摘要
支持向量机是在统计学习理论基础上发展而来的一种新的通用学习方法,较好地解决了有限样本的学习分类问题。在早期癌症诊断中,由于存在癌细胞缺乏、病人个体的特异性和数据本身的噪声等因素的影响,要进行非常准确的诊断是困难的。用支持向量机的分类算法,选取不同的核函数,构造了支持向量机的不同分类器,并将其应用于早期癌症诊断。非线性的支持向量机取得了较高的准确率,表明支持向量机在早期癌症的诊断中有很大的应用潜力。
Support Vector Machine (SVM) is an efficient novel method originated from the statistical learning theory. It is powerful in machine learning to solve problems with finite samples. Due to the deficiency of cancer cells, character of patient and noise in the raw data, it is very difficult to diagnose early cancer accurately. In this paper, SVM is employed in detecting early cancer and the results are encouraged compared with conventional methods. The accuracy of Non-linear SVM classifier is especially high in all kinds of classifiers, which indicates the potential application of SVM in early cancer detection.
出处
《生物医学工程学杂志》
EI
CAS
CSCD
北大核心
2005年第5期1045-1048,共4页
Journal of Biomedical Engineering