Slime mould algorithm: a comprehensive review of recent variants and applications

International Journal of Systems Science, Год журнала: 2022, Номер 54(1), С. 204 - 235

Опубликована: Дек. 16, 2022

Slime Mould Algorithm (SMA) has recently received much attention from researchers because of its simple structure, excellent optimisation capabilities, and acceptable convergence in dealing with various types complex real-world problems. this study aims to retrieve, identify, summarise analyse critical studies related SMA development. Based on this, 98 SMA-related the Web Science were retrieved, selected, identified. The two main review vectors advanced versions SMAs application domains. First, we counted analysed SMAs, summarised, classified, discussed their improvement methods directions. Secondly, sort out domains role, development status, shortcomings each domain. A survey based existing literature shows that clearly outperform some established metaheuristics terms speed accuracy handling benchmark problems solving multiple realistic optimization This not only suggests possible future directions field but, due inclusion graphical tabular comparisons properties, also provides a comprehensive source information about SAMs scope adaptation for

Язык: Английский

---

An improved algorithm optimization algorithm based on RungeKutta and golden sine strategy

Expert Systems with Applications, Год журнала: 2024, Номер 247, С. 123262 - 123262

Опубликована: Янв. 25, 2024

Язык: Английский

---

Multi-objective equilibrium optimizer slime mould algorithm and its application in solving engineering problems

Structural and Multidisciplinary Optimization, Год журнала: 2023, Номер 66(5)

Опубликована: Апрель 24, 2023

Язык: Английский

---

Self-adaptive hybrid mutation slime mould algorithm: Case studies on UAV path planning, engineering problems, photovoltaic models and infinite impulse response

Alexandria Engineering Journal, Год журнала: 2024, Номер 98, С. 364 - 389

Опубликована: Май 11, 2024

There are many classic highly complex optimization problems in the world, therefore, it is still necessary to find an applicable and effective algorithm solve these problems. In this paper, self-adaptive hybrid cross mutation slime mold proposed, which AHCSMA, efficiently. Specifically, there three innovations paper: (i) new Cauchy operator developed improve ability of population; (ii) crossover rate balance mechanism proposed make up for neglected relationship between individuals rates. Then differential vector information dominant individual other population utilized increase evolution speed algorithm; (iii) restart opposition learning designed alleviate situation where falls into local optimality. To verify competitive UAV path planning problems, engineering nonlinear parameter extraction photovoltaic model identification infinite impulse response used test accumulation more than 50 algorithms as comparison algorithms, results report that AHCSMA extremely performs better when optimizing real-life

Язык: Английский

---

A grade-based search adaptive random slime mould optimizer for lupus nephritis image segmentation

Computers in Biology and Medicine, Год журнала: 2023, Номер 160, С. 106950 - 106950

Опубликована: Апрель 17, 2023

Язык: Английский

---

An equilibrium optimizer slime mould algorithm for inverse kinematics of the 7-DOF robotic manipulator

Scientific Reports, Год журнала: 2022, Номер 12(1)

Опубликована: Июнь 8, 2022

Abstract In order to solve the inverse kinematics (IK) of complex manipulators efficiently, a hybrid equilibrium optimizer slime mould algorithm (EOSMA) is proposed. Firstly, concentration update operator used guide anisotropic search improve efficiency. Then, greedy strategy individual and global historical optimal accelerate algorithm’s convergence. Finally, random difference mutation added EOSMA increase probability escaping from local optimum. On this basis, multi-objective (MOEOSMA) MOEOSMA are applied IK 7 degrees freedom manipulator in two scenarios compared with 15 single-objective 9 algorithms. The results show that has higher accuracy shorter computation time than previous studies. scenarios, average convergence 10e−17 10e−18, solution 0.05 s 0.36 s, respectively.

Язык: Английский

---

IBMSMA: An Indicator-based Multi-swarm Slime Mould Algorithm for Multi-objective Truss Optimization Problems

Journal of Bionic Engineering, Год журнала: 2022, Номер 20(3), С. 1333 - 1360

Опубликована: Дек. 1, 2022

Язык: Английский

---

Research on Fault Location in DC Distribution Network Based on Adaptive Artificial Bee Colony Slime Mould Algorithm

IEEE Access, Год журнала: 2023, Номер 11, С. 62630 - 62638

Опубликована: Янв. 1, 2023

To address the problems of slow convergence speed, easy to fall into local minima and low accuracy presented by previous algorithms in DC distribution network fault location, this paper adopts improved artificial bee colony slime mould algorithm (SMA) improve solve. On basis SMA, an adaptive adjustable feedback factor crossover operator are introduced speed; (ABC) is search ability jump out minima, (ISMA) formed. Firstly, based on six-terminal topology, a mathematical model bipolar short-circuit as well single-pole grounded established occurring between G-VSC W-VSC example. Then principle ISMA detail, suitable fitness function measure location network. Finally, experimental simulations conducted obtain points from optimization compare them with actual values verify algorithm. In addition, efficiency robustness further verified comparing other algorithms.

Язык: Английский

---

Simultaneous SVM Parameters and Feature Selection Optimization Based on Improved Slime Mould Algorithm

IEEE Access, Год журнала: 2024, Номер 12, С. 18215 - 18236

Опубликована: Янв. 1, 2024

To address the problems of low classification accuracy, redundancy feature subsets, and performance susceptibility to parameters in wrapper-based selection traditional Support Vector Machine (SVM), an improved Slime Mould Algorithm (ISMA) was proposed for simultaneous optimization SVM selection. Firstly, golden section coefficient introduced improve position update mechanism slime mould individuals, so as accelerate convergence speed SMA local development ability accuracy SMA. Secondly, adaptive lens-imaging learning strategy proposed, which selects a solution with largest difference from optimal highest fitness value through Fitness-Distance Balance method, reverse only performed on its specific dimension, order better balance exploration capabilities Finally, vertical crossover used expand search range, thereby reducing probability algorithm falling into optimum. The experimental results test show that ISMA has higher stability faster speed, high practical engineering problems. Use optimize simultaneously. Simulation experiments were carried out 10 UCI datasets method this paper can obtain under condition effectively 7 is 90% above, reached 100% 2 datasets. In further prove practicability problems, based applied microarray gene expression problem, two cancer obtains when using small number predicted genes, good application diagnosis classification.

Язык: Английский

---

Escape: an optimization method based on crowd evacuation behaviors

Artificial Intelligence Review, Год журнала: 2024, Номер 58(1)

Опубликована: Ноя. 16, 2024

Meta-heuristic algorithms, particularly those based on swarm intelligence, are highly effective for solving black-box optimization problems. However, maintaining a balance between exploration and exploitation within these algorithms remains significant challenge. This paper introduces useful algorithm, called Escape or Algorithm (ESC), inspired by crowd evacuation behavior, to solve real-world cases benchmark The ESC algorithm simulates the behavior of crowds during evacuation, where population is divided into calm, herding, panic groups phase, reflecting different levels decision-making emotional states. Calm individuals guide toward safety, herding imitate others in less secure areas, make volatile decisions most dangerous zones. As transitions converges optimal solutions, akin finding safest exit. effectiveness validated two adjustable problem size test suites, CEC 2017 2022. ranked first 10-dimensional, 30-dimensional tests 2017, 10-dimensional 20-dimensional 2022, second 50-dimensional 100-dimensional 2017. Additionally, performed exceptionally well, ranking engineering problems pressure vessel design, tension/compression spring rolling element bearing as well 3D UAV path planning problems, demonstrating its efficiency complex like planning. Compared with 12 other high-performance, classical, advanced exhibited superior performance source codes will be shared at https://aliasgharheidari.com/ESC.html websites.

Язык: Английский

---