School of Emergency Management, Institute of Disaster Prevention, Langfang, 065201, China; Institute of Geophysics, China Earthquake Administration, Beijing, 100081, China.
School of Emergency Management, Institute of Disaster Prevention, Langfang, 065201, China.
Comput Biol Med. 2022 Jul;146:105563. doi: 10.1016/j.compbiomed.2022.105563. Epub 2022 Apr 28.
The heap-based optimizer (HBO) is an optimization method proposed in recent years that may face local stagnation problems and show slow convergence speed due to the lack of detailed analysis of optimal solutions and a comprehensive search. Therefore, to mitigate these drawbacks and strengthen the performance of the algorithm in the field of medical diagnosis, a new MGOHBO method is proposed by introducing the modified Rosenbrock's rotational direction method (MRM), an operator from the grey wolf optimizer (GWM), and an orthogonal learning strategy (OL). The MGOHBO is compared with eleven famous and improved optimizers on IEEE CEC 2017. The results on benchmark functions indicate that the boosted MGOHBO has several significant advantages in terms of convergence accuracy and speed of the process. Additionally, this article analyzed the diversity and balance of MGOHBO in detail. Finally, the proposed MGOHBO algorithm is utilized to optimize the kernel extreme learning machines (KELM), and a new MGOHBO-KELM is proposed. To validate the performance of MGOHBO-KELM, seven disease diagnostic questions were introduced for testing in this work. In contrast to advanced models such as HBO-KELM and BP, it can be concluded that the MGOHBO-KELM model can achieve optimal results, which also proves that it has practical significance in solving medical diagnosis problems.
基于堆的优化器（HBO）是近年来提出的一种优化方法，由于缺乏对最优解的详细分析和全面搜索，可能会面临局部停滞问题和较慢的收敛速度。因此，为了缓解这些缺点，并增强算法在医学诊断领域的性能，引入了改进的 Rosenbrock 旋转方向法（MRM）、灰狼优化器（GWM）中的一个算子以及正交学习策略（OL），提出了一种新的 MGOHBO 方法。将 MGOHBO 与 IEEE CEC 2017 上的 11 种著名改进优化器进行了比较。基准函数上的结果表明，增强后的 MGOHBO 在收敛精度和过程速度方面具有几个显著优势。此外，本文还详细分析了 MGOHBO 的多样性和平衡性。最后，将提出的 MGOHBO 算法用于优化核极限学习机（KELM），提出了一种新的 MGOHBO-KELM。为了验证 MGOHBO-KELM 的性能，本文引入了七个疾病诊断问题进行测试。与 HBO-KELM 和 BP 等先进模型相比，可以得出结论，MGOHBO-KELM 模型可以达到最优结果，这也证明了它在解决医学诊断问题方面具有实际意义。
