摘要
为提高疾病诊断的效率,本文提出一种改进的灰狼优化算法与核极限学习机的混合模型。通过引入一种新的机制提高灰狼优化算法的探索与利用能力,改进的灰狼优化算法在进行特征选择的同时,也对核极限学习机的2个关键参数进行优化,模型在2个疾病数据集上进行实验验证。实验结果显示:提出的模型在准确率、敏感性、特异性等评价指标方面相对于其他混合模型高出约1%~2%,带特征选择的优化模型相对于没有特征选择的模型在评价指标上也高出约1%~2%。结果表明提出的模型具有一定的优势。
In order to improve the efficiency of disease diagnosis,a hybrid model of improved grey wolf optimization(IGWO)algorithm and kernel extreme learning machine(KELM)is proposed in this paper.By introducing a new mechanism to improve the exploration and exploitation abilities of grey wolf optimization algorithm.In addition to feature selection,the improved Grey Wolf optimization algorithm also optimizes two key parameters of the kernel extreme learning machine.The model was tested on two disease data sets.The experimental results show that the proposed model is about 1%-2%higher than other hybrid models in terms of accuracy,sensitivity and specificity,and the optimized model with feature selection is about 1%-2%higher than the model without feature selection in terms of evaluation met-rics.The results show that the proposed model has certain advantages.
作者
魏瑞芳
Wei Ruifang(Zhejiang Post and Telecommunication College,Shaoxing 312366,Zhejiang,China)
出处
《科技通报》
2024年第3期47-52,共6页
Bulletin of Science and Technology
基金
2022年浙江省国内访问工程师项目(FG2022387)。
关键词
灰狼优化算法
核极限学习机
疾病诊断
特征选择
参数优化
grey wolf optimization algorithm
kernel extreme learning machine
disease diagnosis
feature selection
parameter optimization
