合肥工业大学学报（自然科学版）
閤肥工業大學學報（自然科學版）
합비공업대학학보（자연과학판）
JOURNAL OF HEFEI UNIVERSITY OF TECHNOLOGY(NATURAL SCIENCE)
2015年
7期
929-933
,共5页
钱燕燕%李永忠%章雷%余西亚
錢燕燕%李永忠%章雷%餘西亞
전연연%리영충%장뢰%여서아
多标记学习%ML-KNN算法%半监督学习%入侵检测%KDD CUP99数据集
多標記學習%ML-KNN算法%半鑑督學習%入侵檢測%KDD CUP99數據集
다표기학습%ML-KNN산법%반감독학습%입침검측%KDD CUP99수거집
multi-label learning%multi-label k-nearest neighbor(ML-KNN) algorithm%semi-supervised learning%intrusion detection%KDD CUP99 dataset
针对现有入侵检测技术的不足，文章研究了基于机器学习的异常入侵检测系统，将多标记和半监督学习应用于入侵检测，提出了一种基于多标记学习的入侵检测算法。该算法采用“k近邻”分类准则，统计近邻样本的类别标记信息，通过最大化后验概率（maximum a posteriori ，MAP）的方式推理未标记数据的所属集合。在KDD CUP99数据集上的仿真结果表明，该算法能有效地改善入侵检测系统的性能。
針對現有入侵檢測技術的不足，文章研究瞭基于機器學習的異常入侵檢測繫統，將多標記和半鑑督學習應用于入侵檢測，提齣瞭一種基于多標記學習的入侵檢測算法。該算法採用“k近鄰”分類準則，統計近鄰樣本的類彆標記信息，通過最大化後驗概率（maximum a posteriori ，MAP）的方式推理未標記數據的所屬集閤。在KDD CUP99數據集上的倣真結果錶明，該算法能有效地改善入侵檢測繫統的性能。
침대현유입침검측기술적불족，문장연구료기우궤기학습적이상입침검측계통，장다표기화반감독학습응용우입침검측，제출료일충기우다표기학습적입침검측산법。해산법채용“k근린”분류준칙，통계근린양본적유별표기신식，통과최대화후험개솔（maximum a posteriori ，MAP）적방식추리미표기수거적소속집합。재KDD CUP99수거집상적방진결과표명，해산법능유효지개선입침검측계통적성능。
Aiming at some problems in current techniques of intrusion detection ,the anomaly intrusion detection system based on machine learning is studied ,and an intrusion detection algorithm based on multi-label k-nearest neighbor with multi-label and semi-supervised learning is put forward .For each unlabeled datum ,its k-nearest neighbors in the training set are firstly identified .After that ,based on the statistical information gained from the label sets of these neighboring data ,namely the number of neighboring data belonging to each possible class ,maximum a posteriori(MAP) principle is utilized to determine the label set for the unlabeled data .KDD CUP99 dataset is implemented to evaluate the proposed algorithm .Compared to other algorithms ,the simulation results show that the performance of intrusion detection system is improved by the proposed algorithm .
