摘要
支持向量机SVM是一种基于统计学习理论的机器学习算法,它能在训练样本很少的情况下达到良好的分类效果。TWSVMs是一种通过解决SVM相关问题确定两个非平行平面的新的二元SVM分类器,与传统的SVMs方法相比,Twin SVMs不仅达到了更快的检测速度及更优的检测效果,而且大大降低了算法的时间复杂度。在入侵检测的实际应用中,Twin SVMs能够在小样本条件下保持较高的识别正确率。
SVM is a machine learning method based on statistics. Twin SVM is a binary SVM classifier that determines two nonparallel planes by solving two related SVM - type problems. Compare to the traditional SVM algorithm, it has faster speed, better effect and reduces the complexity of time. During the application of intrusion detection, Twin SVM maintains fine detection status in the condition of small -scale training dataset.
出处
《湖北第二师范学院学报》
2009年第2期61-63,共3页
Journal of Hubei University of Education
基金
湖北第二师范学院院管课题