融合ILogistic映射和t分布的OOA-RF乳腺癌预测模型
Prediction Model of Breast Cancer Using OOA-RF Based on ILogistic Mapping and t-distribution
祖璇 1张广海2
作者信息
- 1. 芜湖学院经济系,安徽芜湖 241008
- 2. 芜湖学院大数据与人工智能系,安徽芜湖 241008
- 折叠
摘要
乳腺癌是女性发病率第一的癌症,也是女性癌症死亡的主要原因,而早期诊断有望增加患者治疗成功的机会.为增加医疗诊断成功率,建立了一种融合ILogistic 映射和 t 分布的OOA-RF乳腺癌预测模型.首先,针对鱼鹰优化算法初始种群分布不均匀问题,引入了改进Logistic 混沌映射方法;其次,为避免陷入局部最优,采用了自适应t分布策略位置扰动;之后训练随机森林回归参数,并在测试数据集上进行实验.结果显示,与OOA-RF、RF相比,本文方法的性能更好;拟合优度R2的值为1.000 0,说明其拟合效果更佳.
Abstract
Breast cancer is the most commonly diagnosed cancer in women and is also the leading cause of cancer death in women,while early diagnosis holds the promise increasing patients'chances of successful treat-ment..In order to increase the success rate of medical diagnosis,a prediction model of breast cancer based on OOA-RF was established,which integrated illogistic mapping and t-distribution.Firstly,an improved Logistic cha-otic mapping method was introduced to solve the problem of initial population unevenness;and secondly,an adap-tive T-distribution strategy was adopted to avoid local optimization;then random forest regression parameters were trained using IOOA-RF and experimented on the test data set.The results showed that compared with OOA-RF and RF,the proposed method showed the best performance;and R2 was 1.000 0,indicating that the method had the best fitting effect.
关键词
ILogistic映射/自适应t分布策略/鱼鹰优化算法/随机森林/乳腺癌预测Key words
ILogistic mapping/adaptive t-distribution strategy/osprey optimization algorithm/random for-est/breast cancer prediction引用本文复制引用
出版年
2025
NETL
NSTL
万方数据