摘要
由一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-关于人工智能的最新研究结果已经发表。根据NewsRx编辑在巴基斯坦伊斯兰堡的新闻报道，研究表明：“入侵检测系统(IDSs)在保护网络基础设施免受网络威胁和确保高度敏感数据的完整性方面发挥着至关重要的作用。传统的IDS技术虽然成功地实现了高精度，但经常存在严重的模型偏差。”这项研究的资助者包括努拉·宾特·阿卜杜勒拉赫曼公主大学。新闻记者从伊克拉大学的研究中得到一句话:“他的偏见主要是由数据的不平衡和某些特征缺乏相关性引起的。本研究旨在通过提出一种基于先进机器学习(ML)的入侵检测系统来解决这些挑战,该系统可以最大限度地减少错误分类错误,并纠正模型偏差。因此,该系统采用递归特征消去(RFE)、特征选择(SFS)、统计特征选择等先进的特征选择技术,细化输入特征集,最大限度地减少非预测属性的影响,并结合了合成少数过抽样技术和编辑最近邻(SMOTE_ENN)等数据重采样方法,提高了入侵检测系统的预测精度和泛化能力。实验结果表明,本文提出的模型,特别是在使用随机森林(RF)算法的情况下,在不同的数据重采样方法下,在精度、精度、召回率和F分方面均优于现有模型.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news reporting out of Islamabad, Pa kistan, by NewsRx editors, research stated, "Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats a nd ensuring the integrity of highly sensitive data. Conventional IDS technologie s, although successful in achieving high levels of accuracy, frequently encounte r substantial model bias." Funders for this research include Princess Nourah Bint Abdulrahman University. The news journalists obtained a quote from the research from Iqra University: "T his bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification error s and corrects model bias. As a result, the predictive accuracy and generalizabi lity of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequ ential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addi tion, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Ada ptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique -Tomek Links (SMOTE_Tomek) to address class imbalance and improve t he accuracy of the model. The experimental results indicate that our proposed mo del, especially when utilizing the random forest (RF) algorithm, surpasses exist ing models regarding accuracy, precision, recall, and F Score across different d ata resampling methods."
NETL
NSTL