This paper presents a novel application of metaheuristic algorithmsfor solving stochastic programming problems using a recently developed gainingsharingknowledgebased optimization (GSK) algorithm. The algorithmis b...
详细信息
This paper presents a novel application of metaheuristic algorithmsfor solving stochastic programming problems using a recently developed gainingsharingknowledgebased optimization (GSK) algorithm. The algorithmis based on human behavior in which people gain and share their knowledgewith others. Different types of stochastic fractional programming problemsare considered in this study. The augmented Lagrangian method (ALM)is used to handle these constrained optimization problems by convertingthem into unconstrained optimization problems. Three examples from theliterature are considered and transformed into their deterministic form usingthe chance-constrained technique. The transformed problems are solved usingGSK algorithm and the results are compared with eight other state-of-the-artmetaheuristic algorithms. The obtained results are also compared with theoptimal global solution and the results quoted in the literature. To investigatethe performance of the GSK algorithm on a real-world problem, a solidstochastic fixed charge transportation problem is examined, in which theparameters of the problem are considered as random variables. The obtainedresults show that the GSK algorithm outperforms other algorithms in termsof convergence, robustness, computational time, and quality of obtainedsolutions.
gaining -sharingknowledgebasedalgorithm (GSK) is a recently emerged meta -heuristic algorithmbased on human behavior and has been successfully applied to solve various optimization problems. However, GSK tends to ...
详细信息
gaining -sharingknowledgebasedalgorithm (GSK) is a recently emerged meta -heuristic algorithmbased on human behavior and has been successfully applied to solve various optimization problems. However, GSK tends to get trapped in local optimum due to the rapid loss of population diversity during the optimization process, resulting in an imbalance between exploration and exploitation. To overcome this deficiency, this paper proposes an enhancing population diversity based GSK (EPD-GSK) framework. The proposed EPDGSK framework incorporates three components: (1) The utilization of Sobol sequence with low divergence to initialize the population, enhancing the diversity of initial solutions. (2) The integration of the Cauchy mutation strategy in the junior phase to perturb individuals and expand the search space. (3) The application of the reverse learning update mechanism in the senior phase, increasing the likelihood of escaping local optimum. These techniques promote population diversity throughout the exploration and exploitation stages. The proposed EPD-GSK framework was evaluated on CEC2017, CEC2020, and the latest CEC2022 test suites as well as on four constrained real -world engineering design problems. The experimental results demonstrate that EPD-GSK can effectively improve the performance of various existing GSK algorithms. Furthermore, EPD-GSK also exhibits better performance compared with other state-of-the-art algorithms.
Despite the effectiveness of deep neural networks, feed-forward neural networks (FFNNs) continue to play a crucial role in many applications, especially when dealing with limited data availability. The primary challen...
详细信息
Despite the effectiveness of deep neural networks, feed-forward neural networks (FFNNs) continue to play a crucial role in many applications, especially when dealing with limited data availability. The primary challenge in FFNNs is determining the optimal weights during the training process, aiming to minimise the disparity between actual and predicted outputs. Although gradient-based techniques like backpropagation (BP) have traditionally been popular for FFNN training, they come with inherent limitations, such as sensitivity to initial weights and susceptibility to getting trapped in local optima. To overcome these challenges, we introduce a novel approach based on the gaining-sharingknowledge-based(GSK) algorithm. To the best of our knowledge, this paper represents the first exploration of GSK for neural network training. After obtaining the appropriate weights for the FFNN by the GSK, the weights and biases are utilised to initialise a Levenberg-Marquardt backpropagation (LMBP) algorithm, serving as a local search component. In other words, our proposed algorithm, GSK-LocS, leverages the global search capabilities of the GSK algorithm and combines them with the local search capabilities of LMBP for neural network training. This integration mitigates sensitivity to initial values and reduces the risk of being trapped in local optima. Experimental results conducted on classification and approximation problems provide compelling evidence that our proposed algorithm is highly competitive compared to other existing methods.
暂无评论