信息工程大学学报2025，Vol.26Issue(1)：14-20,7.DOI:10.3969/j.issn.1671-0673.2025.01.003
采用原型学习的类概念漂移网络数据检测与分类算法
Class Concept Drift Network Data Detection and Classification Algorithm Based on Prototype Learning
陈坤 1李青 1褚瑞娟 1樊讯池 1王润泽1
作者信息
摘要
Abstract
Affected by network equipment update and communication protocol upgrade,the distribu-tion,category and attribute of network data have unpredictable drift characteristics,subsequently im-pairing the classification precision of machine learning-based network data classification models.To solve this problem,a class concept drift network data detection and classification algorithm based on prototype learning is proposed.The network data is addressed from the time series perspective,har-nessing a network equipped with an attention mechanism to distill spatiotemporal features from the data.Drawing on the principles of prototype learning,the distances between samples and prototypes are utilized for classification purposes.In instances of class concept drift,a suitable threshold is estab-lished to identify novel classes,and the mean values are employed to refresh the prototype matrix.Ex-periment result shows that the utilization of prototype matching for classification not only yields higher accuracy than traditional softmax classifiers,but also can effectively detect the drift when the data has class concept drift,and has better classification performance on the drift data.关键词
原型学习/概念漂移/新类检测/网络数据Key words
prototype learning/concept drift/novel class detection/network data分类
信息技术与安全科学引用本文复制引用
陈坤,李青,褚瑞娟,樊讯池,王润泽..采用原型学习的类概念漂移网络数据检测与分类算法[J].信息工程大学学报,2025,26(1):14-20,7.
