摘要
为了提升恶性肿瘤的诊断效率及精准度,基于动态粒子群优化(DPSO)算法和支持向量机提出了DPSO-SVM诊断模型。DPSO在PSO的基础上结合GridSearch,GA等算法对惯性权重的取值以及种群迭代更新方式进行了改进,平衡了算法迭代前期的全局搜索性能与后期的局部搜索性能,提升了迭代后期种群的多样性和收敛速度。仿真实验结果表明,所提出的改进DPSO算法相比传统算法以及标准智能算法寻优效果有明显提升,构建的DPSO-SVM诊断模型与主流诊断模型相比在肿瘤诊断中也有着更优越的性能,提升了诊断效率的同时也降低了诊断误差。
In order to improve the diagnosis efficiency and accuracy of malignant tumors,a DPSO-SVM diagnosis model is proposed in this paper on the basis of dynamic particle swarm optimization(DPSO)algorithm and support vector machine(SVM).The value of inertia weight and the update mode of population iteration is improved by DPSO in combination with GridSearch,GA(genetic algorithm)and other algorithms and on the basis of PSO,which balances the global search performance in the early stage of the algorithm iteration and the local search performance in the later stage of the algorithm iteration,and improves the diversity and convergence speed of the population in the later stage of the iteration.The simulation experiment results show that,in the aspect of optimizing effect,the improved DPSO algorithm is better than the traditional algorithm and the standard intelligent algorithm,and the DPSO-SVM diagnosis model has better performance in tumor diagnosis in comparison with the mainstream diagnosis model,which improves the diagnosis efficiency and reduces the diagnosis error.
作者
杨萌宇
张雷
曾悦
YANG Mengyu;ZHANG Lei;ZENG Yue(Chongqing Jiaotong University,Chongqing 400074,China)
出处
《现代电子技术》
北大核心
2020年第15期110-114,118,共6页
Modern Electronics Technique
基金
国家自然科学基金项目(11401061)
国家自然科学基金项目(11501065)
重庆市教委项目(KJ1600504,KJ1600512)。
作者简介
杨萌宇(1998-),男,山东东营人,主要研究方向为模式识别、机器学习;张雷(1980-),男,重庆人,主要研究方向为系统工程、优化算法、机器学习。
