Publications by authors named "Shizheng Qu"
The Whale Optimization Algorithm (WOA) is regarded as a classic metaheuristic algorithm, yet it suffers from limited population diversity, imbalance between exploitation and exploration, and low solution accuracy. In this paper, we propose the Spiral-Enhanced Whale Optimization Algorithm (SEWOA), which incorporates a nonlinear time-varying self-adaptive perturbation strategy and an Archimedean spiral structure into the original WOA. The Archimedean spiral structure enhances the diversity of the solution space, aiding the algorithm in escaping local optima.
View Article and Find Full Text PDFArticle Synopsis
- * A new multi-view multi-label fast network is proposed, which uses two different views and incorporates advanced techniques for rapid and precise identification of six distinct phenotypic features.
- * The network achieved a high classification accuracy of 94.66% and an inference speed of 11.9 ms, demonstrating its effectiveness in accurately classifying Auricularia cornea fruiting bodies.
The setting of parameter values will directly affect the performance of the neural network, and the manual parameter tuning speed is slow, and it is difficult to find the optimal combination of parameters. Based on this, this paper applies the improved Hunger Games search algorithm to find the optimal value of neural network parameters adaptively, and proposes an ATHGS-GoogleNet model. Firstly, adaptive weights and chaos mapping were integrated into the hunger search algorithm to construct a new algorithm, ATHGS.
View Article and Find Full Text PDF