为进一步提升网络入侵检测效果,提出一种融合FAST特征选择与自适应二进制量子引力搜索支持向量机的(FAST-ABQGSA-SVM)网络入侵检测算法。利用FAST算法过滤掉原始特征集中冗余无关的特征形成候选特征子集,基于组合优化策略采用自适应二...为进一步提升网络入侵检测效果,提出一种融合FAST特征选择与自适应二进制量子引力搜索支持向量机的(FAST-ABQGSA-SVM)网络入侵检测算法。利用FAST算法过滤掉原始特征集中冗余无关的特征形成候选特征子集,基于组合优化策略采用自适应二进制量子引力搜索算法对候选特征子集与SVM分类器参数进行组合优化。在ABQGSA反复学习寻优过程中,采取动态自适应波动式调整策略更新量子旋转角以平衡算法全局搜索能力和局部搜索能力;同时为提升算法的自适应变异能力,设计与进化程度及个体适应度值相关的自适应变异概率,当种群进化出现停滞时及时引入量子位离散交叉操作帮助种群摆脱局部极值。通过KDD CUP 99仿真实验表明,所提出的FAST-ABQGSA-SVM算法较其他同类型检测算法具有更好的鲁棒性、学习精度以及检测效果。展开更多
针对当前移动终端使用中存在的安全隐患,研究了一种新的面向Android移动终端的入侵检测算法。首先是在Android平台上收集移动终端内核信息并进行预处理,通过引入快速核密度估计(fast kernel density estimation,Fast KDE)算法对收集到...针对当前移动终端使用中存在的安全隐患,研究了一种新的面向Android移动终端的入侵检测算法。首先是在Android平台上收集移动终端内核信息并进行预处理,通过引入快速核密度估计(fast kernel density estimation,Fast KDE)算法对收集到的大规模样本进行压缩,得到数量合理的训练样本,然后结合在线增量学习算法,利用支持向量机(SVM)算法对处理后的数据进行判别以识别出入侵。实验结果表明,该方法极大缩短了训练时间,检测性能逐步达到最佳,具有较好的可扩展性和自提升能力。展开更多
Recognizing various traffic signs,especially the popular circular traffic signs,is an essential task for implementing advanced driver assistance system.To recognize circular traffic signs with high accuracy and robust...Recognizing various traffic signs,especially the popular circular traffic signs,is an essential task for implementing advanced driver assistance system.To recognize circular traffic signs with high accuracy and robustness,a novel approach which uses the so-called improved constrained binary fast radial symmetry（ICBFRS） detector and pseudo-zernike moments based support vector machine（PZM-SVM） classifier is proposed.In the detection stage,the scene image containing the traffic signs will be converted into Lab color space for color segmentation.Then the ICBFRS detector can efficiently capture the position and scale of sign candidates within the scene by detecting the centers of circles.In the classification stage,once the candidates are cropped out of the image,pseudo-zernike moments are adopted to represent the features of extracted pictogram,which are then fed into a support vector machine to classify different traffic signs.Experimental results under different lighting conditions indicate that the proposed method has robust detection effect and high classification accuracy.展开更多
文摘为进一步提升网络入侵检测效果,提出一种融合FAST特征选择与自适应二进制量子引力搜索支持向量机的(FAST-ABQGSA-SVM)网络入侵检测算法。利用FAST算法过滤掉原始特征集中冗余无关的特征形成候选特征子集,基于组合优化策略采用自适应二进制量子引力搜索算法对候选特征子集与SVM分类器参数进行组合优化。在ABQGSA反复学习寻优过程中,采取动态自适应波动式调整策略更新量子旋转角以平衡算法全局搜索能力和局部搜索能力;同时为提升算法的自适应变异能力,设计与进化程度及个体适应度值相关的自适应变异概率,当种群进化出现停滞时及时引入量子位离散交叉操作帮助种群摆脱局部极值。通过KDD CUP 99仿真实验表明,所提出的FAST-ABQGSA-SVM算法较其他同类型检测算法具有更好的鲁棒性、学习精度以及检测效果。
文摘针对当前移动终端使用中存在的安全隐患,研究了一种新的面向Android移动终端的入侵检测算法。首先是在Android平台上收集移动终端内核信息并进行预处理,通过引入快速核密度估计(fast kernel density estimation,Fast KDE)算法对收集到的大规模样本进行压缩,得到数量合理的训练样本,然后结合在线增量学习算法,利用支持向量机(SVM)算法对处理后的数据进行判别以识别出入侵。实验结果表明,该方法极大缩短了训练时间,检测性能逐步达到最佳,具有较好的可扩展性和自提升能力。
基金Supported by the Program for Changjiang Scholars and Innovative Research Team (2008)Program for New Centoury Excellent Talents in University(NCET-09-0045)+1 种基金the National Nat-ural Science Foundation of China (60773044,61004059)the Natural Science Foundation of Beijing(4101001)
文摘Recognizing various traffic signs,especially the popular circular traffic signs,is an essential task for implementing advanced driver assistance system.To recognize circular traffic signs with high accuracy and robustness,a novel approach which uses the so-called improved constrained binary fast radial symmetry（ICBFRS） detector and pseudo-zernike moments based support vector machine（PZM-SVM） classifier is proposed.In the detection stage,the scene image containing the traffic signs will be converted into Lab color space for color segmentation.Then the ICBFRS detector can efficiently capture the position and scale of sign candidates within the scene by detecting the centers of circles.In the classification stage,once the candidates are cropped out of the image,pseudo-zernike moments are adopted to represent the features of extracted pictogram,which are then fed into a support vector machine to classify different traffic signs.Experimental results under different lighting conditions indicate that the proposed method has robust detection effect and high classification accuracy.
