meta-heuristic algorithms

In this paper, we present an improved imperialist competitive algorithm for solving an inverse form of the Huxley equation, which is a nonlinear partial differential equation. To show the effectiveness of our proposed algorithm, we conduct a comparative analysis with the original imperialist competitive algorithm and a genetic algorithm. The improvement suggested in this study makes the original imperialist competitive algorithm a more powerful method for function approximation. The numerical results show that the improved imperialist competitive algorithm is an efficient algorithm for determining the unknown boundary conditions of the Huxley equation and solving the inverse form of nonlinear partial differential equations.

Project portfolio selection is a critical challenge for many organizations as they often face budget constraints that limit their ability to support all available projects‎. ‎To address this issue‎, ‎organizations seek to select a feasible subset of projects that maximizes utility‎. ‎While several models for project portfolio selection based on multiple criteria have been proposed‎, ‎they are typically NP-hard problems‎. ‎In this study‎, ‎we propose an efficient Variable Neighborhood Search (VNS) algorithm to solve these problems‎. ‎Our algorithm includes a formula for computing the difference value of the objective function‎, ‎which enhances its accuracy and ensures that selected projects meet desired criteria‎. ‎We demonstrate the effectiveness of our algorithm through rigorous testing and comparison with a genetic algorithm (GA) and CPLEX‎. ‎The results of the Wilcoxon non-parametric test confirm that our algorithm outperforms both GA and CPLEX in terms of speed and accuracy‎. ‎Moreover‎, ‎the variance of the relative error of our algorithm is less than that of GA‎.

Diabetes is a dangerous disease in which the body is incapable of controlling blood sugar due to inadequate insulin hormone levels. This chronic disease increases blood sugar in patients. Therefore, if it is not controlled, it will cause many complications. A considerable number of people in the world suffer from this disease owing to its damage and lack of its initial diagnosis. The patient visits the doctor frequently to diagnose his/her illness and conducts various tests that are boring and costly. Increasing machine learning approaches through heuristics, and novel methods can somewhat decrease the problems. The current study aims to propose a model that can predict diabetes in patients with high accuracy. The paper introduces a new method based on the assortment of metaheuristic algorithms of a particle swarm and fuzzy inference system. The proposed method utilizes fuzzy systems to binary the particle swarm algorithm. The achieved model is applied to the diabetes dataset and then evaluated using a neural network classifier. The results indicate an increase in classification accuracy to 95.47% compared to other existing methods.

In this paper, we introduce a new iterative method for finding the fixed point of a nonlinear function. In fact, we want to offer a new way to obtain the fixed point of various functions using the Grey Wolf Optimizer algorithm. This method is new and very efficient for solving a nonlinear equation. We explain this method with three benchmark functions and compare results with other methods, such as ALO, MVO, MFO and SCA.

One of the main goals of network planners is the protection of important nodes in a network against natural disasters, security threats, attacks, and so on.  Given the importance of this issue,  a new model is presented in this paper for protecting an important node  in a typical network based on a defensive location problem where the two  agents threaten  this node.  The protecting facilities location problem with two agents is formulated as a three-level programming problem.   The decision maker in the upper level is a network planner agent. The planner agent wants to find the best possible location of protecting facilities  to protect the important node against threatening agents. The second and third levels problems are stated as the shortest path problems in the network in which the edges are weighted with positive values. In this work, the genetic, variable neighborhood search, simulated annealing algorithms are used to solve the problem.  The performance of the used metaheuristic algorithms on this class of problems is investigated by a test problem that is generated randomly. Then,   t-test  are used to compare the performance of these algorithms. The best results are obtained by  the variable neighborhood search algorithm.

Investors are always interested to choose the portfolio with the highest return and lowest risk for optimal asset management. A multi-objective portfolio optimization problem with cardinality constraint that determines the number of assets in a portfolio is considered in this paper. Objectives are maximizing the expected value of wealth and minimizing value at risk and conditional value at risk. Due to the complexity of the problem, it is necessary to use meta-heuristic algorithms. We use multi-objective evolutionary algorithms (Multi-Objective Particle Swarm Optimization, Non-Dominated Sorting Genetic Algorithm-II) to overcome this problem. In this research, the liquidity constraint and the thresholds of investments are considered. We use experts’ opinions in a fuzzy method to deal with the uncertainties in the parameters and provide better and more quality decisions. Finally, an Iranian stock market case study is presented to examine the proposed model in various situations. The results indicate that examining uncertainties and other real-world assumptions provides more efficient and practical solutions.