A covert channel is an information channel that is used by the computer process to exfiltrate data through bypassing security policies.The DNS protocol is one of the important ways to implement a covert channel.DNS co...A covert channel is an information channel that is used by the computer process to exfiltrate data through bypassing security policies.The DNS protocol is one of the important ways to implement a covert channel.DNS covert channels are easily used by attackers for malicious purposes.Therefore,an effective detection approach of the DNS covert channels is significant for computer systems and network securities.Aiming at the difficulty of the DNS covert channel identification,we propose a DNS covert channel detection method based on a stacking model.The stacking model is evaluated on a campus network and the experimental results show that the detection based on the stacking model can detect the DNS covert channels effectively.Besides,it can identify unknown covert channel traffic.The area under the curve(AUC)of the proposed method reaches 0.9901,which outperforms existing detection methods.展开更多
为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合...为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合。通过5折交叉验证,根据各基模型在验证集上的AUC(area under curve)值对预测结果进行加权平均,使得表现较好的基模型在最终预测中贡献更大,从而提升模型的整体预测性能。在中老年结构化数据上的实验结果表明,ABS-Stacking模型在泛化能力和抑郁症预测效果上均优于单一模型和传统集成方法。该方法不仅有效解决了基分类器组合选择和性能加权的问题,还显著提高了模型的自适应性和泛化能力,为抑郁症预测提供了新的方法参考。展开更多
文摘董志塬地区位于黄土高原中心地带,滑坡灾害频发,亟需明确滑坡易发性分区,以支持该区域滑坡隐患的科学防控。因此,本文以董志塬为研究区,选取高程、坡向和NDVI等12个影响因素作为评价因子,基于频率比(frequency ratio,FR)模型,结合随机森林(random forest,RF)与人工神经网络(artificial neural network,ANN)模型开展滑坡静态易发性评价,并分析各因子对评价精度的贡献。结果表明,FRRF和FR-ANN模型的曲线下面积(area under the curve,AUC)值分别为0.922和0.918,表明FR-RF模型在董志塬滑坡易发性评价中的精度更高。坡度、坡向和道路密度对滑坡易发性的贡献率分别为16.7%、15.3%和1.4%。为克服地形复杂和数据更新滞后的问题,本文将FR-RF模型的易发性结果与InSAR Stacking结果相结合,将静态滑坡易发性评价精度由6.9%提升到8.1%。动态易发性结果表明,董志塬滑坡高易发区主要分布于河流沿岸,占总面积的6.5%,该区域的滑坡数量占总滑坡数的23.6%,滑坡密度15.7个/km^(2)。低易发区主要位于远离河流的中部区域,占总面积的81.7%,滑坡数量占总滑坡数的57.8%,滑坡密度4.7个/km^(2)。本研究通过融合InSAR Stacking方法,解决了静态滑坡易发性评价数据更新滞后问题,减少了假阴性错误,为传统滑坡易发性评价赋予了时效性,可以实现董志塬滑坡易发性动态评价,为灾害防治提供了重要数据支持。
基金National Key Research and Development Project(2016QY04W0901)and(2016QY04W0903).
文摘A covert channel is an information channel that is used by the computer process to exfiltrate data through bypassing security policies.The DNS protocol is one of the important ways to implement a covert channel.DNS covert channels are easily used by attackers for malicious purposes.Therefore,an effective detection approach of the DNS covert channels is significant for computer systems and network securities.Aiming at the difficulty of the DNS covert channel identification,we propose a DNS covert channel detection method based on a stacking model.The stacking model is evaluated on a campus network and the experimental results show that the detection based on the stacking model can detect the DNS covert channels effectively.Besides,it can identify unknown covert channel traffic.The area under the curve(AUC)of the proposed method reaches 0.9901,which outperforms existing detection methods.
文摘为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合。通过5折交叉验证,根据各基模型在验证集上的AUC(area under curve)值对预测结果进行加权平均,使得表现较好的基模型在最终预测中贡献更大,从而提升模型的整体预测性能。在中老年结构化数据上的实验结果表明,ABS-Stacking模型在泛化能力和抑郁症预测效果上均优于单一模型和传统集成方法。该方法不仅有效解决了基分类器组合选择和性能加权的问题,还显著提高了模型的自适应性和泛化能力,为抑郁症预测提供了新的方法参考。
