Nature-inspired Metaheuristic Techniques Research Articles

Comparative Analysis of Nature-Inspired Metaheuristic Techniques for Optimizing Phishing Website Detection

The increasing number, frequency, and sophistication of phishing website-based attacks necessitate the development of robust solutions for detecting phishing websites to enhance the overall security of cyberspace. Drawing inspiration from natural processes, nature-inspired metaheuristic techniques have been proven to be efficient in solving complex optimization problems in diverse domains. Following these successes, this research paper aims to investigate the effectiveness of metaheuristic techniques, particularly Genetic Algorithms (GAs), Differential Evolution (DE), and Particle Swarm Optimization (PSO), in optimizing the hyperparameters of machine learning (ML) algorithms for detecting phishing websites. Using multiple datasets, six ensemble classifiers were trained on each dataset and their hyperparameters were optimized using each metaheuristic technique. As a baseline for assessing performance improvement, the classifiers were also trained with the default hyperparameters. To validate the genuine impact of the techniques over the use of default hyperparameters, we conducted statistical tests on the accuracy scores of all the optimized classifiers. The results show that the GA is the most effective technique, by improving the accuracy scores of all the classifiers, followed by DE, which improved four of the six classifiers. PSO was the least effective, improving only one classifier. It was also found that GA-optimized Gradient Boosting, LGBM and XGBoost were the best classifiers across all the metrics in predicting phishing websites, achieving peak accuracy scores of 98.98%, 99.24%, and 99.47%, respectively.

Novel rockburst prediction criterion with enhanced explainability employing CatBoost and nature-inspired metaheuristic technique

Rockburst is a major challenge to hard rock engineering at great depth. Accurate and timely assessment of rockburst risk can avoid unnecessary casualties and property losses. Despite the existence of various methods for rockburst assessment, there remains an urgent need for a comprehensive and reliable criterion that is easy to both apply and interpret. Developing a new rockburst criterion based on simple parameters can potentially fill this gap. With its advantages, this criterion can facilitate a more effective and efficient prediction of rockburst potential, thereby contributing significantly to enhancing safety measures. In this paper, combined with the internal and external factors of rockburst, four control variables (i.e., integrity index, stress index, brittleness index, and elastic energy index) were selected to be incorporated into a comprehensive rockburstability index (RBSI). Based on 116 sets of rockburst cases, the rockburst potential was accurately quantified and predicted using the categorical boosting (CatBoost) model and the nature-inspired metaheuristic African vultures optimization algorithm (AVOA). In its performance validation, the criterion achieved the highest accuracy of 90.48%, verifying the reliability and effectiveness of the proposed RBSI criterion. Additionally, an interpretive method was applied to analyze the variable influence on the criterion, facilitating the explanation of predictions and the analysis of the formula’s robustness under different conditions. In general, compared with existing criterion methods involving relevant indicators, the newly proposed RBSI criterion enhances the accuracy of rockburst potential prediction, and it can effectively and swiftly evaluate the preliminary risk of rockburst. Lastly, a graphical user interface was developed to provide a clear visualization of the assessment of rockburst potential.

MSAO: A multi-strategy boosted snow ablation optimizer for global optimization and real-world engineering applications

Snow Ablation Optimizer (SAO) is a cutting-edge nature-inspired meta-heuristic technique that mimics the sublimation and melting processes of snow in its quest for optimal solution to complex problems. While SAO has demonstrated competitive performance in comparison to classical algorithms in early research, it still exhibits certain limitations including low convergence accuracy, a lack of population diversity, and premature convergence, particularly when addressing high-dimensional intricate challenges. To mitigate the above-mentioned adverse factors, this paper introduces a novel variant of SAO with featuring four enhancement strategies collectively referred as MSAO. Firstly, the good point set initialization strategy is employed to generate a uniformly distributed high-quality population, which facilitates the algorithm to enter the appropriate search domain rapidly. Secondly, the greedy selection method is adopted to reserve better candidate solutions for the next iteration, thus striking a robust exploration–exploitation balance. Then, the Differential Evolution (DE) scheme is introduced to expand the search range and enhance the exploitation capability of the algorithm for higher convergence accuracy. Finally, to reduce the risk of falling into local optima, a Dynamic Lens Opposition-Based Learning (DLOBL) strategy is developed to operate on the current optimal solution dimension by dimension. With the blessing of these strategies, the optimization performance of MSAO is comprehensively improved. To comprehensively evaluate the optimization performance of MSAO, a series of numerical optimization experiments are conducted using the IEEE CEC2017 & CEC2022 test sets. In the IEEE CEC2017 experiments, the optimal crossover probability CR=0.8 is determined and the effectiveness of each improvement strategy is ablatively verified. MSAO is compared with the basic SAO, various state-of-the-art optimizers, and CEC2017 champion algorithms in terms of solution accuracy, convergence speed, robustness, and scalability. In the IEEE CEC2022 experiments, MSAO is compared with some recently developed improved algorithms to further validate its superiority. The results demonstrate that MSAO has excellent overall optimization performance, with the smallest Friedman mean rankings of 1.66 and 1.25 on both test suites, respectively. In the majority of test cases, MSAO can provide more accurate and reliable solutions than other competitors. Furthermore, six realistic constrained engineering design challenges and one photovoltaic model parameter estimation issue are employed to demonstrate the practicality of MSAO. Our findings suggest that MSAO has excellent optimization capacity and broad application potential.

Review of Short-Term Load Forecasting for Smart Grids Using Deep Neural Networks and Metaheuristic Methods

Forecasting electricity load demand is critical for power system planning and energy management. In particular, accurate short-term load forecasting (STLF), which focuses on the lead time horizon of few minutes to one week ahead, can help in better load scheduling, unit commitment, and cost-effective operation of smart power grids. In the last decade, different artificial intelligence (AI)-based techniques and metaheuristic algorithms have been utilized for STLF by the researchers and scientists with varying degrees of accuracy and efficacy. Despite the benefits of implemented methods for STLF, many drawbacks and associated problems have also been observed and reported by the researchers. This paper provides a comprehensive review of hybrid deep learning models based on nature-inspired metaheuristic techniques for STLF with respect to the analysis of the results and accuracy. Moreover, it also provides the research findings and gaps that will assist the researchers to have an early awareness of all important benefits and drawbacks of these integrated STLF methods scientifically and systematically. Especially, the hybrid forecast models using artificial intelligence-based methods for smart grids are focused. Several performance indices are used to compare and report the accuracy of these techniques including mean absolute percentage error (MAPE). Multiple other parametric and exogenous variable details have also been focused to figure out the potential of the intelligent load forecasting techniques from the perspective of smart power grids.

Optimum sizing design of steel frame structures through maximum energy dissipation of friction dampers under seismic excitations

This paper focuses on optimum sizing design of steel frame structures equipped with friction dampers (FDs) in order to prevent the vulnerable effect of an earthquake. The fundamental concept is to maximize the energy dissipation of implemented FDs under different seismic excitations. The FDs utilized as passive energy dissipation devices in a steel structure increase the energy dissipation capacity of the structure by decreasing the seismic demand during an earthquake. In this context, the Pall friction dampers (PFDs) are implemented as diagonal damped brace members in investigated structures. Three different earthquake records (Kobe, Kocaeli-Duzce, Erzincan) are utilized to acquire nonlinear dynamic responses of the steel frame structures through time-history analyses. The open application programming interface (OAPI) functions are used to integrate a finite element modelling based structural analysis program, SAP2000, with a design optimization algorithm encoded in MATLAB for achieving the exact structural behaviours by synchronously data transferring. As an optimizer, one of the recent nature-inspired metaheuristic techniques, so-called Grey Wolf (GW) algorithm is used. Initially, under effect of seismic excitations, the steel frame structures are optimally sized for attaining minimum design weights without implementing the PFD elements by subjecting only strength, displacement, drift, and geometric structural design constraints taken from AISC-LRFD practice code provisions. Afterward, in order for optimally modelling the PFD elements, the frames are equipped with PFDs to calculate optimum yield strengths that is defined as slip load of a PFD. To do so, the GW algorithm ensures the maximizing of the dissipated energy and controls the yield strengths between the stories since the shear force due to the earthquake increases towards the base of the structure. Eventually, the provisions-based sizing design optimizations of the steel frame structures equipped with optimally modelled PFD elements are conducted under seismic excitations for conclusive evaluations.

Missing Value Imputation Designs and Methods of Nature-Inspired Metaheuristic Techniques: A Systematic Review

Missing values are highly undesirable in real-world datasets. The missing values should be estimated and treated during the preprocessing stage. With the expansion of nature-inspired metaheuristic techniques, interest in missing value imputation (MVI) has increased. The main goal of this literature is to identify and review the existing research on missing value imputation (MVI) in terms of nature-inspired metaheuristic approaches, dataset designs, missingness mechanisms, and missing rates, as well as the most used evaluation metrics between 2011 and 2021. This study ultimately gives insight into how the MVI plan can be incorporated into the experimental design. Using the systematic literature review (SLR) guidelines designed by Kitchenham, this study utilizes renowned scientific databases to retrieve and analyze all relevant articles during the search process. A total of 48 related articles from 2011 to 2021 was selected to assess the review questions. This review indicated that the synthetic missing dataset is the most popular baseline test dataset to evaluate the effectiveness of the imputation strategy. The study revealed that missing at random (MAR) is the most common proposed missing mechanism in the datasets. This review also indicated that the hybridizations of metaheuristics with clustering or neural networks are popular among researchers. The superior performance of the hybrid approaches is significantly attributed to the power of optimized learning in MVI models. In addition, perspectives, challenges, and opportunities in MVI are also addressed in this literature. The outcome of this review serves as a toolkit for the researchers to develop effective MVI models.

The Role of Neural Networks and Metaheuristics in Agile Software Development Effort Estimation

In any software development, accurate estimation of resources is one of the crucial tasks that leads to a successful project development. A lot of work has been done in estimation of effort in traditional software development. But, work on estimation of effort for agile software development is very scant. This paper provides an effort estimation technique for agile software development using artificial neural networks (ANN) and a metaheuristic technique. The artificial neural networks used are radial basis function neural network (RBFN) and functional link artificial neural network (FLANN). The metaheuristic technique used is whale optimization algorithm (WOA), which is a nature-inspired metaheuristic technique. The proposed techniques FLANN-WOA and RBFN-WOA are evaluated on three agile datasets, and it is found that these neural network models performed extremely well with the metaheuristic technique used. This is further empirically validated using non-parametric statistical tests.

A Comprehensive Analysis of Nature-Inspired Meta-Heuristic Techniques for Feature Selection Problem

Meta-heuristics are problem-independent optimization techniques which provide an optimal solution by exploring and exploiting the entire search space iteratively. These techniques have been successfully engaged to solve distinct real-life and multidisciplinary problems. A good amount of literature has been already published on the design and role of various meta-heuristic algorithms and on their variants. The aim of this study is to present a comprehensive analysis of nature-inspired meta-heuristic utilized in the domain of feature selection. A systematic review methodology has been used for synthesis and analysis of one hundered and seventy six articles. It is one of the important multidisciplinary research areas that assist in finding an optimal set of features so that a better rate of classification can be achieved. The concept of feature selection process along with relevance and redundancy metric is briefly elucidated. A categorical list of nature-inspired meta-heuristic techniques has been presented. The major applications of these techniques are explored to highlight the least and most explored areas. The area of disease diagnosis has been extensively assessed. In addition, the special attention has been given on highlighting the role and performance of binary and chaotic variants of different nature-inspired meta-heuristic techniques. The summary of nature-inspired meta-heuristic methods and their variants along with datasets, performance (mean, best, worst, error rate and standard deviation) is also depicted. In addition, the detailed publication trend of meta-heuristic feature selection approaches has also been presented. The research gaps have been identified for the researcher who inclines to design or analyze the performance of divergent meta-heuristic techniques in solving feature selection problem.

Nature-inspired metaheuristic techniques for automatic clustering: a survey and performance study

The application of several swarm intelligence and evolutionary metaheuristic algorithms in data clustering problems has in the past few decades gained wide popularity and acceptance due to their success in solving and finding good quality solutions to a variety of complex real-world optimization problems. Clustering is considered one of the most important data analysis techniques in the domain of data mining. A clustering problem refers to the partitioning of unlabeled data objects into a certain number of clusters based on their attribute values or features, with the objective of maximizing intra-clusters homogeneity and inter-cluster heterogeneity. This paper presents an up-to-date survey of major nature-inspired metaheuristic algorithms that have been employed to solve automatic clustering problems. Further, a comparative study of several modified well-known global metaheuristic algorithms is carried out to solve automatic clustering problems. Also, three hybrid swarm intelligence and evolutionary algorithms, namely, particle swarm differential evolution algorithm, firefly differential evolution algorithm and invasive weed optimization differential evolution algorithm, are proposed to deal with the task of automatic data clustering. In contrast to many of the existing traditional and evolutionary computational clustering techniques, the clustering algorithms presented in this paper do not require any predetermined information or prior-knowledge of the dataset that is to be classified, but rather they are capable of spontaneously identifying the optimal number of partitions of the data points during the course of program execution. Forty-one benchmarked datasets that comprise eleven artificial and thirty real world datasets are collated and utilized to evaluate the performances of the representative nature-inspired clustering algorithms. According to the extensive experimental results, comparisons and statistical significance, the firefly algorithm appeared to be more appropriate for better clustering of both low and high dimensional data objects than were other state-of-the-art algorithms. Further, an experimental study demonstrates the superiority of the three proposed hybrid algorithms over the standard state-of-the-art methods in finding meaningful clustering solutions to the problem at hand.

Fitness Dependent Optimizer-Based Automatic Generation Control of Multi-Source Interconnected Power System With Non-Linearities

This paper proposed an improved structure of Proportional Integral Derivative (PID) controller called as Integral Proportional Derivative (I-PD), applied for Automatic Generation Control (AGC) of Multi-Source Interconnected Power System (IPS). The parameters of the proposed controller are optimized with a newly developed, powerful, nature-inspired meta-heuristic technique known as Fitness Dependent Optimizer (FDO). To show the efficacy of the proposed controller and the technique used, they have been tested on three different system models. Initially, a two-equal area of diverse source generation including reheat-thermal, gas, and hydro power system is considered. In the second scenario, the same power system model is used with addition of two non-linearities; Generation Rate Constraint (GRC) and Governor Dead Band (GDB). Lastly, multiple non-linearities including Governor Dead Band (GDB), Time Delay (TD), Generation Rate Constraint (GRC), and Boiler Dynamics (BD) have been considered to make the initial system more realistic and practical. The outcome from the proposed techniques is also compared with some recently meta-heuristic algorithms such as Teaching Learning Based Optimization (TLBO), Particle Swarm Optimization (PSO) and Firefly Algorithm (FA). From the results, it has been perceived that the proposed technique shows superior performance in respect of Overshoot (Osh), Undershoot (Ush) and Settling Time (Ts) of the system frequency.

Enhanced and speedy energy extraction from a scaled-up pressure retarded osmosis process with a whale optimization based maximum power point tracking

This paper proposes a novel maximum power point tracking scheme for efficient and speedy extraction of maximum power from a pressure retarded osmosis process subject to rapid salinity variation. The scheme is designed using the Whale Optimization with Differential Evolution algorithm, a nature-inspired metaheuristic technique. The algorithm has facilitated the developed maximum power point tracking controller with features that have helped overcome limitations such as lower tracking efficiency and steady state oscillations as encountered in the conventional methods. Previously, a number of widely used algorithms including perturb & observe, incremental mass resistance and mass feedback controller were used to design maximum power point control schemes for a PRO process to reduce power loss due to rapid salinity variation. However, in using these techniques, a trade-off between the oscillations and the respond time was required to adjust the operation. The proposed scheme is used to solve this problem and is implemented in simulation on a scaled-up PRO system. The performance of the scheme is compared with some popularly used maximum power point tracking controllers. It is observed from results that the proposed method not only outperforms other widely used methods but is also more robust.

Comparative Analysis of Job Scheduling Algorithms in Parallel and Distributed Computing Environments

Due to an unprecedented increase in the number of computing resources in different organizations, effective job scheduling algorithms are required for efficient resource utilization. Job scheduling in considered as NP hard problem in parallel and distributed computing environments such as cluster, grid and clouds. Metaheuristics such as Genetic Algorithms, Ant Colony Optimization, Artificial Bee Colony, Cuckoo Search, Firefly Algorithm, Bat Algorithm etc. are used by researchers to get near optimal solutions to job scheduling problems. These metaheuristic algorithms are used to schedule different types of jobs such as BSP, Workflow and DAG, Independent tasks and Bag-of-Tasks. This paper is an attempt to provide comprehensive review of popular nature-inspired metaheuristic techniques which are used to schedule different categories of jobs to achieve certain performance objectives. Keywords: scheduling, metaheuristics, multi-criteria, metrics, BSP, workflow, independent tasks, bag-of-tasks

A Novel Approach for Multispectral Satellite Image Classification Based on the Bat Algorithm

Among the multiple advantages and applications of remote sensing, one of the most important uses is to solve the problem of crop classification, i.e., differentiating between various crop types. Satellite images are a reliable source for investigating the temporal changes in crop cultivated areas. In this letter, we propose a novel bat algorithm (BA)-based clustering approach for solving crop type classification problems using a multispectral satellite image. The proposed partitional clustering algorithm is used to extract information in the form of optimal cluster centers from training samples. The extracted cluster centers are then validated on test samples. A real-time multispectral satellite image and one benchmark data set from the University of California, Irvine (UCI) repository are used to demonstrate the robustness of the proposed algorithm. The performance of the BA is compared with two other nature-inspired metaheuristic techniques, namely, genetic algorithm and particle swarm optimization. The performance is also compared with the existing hybrid approach such as the BA with K-means. From the results obtained, it can be concluded that the BA can be successfully applied to solve crop type classification problems.

A novel evolutionary technique based on electrolocation principle of elephant nose fish and shark: fish electrolocation optimization

Elephant nose fish searches its food such as larvae by active electrolocation. It discharges electric pulse through its electric organ in tail and detects the object by analyzing the geometrical property of projected electrical image on it. The capacitance value found out from that electric image helps the fish to reach near the food source. Shark also uses passive electrolocation for the same purpose. It can target its prey by sensing the electrical wave generated due to the muscle twitching of small living beings in water. Both the above physiological phenomena, concerning the active and passive electrolocation of fish, has been mathematically developed as nature-inspired meta-heuristic technique named fish electrolocation optimization (FEO). A comparative study based on benchmark functions has been done amongst real coded genetic algorithm, accelerated particle swarm optimization, particle swarm optimization, harmony search and the proposed algorithm. Furthermore, comparative study has been done with simulated annealing and differential evolution on eggcrate function. The proposed technique has also been implemented on real-world optimization problem related to cost-based reliability enhancement in radial distribution system. It can be said by comparing percentage of success, mean number of function evaluation and standard deviation that FEO algorithm works better than other mentioned meta-heuristic techniques.

Optimal Power Flow Using Differential Search Algorithm

—In this article, a new nature-inspired metaheuristic technique called the differential search algorithm is proposed to solve the optimal power flow problem. The proposed differential search algorithm has been developed and tested under normal and contingency power system conditions. To show the effectiveness of the proposed method, it has been demonstrated on the standard IEEE 30-bus and IEEE 118-bus test systems with different objectives that reflect performance indices of the power system. Obtained results using the proposed technique indicate that the proposed differential search algorithm provides an effective, a robust, and a high-quality solution for the optimal power flow problem. The comparisons of the proposed differential search algorithm results with those reported in the literature reveal the potential and superiority of the proposed algorithm in terms of the optimal solution quality and robustness.

Nature-Inspired Metaheuristic Techniques as Powerful Optimizers in the Paper Industry

Nature-Inspired Metaheuristics (NIM) have emerged as a potent tool for solving complex and difficult optimization problems, arising in various industries, which otherwise become quite difficult (if not impossible) to solve by the classical methods based on gradient search. Further, NIM techniques are more likely to obtain a global optimal solution, often desired and sometimes a necessity in several real life situations. In this study we employ SABC, a variant of Artificial Bee Colony (ABC), a relatively newer NIM algorithm, for solving four typical processes of a paper mill where optimization can be applied. We have also considered two chemical process problems that can be related to paper industry. Numerical results show that the proposed SABC scheme is efficient in dealing with these problems.