基于SVM-MLP的乳腺癌预测

乳腺癌一直是影响女性健康最重要的问题之一,已经成为全球女性发病率最高的恶性肿瘤。近年来,利用机器学习和深度学习方法来诊断癌症已经成为发展较快的一个分支。通过使用逻辑回归模型(LR)、高斯核函数支持向量机(SVM)、前馈神经网络(MLP)对同一数据集进行预测,得出其中SVM迭代时间最短,前馈神经网络预测准确率最高。为了减少前馈神经网络的迭代时间,提出了基于SVM优化的前馈神经网络分类乳腺癌模型,实验结果表明:基于SVM优化后的前馈神经网络模型与Logistic模型、传统SVM模型相比具有更高的分类准确率,且迭代时间相对减少。

Prediction of Breast Cancer Based on SVM-MLP

Breast cancer has always been one of the most important issues in women's health,and has become the most common malignant tumor in the world.In recent years,using machine learning and deep learning methods to diagnose cancer has become a rapidly developing branch.In this paper,logistic regression model(LR),Gaussian kernel support vector machine(SVM)and feedforward neural network(MLP)are used to predict the same data set.The results show that the SVM iteration time is the shortest and the feedforward neural network has the highest prediction accuracy.In order to reduce the iteration time of the feedforward neural network,a feedforward neural network model based on SVM optimization is proposed to classify breast cancer.The experimental results show that the feedforward neural network based on SVM optimization hashigher accuracy and reduces iteration time comparing with logistic model and traditional SVM model.