded in the global search operators to prevent stagnation in local optima. To verify the effectiveness of HGDSA, experiments were performed on eleven classification datasets. Experimental results demonstrate that the proposed HGDSA possesses both powerful global and local search abilities. Furthermore, the proposed approach appears to be promising also on high-dimensional datasets. [ABSTRACT FROM AUTHOR]

Software Fault Prediction (SFP) is an important process to detect the faulty components of the software to detect faulty classes or faulty modules early in the software development life cycle. In this paper, a machine learning framework is proposed for SFP. Initially, pre-processing and re-sampling techniques are applied to make the SFP datasets ready to be used by ML techniques. Thereafter seven classifiers are compared, namely K-Nearest Neighbors (KNN), Naive Bayes (NB), Linear Discriminant Analysis (LDA), Linear Regression (LR), Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF). The RF classifier outperforms all other classifiers in terms of eliminating irrelevant/redundant features. The performance of RF is improved further using a dimensionality reduction method called binary whale optimization algorithm (BWOA) to eliminate the irrelevant/redundant features. Finally, the performance of BWOA is enhanced by hybridizing the exploration strategies of the grey wolf optimizer (GWO) and harris hawks optimization (HHO) algorithms. The proposed method is called SBEWOA. The SFP datasets utilized are selected from the PROMISE repository using sixteen datasets for software projects with different sizes and complexity. The comparative evaluation against nine well-established feature selection methods proves that the proposed SBEWOA is able to significantly produce competitively superior results for several instances of the evaluated dataset. The algorithms' performance is compared in terms of accuracy, the number of features, and fitness function. This is also proved by the 2-tailed P-values of the Wilcoxon signed ranks statistical test used. In conclusion, the proposed method is an efficient alternative ML method for SFP that can be used for similar problems in the software engineering domain. [ABSTRACT FROM AUTHOR]

In this paper, a new population initialization method for metaheuristic algorithms is proposed. In our approach, the initial set of candidate solutions is obtained through the sampling of the objective function with the use of the Metropolis–Hastings technique. Under this method, the set of initial solutions adopts a value close to the prominent values of the objective function to be optimized. Different from most of the initialization methods that consider only spatial distribution, in our algorithm, the initial points represent promising regions of the search space, which deserve to be exploited to identify the global optimum. These characteristics allow the proposed approach obtains a faster convergence and improves the quality of the produced solutions. With the objective to demonstrate the capacities of our initialization method, it has been embedded in the classical Differential Evolution algorithm. To evaluate its performance, the complete system has been tested in a set of representative benchmark functions extracted from several datasets. Experimental results show that the proposed technique presents a better convergence speed and an increment in the quality of the solutions than other similar approaches. [ABSTRACT FROM AUTHOR]

With the large-scale integration of wind power into the power grid, improving the wind speed prediction accuracy is of great significance for promoting the consumption of renewable energy. In this paper, a hybrid prediction method for multi-step wind speed prediction based on the empirical wavelet transform (EWT), multi-objective modified seagull optimization algorithm (MOMSOA), and multi-kernel extreme learning machine (MKELM) is proposed. First, EWT is used to decompose the nonstationary wind speed data into a set of stationary subsequences. Then, each subsequence of wind speed is predicted by the MKELM, and the MKELM network is optimized by the MOMSOA newly proposed in this study. Finally, the inverse empirical wavelet transform (IEWT) is adopted to reconstruct the prediction results into the final wind speed prediction results. To assess the performance of the proposed combined model, four groups of experiments are carried out on four wind speed sequences, and a comparative analysis is made with 16 comparison models. The models involved in the investigation are discussed comprehensively in terms of significance and stability. The results demonstrate that the developed combined model outperforms the comparison models. [ABSTRACT FROM AUTHOR]

The whale optimization algorithm (WOA) is a simple structured and easily implemented swarm-based algorithm inspired by the unique bubble-net feeding method of humpback whales. Past studies have shown that WOA performs well in a number of optimization problems. However, it is difficult for WOA to completely free itself from the problems of insufficient convergence accuracy and premature convergence when solving global optimization problems. To address these issues, a hybrid whale optimization algorithm based on symbiotic strategy (HWOAMS) is proposed in this paper. The main idea of the proposed method is to combine the improved symbiotic organisms search algorithm (SOS) with the whale optimization algorithm thus enhancing the search ability of WOA. First, an improved symbiotic phase based on Lévy flight and chaos strategy is introduced into the exploration process to enhance the global search capability; Second, an improved mutualism phase based on Brownian motion is used instead of the original shrinking encircling phase to achieve better local exploitation. Third, an improved parasitic phase based on a modified global optimal spiral operator strategy is embedded in the spiral updating position phase to help the algorithm further improve the exploitation efficiency and convergence accuracy. Finally, a global search strategy is proposed to help the algorithm better balance exploration and exploitation. To establish the effectiveness of the new algorithm, extensive simulation experiments are conducted on HWOAMS using the classical function test set, the CEC 2019 function set and four classical engineering problems. Numerical evaluation results indicate that HWOAMS outperforms 18 other algorithms in terms of local optimum avoidance ability and convergence accuracy in a majority of cases, and has better search performance. [ABSTRACT FROM AUTHOR]

This paper proposes a firefighting multi strategy marine predators algorithm(FMMPA), which uses opposition-based learning (OBL) to make the initial population more uniform, introduces adaptive weight factors to balance exploration ability and exploitation ability, and combines DE/RAND/1 mutation mechanism to increase population diversity. Another purpose of our FMMPA is to add fire weighted selection, including flame edge suppression, combustion unit continuity and wind direction, as the rescue algorithm of forest fire rescue assemble to deal with the allocation of firefighting aircraft in forest fire rescue. We conduct this study based on real maps and the capabilities of the real firefighting aircraft. Compared with ten algorithms, the experimental results show that the proposed FMMPA has superior performance in reducing rescue time, controlling the spread speed of fire edge and minimizing loss cost. [ABSTRACT FROM AUTHOR]

This paper proposes new improved binary versions of the Sine Cosine Algorithm (SCA) for the Feature Selection (FS) problem. FS is an essential machine learning and data mining task of choosing a subset of highly discriminating features from noisy, irrelevant, high-dimensional, and redundant features to best represent a dataset. SCA is a recent metaheuristic algorithm established to emulate a model based on sine and cosine trigonometric functions. It was initially proposed to tackle problems in the continuous domain. The SCA has been modified to Binary SCA (BSCA) to deal with the binary domain of the FS problem. To improve the performance of BSCA, three accumulative improved variations are proposed (i.e., IBSCA1, IBSCA2, and IBSCA3) where the last version has the best performance. IBSCA1 employs Opposition Based Learning (OBL) to help ensure a diverse population of candidate solutions. IBSCA2 improves IBSCA1 by adding Variable Neighborhood Search (VNS) and Laplace distribution to support several mutation methods. IBSCA3 improves IBSCA2 by optimizing the best candidate solution using Refraction Learning (RL), a novel OBL approach based on light refraction. For performance evaluation, 19 real-wold datasets, including a COVID-19 dataset, were selected with different numbers of features, classes, and instances. Three performance measurements have been used to test the IBSCA versions: classification accuracy, number of features, and fitness values. Furthermore, the performance of the last variation of IBSCA3 is compared against 28 existing popular algorithms. Interestingly, IBCSA3 outperformed almost all comparative methods in terms of classification accuracy and fitness values. At the same time, it was ranked 15 out of 19 in terms of number of features. The overall simulation and statistical results indicate that IBSCA3 performs better than the other algorithms. [ABSTRACT FROM AUTHOR]

This paper proposes a novel swarm intelligence-based metaheuristic called as sea-horse optimizer (SHO), which is inspired by the movement, predation and breeding behaviors of sea horses in nature. In the first two stages, SHO mimics different movements patterns and the probabilistic predation mechanism of sea horses, respectively. In detail, the movement modes of a sea horse are divided into floating spirally affected by the action of marine vortices or drifting along the current waves. For the predation strategy, it simulates the success or failure of the sea horse for capturing preys with a certain probability. Furthermore, due to the unique characteristic of the male pregnancy, in the third stage, the proposed algorithm is designed to breed offspring while maintaining the positive information of the male parent, which is conducive to increase the population diversity. These three intelligent behaviors are mathematically expressed and constructed to balance the local exploitation and global exploration of SHO. The performance of SHO is evaluated on 23 well-known functions and CEC2014 benchmark functions compared with six state-of-the-art metaheuristic algorithms. Finally, five real-world engineering problems are utilized to test the effectiveness of SHO. The experimental results demonstrate that SHO is a high-performance optimizer and positive adaptability to deal with constraint problems. SHO source code is available from: https://www.mathworks.com/matlabcentral/fileexchange/115945-sea-horse-optimizer [ABSTRACT FROM AUTHOR]

Mobile ad hoc network (MANET) is the collection of mobile nodes, which might act as the hosts and routers in an ad hoc network. They can self-organize dynamically without using any pre-established communications. Mobile nodes alter their position based on certain constraints while transmitting the packets. Here, the location or position-based routing is essential to transmit the packet which intends to enhance the network lifetime. This paper proposes the implementation of a new geographic routing protocol in MANET, where the optimal route selection process is carried out by Hybrid Roxes Whale Optimization (HRWO) algorithm that hybridizes the Whale Optimization Algorithm (WOA) and Rock Hyraxes Swarm Optimization (RHSO) algorithm. Moreover, the optimal routing is done by considering several parameters like the average distance between nodes (mobility-related information based on the location), delay, link lifetime, risk evaluation, and packet loss, respectively. At the end, the performance of the adopted routing approach is evaluated over other traditional schemes based on various metrics like average distance, packet loss, delay, risk, and link lifetime, respectively. [ABSTRACT FROM AUTHOR]

The detection of software vulnerabilities is considered a vital problem in the software security area for a long time. Nowadays, it is challenging to manage software security due to its increased complexity and diversity. So, vulnerability detection applications play a significant part in software development and maintenance. The ability of the forecasting techniques in vulnerability detection is still weak. Thus, one of the efficient defining features methods that have been used to determine the software vulnerabilities is the metaheuristic optimization methods. This paper proposes a novel software vulnerability prediction model based on using a deep learning method and SYMbiotic Genetic algorithm. We are first to apply Diploid Genetic algorithms with deep learning networks on software vulnerability prediction to the best of our knowledge. In this proposed method, a deep SYMbiotic-based genetic algorithm model (DNN-SYMbiotic GAs) is used by learning the phenotyping of dominant-features for software vulnerability prediction problems. The proposed method aimed at increasing the detection abilities of vulnerability patterns with vulnerable components in the software. Comprehensive experiments are conducted on several benchmark datasets; these datasets are taken from Drupal, Moodle, and PHPMyAdmin projects. The obtained results revealed that the proposed method (DNN-SYMbiotic GAs) enhanced vulnerability prediction, which reflects improving software quality prediction. [ABSTRACT FROM AUTHOR]

Bag-of-Tasks is a well-known model that processes big-data applications supporting embarrassingly parallel jobs with independent tasks. Scheduling Bag-of-Tasks in a dynamic multi-cloud environment is an NP-hard problem that has attracted a lot of attention in the last years. Such a problem can be modeled using a bi-level optimization framework due to its hierarchical scheme. Motivated by this issue, in this paper, an efficient bi-level multi-follower algorithm, based on hybrid metaheuristics, is proposed to solve the multi-objective budget-constrained dynamic Bag-of-Tasks scheduling problem in a heterogeneous multi-cloud environment. In our proposed model, the objective function differs depending on the scheduling level: The upper level aims to minimize the makespan of the whole Bag-of-Tasks under budget constraints; while each follower aims to minimize the makespan and the execution cost of tasks belonging to the Bag-of-Tasks. Since multiple conflicting objectives exist in the lower level, we propose an improved variant of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) called Efficient NSGA-II (E-NSGA-II), applying a recently proposed quick non-dominated sorting algorithm (QNDSA) with quasi-linear average time complexity. By performing experiments on proposed synthetic datasets, our algorithm demonstrates high performance in terms of makespan and execution cost while respecting budget constraints. Statistical analysis validates the outperformance of our proposal regarding the considering metrics. [ABSTRACT FROM AUTHOR]

Trapping in local solutions is the main issue in several metaheuristic techniques. To solve such drawbacks by enhancing the search agents, a modified search strategy becomes a more attractive tactic. In this paper, an innovative version of Manta Ray Foraging Optimization (MRFO) is proposed to solve its crucial drawbacks while handling global and engineering optimization problems. The proposed version presents an integrated variant of MRFO with the triangular mutation operator and orthogonal learning strategy, called MRTMO. The two approaches are considered to achieve a robust equipoise between algorithm cores and provide a reliable mechanism to guide the search agents during the optimization process. The proposed MRTMO was tested with challenging CEC2005 and CEC2017 functions and six engineering problems to show its performance. Additionally, several evaluation metrics were employed to ensure the efficiency and robustness of the proposed MRTMO. Furthermore, extensive comparisons with existing optimization algorithms were carried out to ensure the superiority of MRTMO. The numerical experiments proved the competitive performance of the proposed MRTMO in solving all tested CEC optimization and engineering problems. [ABSTRACT FROM AUTHOR]

The Harris hawks optimizer (HHO) is a novel meta-heuristic algorithm that imitates a Harris hawk's hunting behavior and has an efficient exploitation mode. However, it suffers from low exploration because the transition of the search style is mainly based on the escape energy and it focuses on exploitation in the middle and later periods of the algorithm. In this paper, to overcome the weaknesses of the HHO, a Harris hawks optimizer based on the novice protection tournament (NpTHHO) is proposed to overcome the weaknesses of the HHO. Inspired by the root-mean-square prop (RMSProp) in machine learning, we first propose a novice protection mechanism to better reallocate resources. Then, we add a mutation mechanism to the exploration stage to further improve the global search efficiency of the HHO. Finally, we take into consideration 23 benchmark functions and several engineering optimization problems to verify the performance of the proposed algorithm. Experimental results indicate the proposed algorithm's competitive performance compared to the HHO and other well-established algorithms. [ABSTRACT FROM AUTHOR]

The paper proposes a bi-level programming model for community participation in techno-economic planning of an integrated energy system. Distribution system operator/System planner considered as a upper level decision maker anticipates the optimal operational response of community operator by solving lower level problem to make financial decisions while planning a sector coupled integrated energy system.To establish reliable, scalable, robust and data-driven decision making tool in techno-economic planning, a smart framework is proposed to quantify the effects of solar power uncertainties, assess hourly electric vehicle (EV) charging profile, analyze probabilistic reliability and obtain optimal financial decision by solving bi-level programming model using four meta-heuristics algorithms. During the preliminary stage, the potential effects of seasonal and climatic variations on solar radiation are quantified through nine distinct probabilistic classifiers trained using support vector classification approach. It serves as a data driven scenario generation tool for robust exploration of bi-level decision making process. Additionally, the impact of EV arrivals in a limited server charging facility is studied using queueing theory to estimate the mean hourly EV charging demand. Finally, the optimal settings of particle swarm optimisation (PSO), genetic algorithm (GA), red deer algorithm (RDA) and evolve class topper optimization (E-CTO) are identified through Taguchi's design of experiments. Based on these optimal settings, the proposed bi-level model is solved to obtain the best investment decision for planning a community based energy system. The results suggest that E-CTO shows a better response in terms of computational speed, convergence rate, accuracy and reliability. A minimum value of Rs 4.18 per kWh is obtained as the cost of energy using E-CTO. Numerical investigations were studied on a two area consumer centric energy system connected to the local grid to show the effectiveness of the proposed bi-level approach and meta-heuristic algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a parallel evolutionary metaheuristic which includes different threads aimed at balancing exploration versus exploitation. Exploring different areas of the search space independently, each thread also communicates with other threads, and exploits the search space by improving a common high quality solution. The presented metaheuristic has been applied to three famous and hard-to-solve optimization problems, namely the job shop scheduling, the permutation flowshop scheduling, and the quadratic assignment problems. The results of computational experiments indicate that it is effective, versatile and robust, competing with the-state-of-art procedures presented for these three problems. In effect, in terms of solution quality, and average required running time to reach a high quality solution, the procedure outperforms several state-of-the-art procedures on multiple benchmark instances. [ABSTRACT FROM AUTHOR]

Most swarm intelligence algorithms are stochastic metaheuristic algorithms in nature, and thus they may not solve all optimisation problems perfectly. Different algorithms may have different advantages, and the different real cases should be analysed independently. In this paper, a new brick-up re- building method for metaheuristic algorithms is proposed and discussed. This brick-up method creatively separates the metaheuristic algorithms into components (bricks) and generate a brick pool for further use. Then a new and best fitting algorithm will be generated custom-made to different problem and suggested to user as the best solution available in metaheuristic design. The main contributions for this research are the metaheuristic brick selection rules analysis and brick-up system model simulation. The proposed model has been tested on CEC 2015 benchmark function sets to verify its performance. The experimental results show that this recombination model can produce a metaheuristic algorithm that is as efficient as each individual candidate algorithm or better. [ABSTRACT FROM AUTHOR]

The P-Median Problem is one of the basic cases of facility location problems and has been studied for many years. Most methods of solving it are based on classical heuristics or meta-heuristic and they don't perform well on large-scale problems according to time cost. In this paper, we propose the first reinforcement learning-based method which uses Multi-Talking-Heads Graph Attention Networks to learn representations and design a learnable attention mechanism to solve the uncapacitated P-Median Problem. We train the model using REINFORCE algorithm and show that it has good performance on uncapacitated P-Median Problem according to solution quality and time consumption. We also apply our model to the realistic dataset and empirically figure out that the difference between data distributions is one of the most important factors to influence the final performances. [ABSTRACT FROM AUTHOR]

Swarm intelligence algorithms have superior performance in searching for the optimal feature subset, where Monarch Butterfly Optimization (MBO) can solve the continuous optimization problem. However, there exist some defects for MBO such as the limited searchable positions, falling into local optimum easily and unsolved binary variables. To address these drawbacks, this paper develops two mechanisms to propose several revisions of binary MBO (BMBO) for metaheuristic feature selection. First, to make MBO suitable to solve the feature selection optimization problems, the S-shaped and V-shaped transfer functions are introduced to convert continuous space into binary, and then force the butterfly to move in the binary search space. Two updated positions of the monarch butterfly population are designed based on these above transfer functions respectively to construct two BMBO models, namely BMBO-S and BMBO-V, as the first mechanism of BMBO. Second, the new step length parameter is proposed to update the position of monarch butterfly individuals. To prevent MBO from falling into the local optimum, the local disturbance and group division strategies are added into MBO to construct new BMBO method. It follows that a mutation rate is employed to enhance the detection stage of BMBO, and the mutation operator-based BMBO (BMBO-M) is designed to avoid the premature convergence of MBO. Third, this fitness function is integrated with the KNN classifier and the weight of the feature subset length to rank the selected feature subset, and a metaheuristic feature selection algorithm with BMBO-M is developed. Experiments applied to nineteen low dimensional UCI datasets and seven high dimensional datasets demonstrate our designed algorithm has great classification efficiency when compared with the other related technologies. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms (MAs) are used to find the answers to NP-Hard problems. NP-Hard problems basically refer to a set of optimization problems that cannot be solved in a polynomial at a time. MAs try to find the optimal or near-definitive answer in the shortest possible time to solve such problems and a set of optimization algorithms with different origins. These algorithms may be inspired by the natural sciences, physics, mathematics, and political science. However, a particular Metaheuristic algorithm may not provide the best answer to all problems. Each MA may have a better response to specific problems than other similar algorithms. Therefore, researchers will try to introduce and discover new algorithms to find optimal answers to a wide range of problems. In this paper, a new Meta-heuristic algorithm called the Water optimization algorithm (WAO) is presented. WAO is inspired by the chemical and physical properties of water molecules. The main idea of the proposed algorithm is to link water molecules together to find the optimal points. Factors such as particle motion, particle evaporation, and particle bonding have created a mechanism based on swarm intelligence and physical intelligence that inspired this algorithm to solve persistent problems. In this algorithm, answers are defined as a water molecule, a set of them is defined as a local answer. Water bonds provide the right move towards the optimal response. In evaluating the performance of the proposed algorithm, the proposed method is applied to some standard functions and some practical problems. The results obtained from the experiments show that the proposed algorithm has provided appropriate and acceptable answers in terms of execution time and accuracy compared to some similar algorithms. [ABSTRACT FROM AUTHOR]

In recent years, the number and severity of natural disasters have increased. These disasters always carry the risks of mortality and injury. But its mortality risks are much higher for people with disabilities than for normal people. One of the most important issues during natural disasters is to pay attention to the provision of accommodation and the possibility of evacuating people with disabilities. In this paper, a Mixed-Integer Linear Programming (MILP) model is proposed for shelter locations, evacuation routing, compatibility constraints in the context of disability, and time windows to picking up people with disabilities from different locations and transporting them to shelters. This study considers the time required for the movement of people with disabilities, heterogeneous vehicles, different capacities, several depots, and several shelters. The intended objective functions are the total distance traveled by vehicles, the maximum distance of a tour, and a hybrid objective function created by the weighted combination of both mentioned objective functions. A new Giza Pyramids Construction (GPC) algorithm is used to solve the model. Using the approach of the GPC algorithm, which is one of the soft computing methods, greatly reduces the computation complexity. To examine the performance of the proposed algorithm, thirty instances at different scales are generated with and without time window constraints. For validation, the results obtained from the proposed algorithm are compared with the results obtained from four algorithms including SA, IWO, DE, and EPC. The results show that the GPC algorithm performed better than other algorithms in solving the model. According to the results, the proposed GPC algorithm is 5%, 44%, 10%, and 4% better than SA, IWO, DE, and EPC, respectively. Furthermore, considering the time window significantly increases the total network evacuation time. Based on our experiments the proposed model and solution approach can be helpful in solving the real problems related to the evacuation of people with disabilities during natural disasters. [ABSTRACT FROM AUTHOR]

The seagull optimization algorithm (SOA) is a recently proposed meta-heuristic optimization algorithm inspired by seagull foraging behavior. It has the advantages of simple structure and easy implementation. However, it also has some shortcomings, such as easily falling into local optimal and low convergence accuracy when solving complex engineering optimization problems. In this paper, to overcome the defects of the original SOA, an enhanced seagull optimization algorithm (ESOA) based on mutualism mechanism and commensalism mechanism is proposed. To evaluate the performance of the ESOA algorithm, the IEEE CEC2020 benchmark suite is utilized to verify the effectiveness of the ESOA algorithm, and the results are compared and analyzed with the latest meta-heuristic optimization algorithms. In addition, the ESOA algorithm is applied to twelve different types of engineering optimization problems, including pressure vessel design problem, multiple disc clutch brake design problem, three bar truss design problem, car crashworthiness problem, cantilever beam problem, abrasive water jet machine, gas transmission compressor design problem, hydro-static thrust bearing design problem, speed reducer problem, tubular column design problem, I beam design problem and industrial refrigeration system design problem. The convergence curves of ESOA and the comparison results of the latest metaheuristic algorithms are analyzed and compared with those reported in the latest literature. The results show that the ESOA algorithm is an optimization method that can find the optimal solution in engineering design problems, and has strong competitiveness compared with other algorithms. [ABSTRACT FROM AUTHOR]

A novel optimization algorithm called hybrid salp swarm algorithm with teaching-learning based optimization (HSSATLBO) is proposed in this paper to solve reliability redundancy allocation problems (RRAP) with nonlinear resource constraints. Salp swarm algorithm (SSA) is one of the newest meta-heuristic algorithms which mimic the swarming behaviour of salps. It is an efficient swarm optimization technique that has been used to solve various kinds of complex optimization problems. However, SSA suffers a slow convergence rate due to its poor exploitation ability. In view of this inadequacy and resulting in a better balance between exploration and exploitation, the proposed hybrid method HSSATLBO has been developed where the searching procedures of SSA are renovated based on the TLBO algorithm. The good global search ability of SSA and fast convergence of TLBO help to maximize the system reliability through the choices of redundancy and component reliability. The performance of the proposed HSSATLBO algorithm has been demonstrated by seven well-known benchmark problems related to reliability optimization that includes series system, complex (bridge) system, series-parallel system, overspeed protection system, convex system, mixed series-parallel system, and large-scale system with dimensions 36, 38, 40, 42 and 50. After illustration, the outcomes of the proposed HSSATLBO are compared with several recently developed competitive meta-heuristic algorithms and also with three improved variants of SSA. Additionally, the HSSATLBO results are statistically investigated with the wilcoxon sign-rank test and multiple comparison test to show the significance of the results. The experimental results suggest that HSSATLBO significantly outperforms other algorithms and has become a remarkable and promising tool for solving RRAP. [ABSTRACT FROM AUTHOR]

Group Theory-based Optimization Algorithm (GTOA) is a novel population-based global optimization algorithm, which is used to solve combinatorial optimization problems. This paper studies the applicability of GTOA in numerical optimization and proposes two versions of GTOA based on binary coding (GTOA-b) and 0 ∼ 9 integer coding (GTOA-d). Firstly, the coding transformation methods for representing the feasible solutions are introduced, which make GTOA suitable for continuous optimization. On this basis, the original evolution operators are modified to reduce the deviation and speed up global convergence. The experiment using the CEC2017 test suit is carried out to validate the performance of the algorithms. The influence of parameter values and the differences between the calculated results are analyzed by nonparametric tests. Computation results showed that the convergence rate of GTOA-d is faster than that of GTOA-b, and it achieved better results on the benchmark functions with higher dimensions. The comparison against twelve state-of-the-art and recently introduced meta-heuristic algorithms showed that GTOA-d has the superiority on convergence stability, it obtained significantly better performance than seven of its competitors. Finally, all the algorithms are applied to an Amplitude Variation with Offset inversion case study. The simulation showed that the proposed GTOA-d achieved satisfactory inversion results, and it has better performance in terms of convergence rate and average accuracy. The results demonstrate that the proposed GTOA-d is an effective algorithm for numerical optimization. [ABSTRACT FROM AUTHOR]

An efficient survey of numerous traditional metaheuristic algorithms (MAs) has been investigated in this paper. Among successful MAs, differential evolution (DE) and particle swarm optimization (PSO) have been widely recognized to solve complex optimization problems and received much attention from many researchers. Therefore, DE and PSO are chosen in the present study and an extensive survey of their recent-past variants with hybrids has been inspected again. After this an advanced DE (ADE) and PSO (APSO) with their hybrid (AHDEPSO) are proposed for unconstrained optimization problems. In ADE a novel mutation strategy, crossover probability and random nature selection scheme (to avoid premature convergence) as well as in APSO novel gradually varying parameters (to avoid stagnation) are introduced. Hence, ADE and APSO affords different convergence characteristics to the solution space. Also to balance between exploration and exploitation, in AHDEPSO population is divided (multi-population approach) and merged with others in a pre-defined way. Thus, AHDEPSO achieves better solutions and it is expected to obtain productive solutions with an increasing success rate at each cycle. To verify the performance of all 3 proposed algorithms i.e. ADE, APSO, and AHDEPSO applied to solve 23 basic, 30 IEEE CEC 2017 unconstrained benchmark functions and 3 real-world problems. There are several numerical and graphical analyses have been done to verify the performances of the proposed algorithms robustly. Additionally, statistical and comparative analysis confirms the superiority of the proposed algorithms among traditional DE and PSO with their recent variants and hybrids as well as over many state-of-the-art algorithms. Finally, between 3 proposed algorithms the best one i.e. AHDEPSO is recommended to solve unconstrained optimization problems. [ABSTRACT FROM AUTHOR]

Salp swarm algorithm (SSA) is a relatively new and straightforward swarm-based meta-heuristic optimization algorithm, which is inspired by the flocking behavior of salps when foraging and navigating in oceans. Although SSA is very competitive, it suffers from some limitations including unbalanced exploration and exploitation operation, slow convergence. Therefore, this study presents an improved version of SSA, called OOSSA, to enhance the comprehensive performance of the basic method. In preference, a new opposition-based learning strategy based on optical lens imaging principle is proposed, and combined with the orthogonal experimental design, an orthogonal lens opposition-based learning technique is designed to help the population jump out of a local optimum. Next, the scheme of adaptively adjusting the number of leaders is embraced to boost the global exploration capability and improve the convergence speed. Also, a dynamic learning strategy is applied to the canonical methodology to improve the exploitation capability. To confirm the efficacy of the proposed OOSSA, this paper uses 26 standard mathematical optimization functions with various features to test the method. Alongside, the performance of the proposed methodology is validated by Wilcoxon signed-rank and Friedman statistical tests. Additionally, three well-known engineering optimization problems and unknown parameters extraction issue of photovoltaic model are applied to check the ability of the OOSA algorithm to obtain solutions to intractable real-world problems. The experimental results reveal that the developed OOSSA is significantly superior to the standard SSA, currently popular SSA-based algorithms, and other state-of-the-artmeta-heuristic algorithms for solving numerical optimization, real-world engineering optimization, and photovoltaic model parameter extraction problems. Finally, an OOSSA-based path planning approach is developed for creating the shortest obstacle-free route for autonomous mobile robots. Our introduced method is compared with several successful swarm-based metaheuristic techniques in five maps, and the comparative results indicate that the suggested approach can generate the shortest collision-free trajectory as compared to other peers. [ABSTRACT FROM AUTHOR]

Crow search algorithm (CSA) is a novel meta-heuristic optimization algorithm based on the intelligent behavior of the crow population. Although the algorithm has the characteristics of few parameters, simple structure, and easy application, it has the shortcomings of low convergence accuracy and imbalance between exploration and exploitation capabilities. The occurrence of these issues is originated from crow learning from only one goal. In this paper, an improved crow search algorithm based on oppositional forgetting learning (OFLCSA) is proposed. In order to solve the shortcomings of CSA, the forgetting mechanism is introduced to help the algorithm jump out of the local optimum. Moreover, the opposition-based learning (OBL) strategy is combined with the forgetting mechanism to increase the probability of approaching the optimal solution. In addition, the elite crow and adaptive flight length are used to improve the convergence accuracy. To verify the performance of OFLCSA, experiments were conducted on the Congress on Evolutionary Computation (CEC) 2014 and CEC 2019 benchmark functions. OFLCSA is compared with the ten state-of-the-art meta-heuristic optimization algorithms. Moreover, OFLCSA is evaluated by four real-world engineering applications. Experimental results and analysis show that OFLCSA is a competitive meta-heuristic optimization algorithm. [ABSTRACT FROM AUTHOR]

Community detection is one of the long standing and challenging tasks in the field of Complex Networks (CNs). Recently, deep learning is one of the promising community detection methods, which can learn effectively low-dimensional representation of CNs. However, the existing methods have major drawbacks in terms of local minima and slow convergence, since they use Gradient Descent Backpropagation algorithm (GDBP). This reduces the performance of community detection in terms of effectiveness and efficiency. To overcome these drawbacks, this paper introduces a new parallel deep learning model based on Metaheuristic (MH) algorithm instead of the GDBP algorithm. To be specific, a new parallel stacked autoencoder (SAE) based on particle swarm optimization (PSO) is developed for feature learning and community detection in CNs. The PSO algorithm uses a multi-objective fitness function that includes the standard loss function (i.e., MSE) of the autoencoder and the modularity function to guide SAE optimization and improve community detection performance. In addition, an efficient distributed parallel implementation is proposed to improve the efficiency and scalability of the SAE-based PSO method. The parameter settings of PSO such as features-dimension and number of particles, are tuned and studied to observe their implications on community detection performance. We conducted an experiment comprising datasets of 10 real-world networks to evaluate the proposed method in different parameter settings. The results demonstrated that the SAE-based PSO method is promising and provides a competitive performance against state-of-art methods in community detection. Furthermore, the results showed that the parallel implementation of the proposed method could improve efficiency with three or greater orders of speed. [ABSTRACT FROM AUTHOR]

Whale optimization algorithm (WOA) is a new meta-heuristic algorithm for mathematical description of the foraging behavior of whales. Cloud model (CM) is an effective model to describe cognitive uncertainty, at the same time, it can comprehensively describe the randomness and fuzziness in uncertain phenomena. Skew normal distribution (SND) can better describe the biological behavior situation when the environment changes. In this paper, a new skew normal cloud model (SNCM) is established in the first place by combining the CM with the SND and the skew normal membership function to describe the fuzziness and randomness of environmental change. Secondly,because of the randomness and fuzziness of the whales' foraging behavior, in order to improve the exploration and exploitation ability of WOA,an emendatory WOA based on the skew normal cloud (SNC) is proposed through the use of the SNCM to modify the shrinking encircling and spiral update strategies of WOA, and the adaptive position and skewness parameters in the SNC are designed to increase the exploration capability in prophase and the exploitation capability in anaphase. Lastly,the experimental results of the complex CEC2017 test set verify the effectiveness of the emendatory WOA under different strategies and different dimensions and different improved WOA algorithm and other representative heuristic algorithms. Three degree reduction of S − λ curves verify the practicability of the the modified WOA in the field of curve design. [ABSTRACT FROM AUTHOR]

Acquiring medical images while maintaining patient information confidentiality is a difficult task, which leads to a lack of sufficient data for deep learning-based disease detection. To address the challenges of few-shot learning in such scenarios, researchers generally resort to the transfer learning ability of the pre-train model. However, in practice, the pre-trained model only updates its fully connected layers or a few other layers with limited data examples while holding its many layers unchanged. Nonetheless, such transfer learning paradigms are not expected to alter the layer structure of the model. Consequently, the benefits of pre-trained models are limited, especially when the target dataset deviates from the source dataset in terms of data pattern. Moreover, the time cost of transfer retraining should also be considered. To alleviate these impacts, we propose a novel paradigm for multiple disease detection via medical images that combined a meta-heuristic algorithm and transfer learning. We also present a novel optimization algorithm and design two novel adaptive frameworks (BTL, DTL), and four adaptive neural networks (BVTN, BSTN, DVTN, and DSTN). In our paradigm, pre-trained models could adaptively adjust the feature extraction ability by reshaping a few network layers to accommodate the data distribution differences between source and target datasets. Thus, the negative impact of such differences can be effectively alleviated. We conduct experiments on three datasets (brain magnetic resonance, chest X-ray, and skin image datasets) with different data distributions. Experimental results show that our paradigm can effectively mitigate the impact of differences in data distribution, and that our method outperforms four state-of-the-art methods on all three datasets. [ABSTRACT FROM AUTHOR]

A new memetic metaheuristic optimizer, hybridizing the classical Slime Mould Optimization Algorithm (SMA) with Harris hawk's Optimizer (HHO), is developed. The proposed hSMA-HHO is based on SMA- a swarm-inspired population metaheuristics algorithm with a notable approach in global optimization and HHO- a nature-inspired algorithm based on the supportive behavior and hunting style of Harris hawks. Although both algorithms perform well individually, they still require improvement for better efficacious results. The exploitation and exploration behavior are improved. Also, the problem of trapping in local optima is removed as observed by investigating the proposed algorithm on an extensive set of standard benchmarks comprising multiple functions with various dimensions. The results achieved are analyzed and compared with other recent metaheuristic algorithms. Furthermore, convergence graphs and statistical analysis prove the supremacy of the proposed hSMA-HHO algorithm over other up-to-date metaheuristics algorithms. The proposed algorithm is also checked to solve the optimal design of 11 well-recognized constrained engineering problems. Analysis and comparison of results reveal that the proposed hSMA-HHO algorithm is an encouraging and viable optimization approach for elucidating different engineering design problems. [ABSTRACT FROM AUTHOR]

Genetic Algorithm (GA) is a widely used metaheuristic for addressing challenging optimization problems. Selecting suitable settings for GA parameters can lead to a considerable improvement in its performance, but this is often difficult due to the larger number of alternatives available and variable performance depending on the problem solved. Furthermore, consideration of multiple performance criteria in parameter selection adds an additional layer of complexity. Therefore, practitioners often rely on their previous experiences or perform trial-and-error experiments when determining suitable parameter settings. In this study, we define the problem of finding suitable settings for GAs as a bi-objective optimization problem with an aim to find efficient settings that will maximize the approximation quality and minimize the run time of the GA. We conduct an empirical study on a GA that solves Traveling Salesperson Problem (TSP). Two evolutionary algorithms are utilized in a nested manner to address the bi-objective parameter setting problem: a GA to solve the TSP instances and a multi-objective evolutionary algorithm to find the bi-objective efficient settings of the GA. We find efficient settings for each instance through an empirical study with 31 TSP instances and identify settings that perform well regardless of the instance solved. The results provide valuable insights into the behavior of efficient settings, demonstrating that some operators and parameters are robust to changes in problem size, while others require adjustment. [ABSTRACT FROM AUTHOR]

The use of chemicals and preservatives during the production of most daily-used products has increased rapidly over the last few decades. In turn, manufacturers, to improve the sustainability of a manufacturing unit in the current highly competitive market, are obliged to provide various facilities to their customers. However, estimating the best optimal decision for manufacturing companies seems like a daunting task amid highly uncertain market conditions. By shedding more light on these facts and considering the gaps in the existing literature on production inventory, this work aims to incorporate a production model which is concerned with the factors mentioned above, so that it can be beneficial for a manufacturer. This work involves the demonstration of an imperfect green production system under single-layer full-trade credit financing and partial backlog shortages using interval flexibility. Based on the credit period lengths provided by the manufacturer to the consumers, three distinct cases have arisen and for each case, the average profit of the system appears to be an interval valued optimal control problem, and several theorems are evaluated to obtain analytical forms of respective objective functions of each case. Additionally, to test the effect of different credit lengths on optimal policy and to examine the feasibility of each case, a numerical example is solved using the Equilibrium Optimizer (EO) algorithm. Finally, a sensitivity experiment is performed and the results obtained from the simulation are shown graphically to gain some managerial insights. [ABSTRACT FROM AUTHOR]

With the uncertainty of a cloud environment and the diversity of workload requirements increasing the scheduling cost of container-based cloud, especially for load spikes of application access, optimizing the utilization efficiency of cloud resources and quality of service is the focus of container cluster technology in the future. Different from traditional virtual machine-based scheduling, containerized applications of heterogeneous workloads bring higher scheduling complexity with its elastic scaling and multi-replicas operation. To tackle this problem, we propose a priority-aware workloads scheduling algorithm PA-CCWS. Firstly, we implement workload characterization and behavior identification, quantify the analysis results with TOPSIS method, generate the workloads priority and build priority scheduling buffer queue. Meanwhile, the model learning is accelerated by the experience replay mechanism that inserts and updates the priority of historical experience through the real-time feedback of actual container scheduling from DDQN. Then, we describe containerized applications oriented deep reinforcement learning scheduling algorithm which combined with the two kinds of priorities, to optimize scheduling decision. Finally, we evaluate the effectiveness of our algorithm in terms of resource utilization, resource imbalance degree and SLA compliance rate, etc. Compared with meta-heuristic algorithm PSOS, mathematical model-based algorithm KCSS and other excellent deep reinforcement learning based scheduling algorithms such as DeepRM-Plus and RLSched applying in the container-based cloud, PA-CCWS shows better resource utilization efficiency and convergence stability in containerized applications scheduling. [ABSTRACT FROM AUTHOR]