Meta-heuristic optimization algorithms for solving real-world mechanical engineering design problems: a comprehensive survey, applications, comparative analysis, and results

Enhanced slime mould algorithm with chaotic and orthogonal optimization-based learning for improved severity prediction accuracy in malaria patient outcomes

Malaria remains a critical health challenge in developing countries, particularly in Africa, where it disproportionately affects vulnerable populations. Accurate malaria severity prediction is important for proper treatment and improved patient survival rates. This study proposes an improved Slime Mould Algorithm (iSMA) to address the limitations of the standard SMA, including slow convergence, poor initialization, local optima entrapment, and imbalance between exploration and exploitation. The iSMA incorporates four key innovations: a Chaotic Initialization Strategy (CIS) to generate a diverse initial population, enhancing solution diversity; an enhanced Opposition-Based Learning (eOBL) mechanism to strengthen exploration; an Orthogonal Learning (OL) strategy to improve the balance between exploration and exploitation while accelerating convergence; and a Restart Strategy (RS) to reinitialize underperforming individuals, effectively preventing entrapment in local optima. Integrating the Random Forest (RF) feature selection process with the Support Vector Machine (SVM) classifier, forming the proposed new model RF-iSMA-SVM, classifies malaria into severe and no-severe cases. The iSMA performed better than nine other recent metaheuristic algorithms, as was broadly exhibited in the benchmark tests conducted on CEC2022 functions. When testing the RF-iSMA-SVM model on malaria datasets from health centers in Sierra Leone, the proposed model demonstrated superior predictive performance compared to recent conventional methods. The results yield an accuracy value of 0.981, specificity of 0.827, sensitivity of 0.974, and a Matthews Correlation Coefficient (MCC) score of 0.794. This shows the significant improvement over the standard techniques used for predicting the severity of malaria, which indicates great potential for healthcare practices and decision-making. These results support the model's reliability and effectiveness in improving the prediction of malaria severity. This study offers a novel practical tool for malaria case management by combining advanced optimization techniques with machine learning. It could enhance healthcare decision-making and improve outcomes for affected populations.

A Particle Swarm Optimization-Guided Ivy Algorithm for Global Optimization Problems

In recent years, metaheuristic algorithms have garnered significant attention for their efficiency in solving complex optimization problems. However, their performance critically depends on maintaining a balance between global exploration and local exploitation; a deficiency in either can result in premature convergence to local optima or low convergence efficiency. To address this challenge, this paper proposes an enhanced ivy algorithm guided by a particle swarm optimization (PSO) mechanism, referred to as IVYPSO. This hybrid approach integrates PSO's velocity update strategy for global searches with the ivy algorithm's growth strategy for local exploitation and introduces an ivy-inspired variable to intensify random perturbations. These enhancements collectively improve the algorithm's ability to escape local optima and enhance the search stability. Furthermore, IVYPSO adaptively selects between local growth and global diffusion strategies based on the fitness difference between the current solution and the global best, thereby improving the solution diversity and convergence accuracy. To assess the effectiveness of IVYPSO, comprehensive experiments were conducted on 26 standard benchmark functions and three real-world engineering optimization problems, with the performance compared against 11 state-of-the-art intelligent optimization algorithms. The results demonstrate that IVYPSO outperformed most competing algorithms on the majority of benchmark functions, exhibiting superior search capability and robustness. In the stability analysis, IVYPSO consistently achieved the global optimum across multiple runs on the three engineering cases with reduced computational time, attaining a 100% success rate (SR), which highlights its strong global optimization ability and excellent repeatability.

Multi-Strategy-Assisted Hybrid Crayfish-Inspired Optimization Algorithm for Solving Real-World Problems

In order to solve problems with the original crayfish optimization algorithm (COA), such as reduced diversity, local optimization, and insufficient convergence accuracy, a multi-strategy optimization algorithm for crayfish based on differential evolution, named the ICOA, is proposed. First, the elite chaotic difference strategy is used for population initialization to generate a more uniform crayfish population and increase the quality and diversity of the population. Secondly, the differential evolution strategy and the dimensional variation strategy are introduced to improve the quality of the crayfish population before its iteration and to improve the accuracy of the optimal solution and the local search ability for crayfish at the same time. To enhance the updating approach to crayfish exploration, the Levy flight strategy is adopted. This strategy aims to improve the algorithm's search range and local search capability, prevent premature convergence, and enhance population stability. Finally, the adaptive parameter strategy is introduced to improve the development stage of crayfish, so as to better balance the global search and local mining ability of the algorithm, and to further enhance the optimization ability of the algorithm, and the ability to jump out of the local optimal. In addition, a comparison with the original COA and two sets of optimization algorithms on the CEC2019, CEC2020, and CEC2022 test sets was verified by Wilcoxon rank sum test. The results show that the proposed ICOA has strong competition. At the same time, the performance of ICOA is tested against different high-performance algorithms on 6 engineering optimization examples, 30 high-low-dimension constraint problems and 2 large-scale NP problems. Numerical experiments results show that ICOA has superior performance on a range of engineering problems and exhibits excellent performance in solving complex optimization problems.

Swarm-initialized adaptive controller with beetle antenna searching of wearable lower limb exoskeleton for sit-to-stand and walking motions

In recent years, exoskeleton robots have attracted great interest from researchers in the area of robotics due to their ability to assist human functionality improvement. A wearable lower limb exoskeleton is aimed at supporting the limb functionality rehabilitation process and to assist physical therapists. Development of a stable and robust control system for multi-joint rehabilitation robots is a challenging task due to their non-linear dynamic systems. This paper presents the development of a Swarm-Initialized Adaptive (SIA) based controller, which is a combination of a swarm-based intelligence, named Swarm Beetle Antenna Searching (SBAS), and an adaptive Lyapunov-based controller. The SBAS initializes the parameters of SIA to efficiently improve the performance of the control system and then these controller parameters are updated by an adaptive controller. The control system is validated in a lower limb exoskeleton prototype with four degrees of freedom, using a healthy human subject for sit-to-stand and walking motions. The experimental results show the applicability of the proposed method and demonstrate that our approach obtained efficient control performance in terms of steady-state error and robustness and can be used for a lower limb exoskeleton to improve human mobility.

A Novel Hybrid Improved RIME Algorithm for Global Optimization Problems

The RIME algorithm is a novel physical-based meta-heuristic algorithm with a strong ability to solve global optimization problems and address challenges in engineering applications. It implements exploration and exploitation behaviors by constructing a rime-ice growth process. However, RIME comes with a couple of disadvantages: a limited exploratory capability, slow convergence, and inherent asymmetry between exploration and exploitation. An improved version with more efficiency and adaptability to solve these issues now comes in the form of Hybrid Estimation Rime-ice Optimization, in short, HERIME. A probabilistic model-based sampling approach of the estimated distribution algorithm is utilized to enhance the quality of the RIME population and boost its global exploration capability. A roulette-based fitness distance balanced selection strategy is used to strengthen the hard-rime phase of RIME to effectively enhance the balance between the exploitation and exploration phases of the optimization process. We validate HERIME using 41 functions from the IEEE CEC2017 and IEEE CEC2022 test suites and compare its optimization accuracy, convergence, and stability with four classical and recent metaheuristic algorithms as well as five advanced algorithms to reveal the fact that the proposed algorithm outperforms all of them. Statistical research using the Friedman test and Wilcoxon rank sum test also confirms its excellent performance. Moreover, ablation experiments validate the effectiveness of each strategy individually. Thus, the experimental results show that HERIME has better search efficiency and optimization accuracy and is effective in dealing with global optimization problems.

QSAR modelling of enzyme inhibition toxicity of ionic liquid based on chaotic spotted hyena optimization algorithm

Ionic liquids (ILs) have attracted considerable interest due to their unique properties and prospective uses in various industries. However, their potential toxicity, particularly regarding enzyme inhibition, has become a growing concern. In this study, a QSAR model was proposed to predict the enzyme inhibition toxicity of ILs. A dataset of diverse ILs with corresponding toxicity data against three enzymes was compiled. Molecular descriptors that capture the physicochemical, structural, and topological properties of the ILs were calculated. To optimize the selection of descriptors and develop a robust QSAR model, the chaotic spotted hyena optimization algorithm, a novel nature-inspired metaheuristic, was employed. The proposed algorithm efficiently searches for an optimal subset of descriptors and model parameters, enhancing the predictive performance and interpretability of the QSAR model. The developed model exhibits excellent predictive capability, with high classification accuracy and low computation time. Sensitivity analysis and molecular interpretation of the selected descriptors provide insights into the critical structural features influencing the toxicity of ILs. This study showcases the successful application of the chaotic spotted hyena optimization algorithm in QSAR modelling and contributes to a better understanding of the toxicity mechanisms of ILs, aiding in the design of safer alternatives for industrial applications.

A Self-Learning Hyper-Heuristic Algorithm Based on a Genetic Algorithm: A Case Study on Prefabricated Modular Cabin Unit Logistics Scheduling in a Cruise Ship Manufacturer

Hyper-heuristic algorithms are known for their flexibility and efficiency, making them suitable for solving engineering optimization problems with complex constraints. This paper introduces a self-learning hyper-heuristic algorithm based on a genetic algorithm (GA-SLHH) designed to tackle the logistics scheduling problem of prefabricated modular cabin units (PMCUs) in cruise ships. This problem can be regarded as a multi-objective fuzzy logistics collaborative scheduling problem. Hyper-heuristic algorithms effectively avoid the extensive evaluation and repair of infeasible solutions during the iterative process, which is a common issue in meta-heuristic algorithms. The GA-SLHH employs a genetic algorithm combined with a self-learning strategy as its high-level strategy (HLS), optimizing low-level heuristics (LLHs) while uncovering potential relationships between adjacent decision-making stages. LLHs utilize classic scheduling rules as solution support. Multiple sets of numerical experiments demonstrate that the GA-SLHH exhibits a stronger comprehensive optimization ability and stability when solving this problem. Finally, the validity of the GA-SLHH in addressing real-world decision-making issues in cruise ship manufacturing companies is validated through practical enterprise cases. The results of a practical enterprise case show that the scheme solved using the proposed GA-SLHH can reduce the transportation time by up to 37%.

Population interaction network in representative gravitational search algorithms: Logistic distribution leads to worse performance

In this paper, a novel study on the way inter-individual information interacts in meta-heuristic algorithms (MHAs) is carried out using a scheme known as population interaction networks (PIN). Specifically, three representative MHAs, including the differential evolutionary algorithm (DE), the particle swarm optimization algorithm (PSO), the gravitational search algorithm (GSA), and four classical variations of the gravitational search algorithm, are analyzed in terms of inter-individual information interactions and the differences in the performance of each of the algorithms on IEEE Congress on Evolutionary Computation 2017 benchmark functions. The cumulative distribution function (CDF) of the node degree obtained by the algorithm on the benchmark function is fitted to the seven distribution models by using PIN. The results show that among the seven compared algorithms, the more powerful DE is more skewed towards the Poisson distribution, and the weaker PSO, GSA, and GSA variants are more skewed towards the Logistic distribution. The more deviation from Logistic distribution GSA variants conform, the stronger their performance. From the point of view of the CDF, deviating from the Logistic distribution facilitates the improvement of the GSA. Our findings suggest that the population interaction network is a powerful tool for characterizing and comparing the performance of different MHAs in a more comprehensive and meaningful way.

Neural network-based performance assessment of one- and two-liquid phase biotrickling filters for the removal of a waste-gas mixture containing methanol, α-pinene, and hydrogen sulfide

The performance of one- and two-liquid phase biotrickling filters (OLP/TLP-BTFs) treating a mixture of gas-phase methanol (M), α-pinene (P), and hydrogen sulfide (H) was assessed using artificial neural network (ANN) modeling. The best ANN models with the topologies 3-9-3 and 3-10-3 demonstrated an exceptional capacity for predicting the performance of O/TLP-BTFs, with R2 > 99%. The analysis of causal index (CI) values for the model of OLP-BTF revealed a negative impact of M on P removal (CI = -2.367), a positive influence of P and H on M removal (CI = +7.536 and CI = +3.931) and a negative effect of H on P removal (CI = -1.640). The addition of silicone oil in TLP-BTF reduced the negative impact of M and H on P degradation (CI = -1.261 and CI = -1.310, respectively) compared to the OLP-BTF. These findings suggested that silicone oil had the potential to improve P availability to the biofilm by increasing the concentration gradient of P between the air/gas and aqueous phases. Multi-objective particle swarm optimization (MOPSO) suggested an optimum operational condition, i.e. inlet M, P, and H concentrations of 1.0, 1.1, and 0.3 g m-3, respectively, with elimination capacities (ECs) of 172.1, 26.5, and 0.025 g m-3 h-1 for OLP-BTF. Likewise, one of the optimum operational conditions for TLP-BTF is achievable at inlet concentrations of 4.9, 1.7, and 0.8 g m-3, leading to the optimum ECs of 299.7, 52.9, and 0.072 g m-3 h-1 for M, P, and H, respectively. These results provide important insights into the treatment of complex waste gas mixtures, addressing the interactions between the pollutant removal characteristics in OLP/TLP-BTFs and providing novel approaches in the field of biological waste gas treatment.

Maximum Lyapunov exponent-based multiple chaotic slime mold algorithm for real-world optimization

Slime mold algorithm (SMA) is a nature-inspired algorithm that simulates the biological optimization mechanisms and has achieved great results in various complex stochastic optimization problems. Owing to the simulated biological search principle of slime mold, SMA has a unique advantage in global optimization problem. However, it still suffers from issues of missing the optimal solution or collapsing to local optimum when facing complicated problems. To conquer these drawbacks, we consider adding a novel multi-chaotic local operator to the bio-shock feedback mechanism of SMA to compensate for the lack of exploration of the local solution space with the help of the perturbation nature of the chaotic operator. Based on this, we propose an improved algorithm, namely MCSMA, by investigating how to improve the probabilistic selection of chaotic operators based on the maximum Lyapunov exponent (MLE), an inherent property of chaotic maps. We implement the comparison between MCSMA with other state-of-the-art methods on IEEE Congress on Evolution Computation (CEC) i.e., CEC2017 benchmark test suits and CEC2011 practical problems to demonstrate its potency and perform dendritic neuron model training to test the robustness of MCSMA on classification problems. Finally, the parameters' sensitivities of MCSMA, the utilization of the solution space, and the effectiveness of the MLE are adequately discussed.

van Staden R, Fragomeni S. Shrink–swell index prediction through deep learning

Growing application of artificial intelligence in geotechnical engineering has been observed; however, its ability to predict the properties and nonlinear behaviour of reactive soil is currently not well considered. Although previous studies provided linear correlations between shrink–swell index and Atterberg limits, obtained model accuracy values were found unsatisfactory results. Artificial intelligence, specifically deep learning, has the potential to give improved accuracy. This research employed deep learning to predict more accurate values of shrink–swell indices, which explored two scenarios; Scenario 1 used the features liquid limit, plastic limit, plasticity index, and linear shrinkage, whilst Scenario 2 added the input feature, fines percentage passing through a 0.075-mm sieve (%fines). Findings indicated that the implementation of deep learning neural networks resulted in increased model measurement accuracy in Scenarios 1 and 2. The values of accuracy measured in this study were suggestively higher and have wider variance than most previous studies. Global sensitivity analyses were also conducted to investigate the influence of each input feature. These sensitivity analyses resulted in a range of predicted values within the variance of data in Scenario 2, with the %fines having the highest contribution to the variance of the shrink–swell index and a relevant interaction between linear shrinkage and %fines. The proposed model Scenario 2 was around 10–65% more accurate than the preceding models considered in this study, which can then be used to expeditiously estimate more accurate values of shrink–swell indices.

Classification of breast cancer using a manta-ray foraging optimized transfer learning framework

Due to its high prevalence and wide dissemination, breast cancer is a particularly dangerous disease. Breast cancer survival chances can be improved by early detection and diagnosis. For medical image analyzers, diagnosing is tough, time-consuming, routine, and repetitive. Medical image analysis could be a useful method for detecting such a disease. Recently, artificial intelligence technology has been utilized to help radiologists identify breast cancer more rapidly and reliably. Convolutional neural networks, among other technologies, are promising medical image recognition and classification tools. This study proposes a framework for automatic and reliable breast cancer classification based on histological and ultrasound data. The system is built on CNN and employs transfer learning technology and metaheuristic optimization. The Manta Ray Foraging Optimization (MRFO) approach is deployed to improve the framework's adaptability. Using the Breast Cancer Dataset (two classes) and the Breast Ultrasound Dataset (three-classes), eight modern pre-trained CNN architectures are examined to apply the transfer learning technique. The framework uses MRFO to improve the performance of CNN architectures by optimizing their hyperparameters. Extensive experiments have recorded performance parameters, including accuracy, AUC, precision, F1-score, sensitivity, dice, recall, IoU, and cosine similarity. The proposed framework scored 97.73% on histopathological data and 99.01% on ultrasound data in terms of accuracy. The experimental results show that the proposed framework is superior to other state-of-the-art approaches in the literature review.

Design of Aquila Optimization Heuristic for Identification of Control Autoregressive Systems

Swarm intelligence-based metaheuristic algorithms have attracted the attention of the research community and have been exploited for effectively solving different optimization problems of engineering, science, and technology. This paper considers the parameter estimation of the control autoregressive (CAR) model by applying a novel swarm intelligence-based optimization algorithm called the Aquila optimizer (AO). The parameter tuning of AO is performed statistically on different generations and population sizes. The performance of the AO is investigated statistically in various noise levels for the parameters with the best tuning. The robustness and reliability of the AO are carefully examined under various scenarios for CAR identification. The experimental results indicate that the AO is accurate, convergent, and robust for parameter estimation of CAR systems. The comparison of the AO heuristics with recent state of the art counterparts through nonparametric statistical tests established the efficacy of the proposed scheme for CAR estimation.