Genetic Algorithm with Machine Learning to Estimate the Optimal Objective Function Values of Subproblems
Genetic Algorithm with Machine Learning to Estimate the Optimal Objective Function Values of Subproblems
复制标题
DOI：
10.1145/3533050.3533051
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
H. Iima;Yohei Hazama
中科院分区：
文献类型：
--
作者：
H. Iima;Yohei Hazama
本文讨论了具有两个决策变量向量的优化问题。当第一个决策变量向量被赋予任意值时，该问题可以分为多个子问题。在求解该问题的传统遗传算法中，一个个体往往用第一个决策变量向量的值来表示。在评估个体时，剩余决策变量向量的值由元分析或贪婪算法确定。然而，这样的遗传算法是耗时的或不是通用的。我们提出了一个遗传算法与神经网络模型来估计子问题的最优目标函数值。与其他遗传算法的实验结果表明，该方法是有效的。
This paper addresses an optimization problem with two decision variable vectors. This problem can be divided into multiple subproblems when an arbitrary value is given to the first decision variable vector. In conventional genetic algorithms (GAs) for the problem, an individual is often expressed by the value of the first decision variable vector. In evaluating the individual, the value of the remaining decision variable vector is determined by metaheuristics or greedy algorithms. However, such GAs are time-consuming or not general-purpose. We propose a GA with a neural network model to estimate the optimal objective function values of the subproblems. Experimental results compared to other GAs show that the proposed method is effective.