Improved marine predators algorithm for feature selection and SVM optimization

Heming Jia,Kangjian Sun,Yao Li,Ning Cao 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.4

Owing to the rapid development of information science, data analysis based on machine learning has become an interdisciplinary and strategic area. Marine predators algorithm (MPA) is a novel metaheuristic algorithm inspired by the foraging strategies of marine organisms. Considering the randomness of these strategies, an improved algorithm called co-evolutionary cultural mechanism-based marine predators algorithm (CECMPA) is proposed. Through this mechanism, search agents in different spaces can share knowledge and experience to improve the performance of the native algorithm. More specifically, CECMPA has a higher probability of avoiding local optimum and can search the global optimum quickly. In this paper, it is the first to use CECMPA to perform feature subset selection and optimize hyperparameters in support vector machine (SVM) simultaneously. For performance evaluation the proposed method, it is tested on twelve datasets from the university of California Irvine (UCI) repository. Moreover, the coronavirus disease 2019 (COVID-19) can be a real-world application and is spreading in many countries. CECMPA is also applied to a COVID-19 dataset. The experimental results and statistical analysis demonstrate that CECMPA is superior to other compared methods in the literature in terms of several evaluation metrics. The proposed method has strong competitive abilities and promising prospects.

Modified beluga whale optimization with multi-strategies for solving engineering problems

Jia Heming,Wen Qixian,Wu Di,Wang Zhuo,WANG YUHAO,Wen Changsheng,Abualigah Laith 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.6

The beluga whale optimization (BWO) algorithm is a recently proposed metaheuristic optimization algorithm that simulates three behaviors: beluga whales interacting in pairs to perform mirror swimming, population sharing information to cooperate in predation, and whale fall. However, the optimization performance of the BWO algorithm still needs to be improved to enhance its practicality. This paper proposes a modified beluga whale optimization (MBWO) with a multi-strategy. It was inspired by beluga whales’ two behaviors: group gathering for foraging and searching for new habitats in long-distance migration. This paper proposes a group aggregation strategy (GAs) and a migration strategy (Ms). The GAs can improve the local development ability of the algorithm and accelerate the overall rate of convergence through the group aggregation fine search; the Ms randomly moves towards the periphery of the population, enhancing the ability to jump out of local optima. In order to verify the optimization ability of MBWO, this article conducted comprehensive testing on MBWO using 23 benchmark functions, IEEE CEC2014, and IEEE CEC2021. The experimental results indicate that MBWO has a strong optimization ability. This paper also tests MBWO’s ability to solve practical engineering optimization problems through five practical engineering problems. The final results prove the effectiveness of MBWO in solving practical engineering optimization problems.

An Improved Reptile Search Algorithm with Ghost Opposition-based Learning for Global Optimization Problems

Jia Heming,Lu Chenghao,Wu Di,Wen Changsheng,Rao Honghua,Abualigah Laith 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.4

In 2021, a meta-heuristic algorithm, Reptile Search Algorithm (RSA), was proposed. RSA mainly simulates the cooperative predatory behavior of crocodiles. Although RSA has a fast convergence speed, due to the influence of the crocodile predation mechanism, if the algorithm falls into the local optimum in the early stage, RSA will probably be unable to jump out of the local optimum, resulting in a poor comprehensive performance. Because of the shortcomings of RSA, introducing the local escape operator can effectively improve crocodiles' ability to explore space and generate new crocodiles to replace poor crocodiles. Benefiting from adding a restart strategy, when the optimal solution of RSA is no longer updated, the algorithm’s ability to jump out of the local optimum is effectively improved by randomly initializing the crocodile. Then joining Ghost opposition-based learning to balance the IRSA’s exploitation and exploration, the Improved RSA with Ghost Opposition-based Learning for the Global Optimization Problem (IRSA) is proposed. To verify the performance of IRSA, we used nine famous optimization algorithms to compare with IRSA in 23 standard benchmark functions and CEC2020 test functions. The experiments show that IRSA has good optimization performance and robustness, and can effectively solve six classical engineering problems, thus proving its effectiveness in solving practical problems.

Multi-strategy Remora Optimization Algorithm for solving multi-extremum problems

Jia Heming,LI YONGCHAO,Wu Di,Rao Honghua,Wen Changsheng,Abualigah Laith 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.4

A metaheuristic algorithm that simulates the foraging behavior of remora has been proposed in recent years, called ROA. ROA mainly simulates host parasitism and host switching in the foraging behavior of remora. However, in the experiment, it was found that there is still room for improvement in the performance of ROA. When dealing with complex optimization problems, ROA often falls into local optimal solutions, and there is also the problem of too-slow convergence. Inspired by the natural rule of “Survival of the fittest”, this paper proposes a random restart strategy to improve the ability of ROA to jump out of the local optimal solution. Secondly, inspired by the foraging behavior of remora, this paper adds an information entropy evaluation strategy and visual perception strategy based on ROA. With the blessing of three strategies, a multi-strategy Remora Optimization Algorithm (MSROA) is proposed. Through 23 benchmark functions and IEEE CEC2017 test functions, MSROA is comprehensively tested, and the experimental results show that MSROA has strong optimization capabilities. In order to further verify the application of MSROA in practice, this paper tests MSROA through five practical engineering problems, which proves that MSROA has strong competitiveness in solving practical optimization problems.

Improved snow ablation optimizer with heat transfer and condensation strategy for global optimization problem

Jia Heming,You Fangkai,Wu Di,Rao Honghua,Wu Hangqu,Abualigah Laith 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.6

The snow ablation optimizer (SAO) is a new metaheuristic algorithm proposed in April 2023. It simulates the phenomenon of snow sublimation and melting in nature and has a good optimization effect. The SAO proposes a new two-population mechanism. By introducing Brownian motion to simulate the random motion of gas molecules in space. However, as the temperature factor changes, most water molecules are converted into water vapor, which breaks the balance between exploration and exploitation, and reduces the optimization ability of the algorithm in the later stage. Especially in the face of high-dimensional problems, it is easy to fall into local optimal. In order to improve the efficiency of the algorithm, this paper proposes an improved snow ablation optimizer with heat transfer and condensation strategy (SAOHTC). Firstly, this article proposes a heat transfer strategy, which utilizes gas molecules to transfer heat from high to low temperatures and move their positions from low to high temperatures, causing individuals with lower fitness in the population to move towards individuals with higher fitness, thereby improving the optimization efficiency of the original algorithm. Secondly, a condensation strategy is proposed, which can transform water vapor into water by simulating condensation in nature, improve the deficiency of the original two-population mechanism, and improve the convergence speed. Finally, to verify the performance of SAOHTC, in this paper, two benchmark experiments of IEEE CEC2014 and IEEE CEC2017 and five engineering problems are used to test the superior performance of SAOHTC.

Improve coati optimization algorithm for solving constrained engineering optimization problems

Jia Heming,Shi Shengzhao,Wu Di,Rao Honghua,Zhang Jinrui,Abualigah Laith 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.6

The coati optimization algorithm (COA) is a meta-heuristic optimization algorithm proposed in 2022. It creates mathematical models according to the habits and social behaviors of coatis: (i) In the group organization of the coatis, half of the coatis climb trees to chase their prey away, while the other half wait beneath to catch it and (ii) Coatis avoidance predators behavior, which gives the algorithm strong global exploration ability. However, over the course of our experiment, we uncovered opportunities for enhancing the algorithm’s performance. When confronted with intricate optimization problems, certain limitations surfaced. Much like a long-nosed raccoon gradually narrowing its search range as it approaches the optimal solution, COA algorithm exhibited tendencies that could result in reduced convergence speed and the risk of becoming trapped in local optima. In this paper, we propose an improved coati optimization algorithm (ICOA) to enhance the algorithm’s efficiency. Through a sound-based search envelopment strategy, coatis can capture prey more quickly and accurately, allowing the algorithm to converge more rapidly. By employing a physical exertion strategy, coatis can have a greater variety of escape options when being chased, thereby enhancing the algorithm’s exploratory capabilities and the ability to escape local optima. Finally, the lens opposition-based learning strategy is added to improve the algorithm’s global performance. To validate the performance of the ICOA, we conducted tests using the IEEE CEC2014 and IEEE CEC2017 benchmark functions, as well as six engineering problems.

Reinforcement learning guided Spearman dynamic opposite Gradient-based optimizer for numerical optimization and anchor clustering

Sun Kangjian,Huo Junhong,Jia Heming,Yue Lin 한국CDE학회 2024 Journal of computational design and engineering Vol.11 No.1

As science and technology advance, the need for novel optimization techniques has led to an increase. The recently proposed metaheuristic algorithm, Gradient-based optimizer (GBO), is rooted in the gradient-based Newton's method. GBO has a more concrete theoretical foundation. However, gradient search rule (GSR) and local escaping operator (LEO) operators in GBO still have some shortcomings. The insufficient updating method and the simple selection process limit the search performance of the algorithm. In this paper, an improved version is proposed to compensate for the above shortcomings, called RL-SDOGBO. First, during the GSR phase, the Spearman rank correlation coefficient is used to determine weak solutions on which to perform dynamic opposite learning. This operation assists the algorithm to escape from local optima and enhance exploration capability. Secondly, to optimize the exploitation capability, reinforcement learning is used to guide the selection of solution update modes in the LEO operator. RL-SDOGBO is tested on 12 classical benchmark functions and 12 CEC2022 benchmark functions with seven representative metaheuristics, respectively. The impact of the improvements, the scalability and running time of the algorithm, and the balance of exploration and exploitation are analyzed and discussed. Combining the experimental results and some statistical results, RL-SDOGBO exhibits excellent numerical optimization performance and provides high-quality solutions in most cases. In addition, RL-SDOGBO is also used to solve the anchor clustering problem for small target detection, making it a more potential and competitive option.

A multi-strategy enhanced African vultures optimization algorithm for global optimization problems

Zheng Rong,Hussien Abdelazim G,Qaddoura Raneem,Jia Heming,Abualigah Laith,Wang Shuang,Saber Abeer 한국CDE학회 2023 Journal of computational design and engineering Vol.10 No.1

The African vultures optimization algorithm (AVOA) is a recently proposed metaheuristic inspired by the African vultures’ behaviors. Though the basic AVOA performs very well for most optimization problems, it still suffers from the shortcomings of slow convergence rate and local optimal stagnation when solving complex optimization tasks. Therefore, this study introduces a modified version named enhanced AVOA (EAVOA). The proposed EAVOA uses three different techniques namely representative vulture selection strategy, rotating flight strategy, and selecting accumulation mechanism, respectively, which are developed based on the basic AVOA. The representative vulture selection strategy strikes a good balance between global and local searches. The rotating flight strategy and selecting accumulation mechanism are utilized to improve the quality of the solution. The performance of EAVOA is validated on 23 classical benchmark functions with various types and dimensions and compared to those of nine other state-of-the-art methods according to numerical results and convergence curves. In addition, three real-world engineering design optimization problems are adopted to evaluate the practical applicability of EAVOA. Furthermore, EAVOA has been applied to classify multi-layer perception using XOR and cancer datasets. The experimental results clearly show that the EAVOA has superiority over other methods.