通过基于Choquet积分的特征聚合改进网络异常检测
Improving Network Anomaly Detection via Choquet-Integral-Based Feature Aggregation
浏览论文内容
中文总结 AI 辅助
研究通过基于Choquet积分的特征聚合框架改进网络异常检测，结合自适应加权与增量特征选择解决特征冗余，用随机森林和XGBoost分类器评估，该聚合提高准确率且减少数据量，在特定场景有显著收益。
中文摘要 AI 辅助
本文研究了一种基于广义Choquet积分的特征聚合框架，以改进高维网络流量数据中的异常检测。该方法将自适应加权与增量特征选择相结合来解决特征冗余问题。使用随机森林和XGBoost分类器，在不同特征子集大小下评估了用原始特征和Choquet聚合特征训练的模型。所提出的聚合方法在不降低精度和召回率的情况下，准确率提高了7%，同时数据量减少了77.5%（从214MB降至48MB）。多分层重复平均结果表明，基于Choquet的聚合在特征可用性有限的情况下产生了统计学上显著的收益（p<0.05），突出了其在带宽和特征可用性约束下适用于实时入侵检测。
英文摘要
This work investigates a generalized Choquet-integral-based feature aggregation framework to improve anomaly detection in high-dimensional network traffic data. The approach combines adaptive weighting with incremental feature selection to address feature redundancy. Using Random Forest and XGBoost classifiers, we evaluate models trained with both raw and Choquet-aggregated features under varying feature subset sizes. The proposed aggregation achieves up to $7\%$ higher accuracy while reducing data volume by $77.5\%$ (from $214$~MB to $48$~MB), without degrading precision and recall. Results averaged over multiple stratified repetitions indicate that Choquet-based aggregation yields statistically significant gains ($p < 0.05$) in scenarios with limited feature availability, highlighting its suitability for real-time intrusion detection under bandwidth and feature-availability constraints.
发表机构
- Federal University of Rio Grande - FURG, Brazil（巴西里约格朗德联邦大学）
- Federal University of Rio Grande do Norte - UFRN, Brazil（巴西里约格朗德北联邦大学）
机构由 AI 辅助整理，请以论文原文为准。
