网格搜索的支持向量机方法在乳腺癌诊断中的应用
Application of Grid Search-Optimized Support Vector Machine in Breast Cancer Diagnosis

支持向量机(SVM)作为一种高效的分类模型，其性能在很大程度上取决于超参数的选择。本文利用支持向量机分类原理对乳腺癌诊断问题进行建模分析，采用网格搜索方法和五折交叉验证的方法对SVM的超参数进行优化选择，评估优化后模型的性能。实验结果表明，得到模型的准确率为98.24%、召回率为96.83%、F1分数为0.976、ROC AUC为0.9965。表明采用最优超参数组合的SVM模型在乳腺癌数据集上取得了很好的效果。
As an efficient classification model, the performance of Support Vector Machine (SVM) largely depends on the selection of hyperparameters. This study employs SVM classification principles for modeling and analyzing breast cancer diagnosis problems, utilizing grid search method and five-fold cross-validation to optimize the selection of SVM hyperparameters and evaluate the performance of the optimized model. Experimental results demonstrate that the model achieved an accuracy of 98.24%, recall of 96.83%, F1-score of 0.976, and ROC AUC of 0.9965. The findings indicate that the SVM model with optimal hyperparameter combinations achieved excellent performance on the breast cancer dataset.