As an important application research topic of the intelligent aviation multi-station, collaborative detecting must overcome the problem of scouting measurement with status of 'fragmentation', and the NP-hardne...As an important application research topic of the intelligent aviation multi-station, collaborative detecting must overcome the problem of scouting measurement with status of 'fragmentation', and the NP-hardness problem of matching association between target and measurement in the process of scouting to data-link, which has complicated technical architecture of network construction. In this paper, taking advantage of cooperation mechanism on signal level in the aviation multi-station sympathetic network, a method of obtaining target time difference of arrival (TDOA) measurement using multi-station collaborative detecting based on time-frequency association is proposed. The method can not only achieve matching between target and its measurement, but also obtain TDOA measurement by further evolutionary transaction through refreshing sequential pulse time of arrival (TOA) measurement matrix for matching and correlating. Simulation results show that the accuracy of TDOA measurement has significant superiority over TOA, and detection probability of false TDOA measurement introduced by noise and fake measurement can be reduced effectively.展开更多
Three-dimensional (3-D) matched filtering has been suggested as a powerful processing technique for detecting weak, moving IR point target immersed in a noisy field. Based on the theory of the 3-D matched filtering an...Three-dimensional (3-D) matched filtering has been suggested as a powerful processing technique for detecting weak, moving IR point target immersed in a noisy field. Based on the theory of the 3-D matched filtering and the optimal linear processing, the optimal point target detector is being analyzed in this paper. The performance of the detector is introduced in detail. The results provide a standard reference to evaluate the performance of any other point target detection algorithms.展开更多
To mitigate the deleterious effects of clutter and jammer, modern radars have adopted adaptive processing techniques such as constant false alarm rate(CFAR) detectors which are widely used to prevent clutter and noise...To mitigate the deleterious effects of clutter and jammer, modern radars have adopted adaptive processing techniques such as constant false alarm rate(CFAR) detectors which are widely used to prevent clutter and noise interference from saturating the radar’s display and preventing targets from being obscured.This paper concerns with the detection analysis of the novel version of CFAR schemes(cell-averaging generalized trimmed-mean,CATM) in the presence of additional outlying targets other than the target under research. The spurious targets as well as the tested one are assumed to be fluctuating in accordance with the χ~2-model with two-degrees of freedom. In this situation, the processor performance is enclosed by the swerling models(SWI and SWII). Between these bounds, there is an important class of target fluctuation which is known as moderately fluctuating targets. The detection of this class has many practical applications. Structure of the CATM detector is described briefly. Detection performances for optimal, CAM, CA, trimmed-mean(TM) and ordered-statistic(OS) CFAR strategies have been analyzed and compared for desired probability of false alarm and determined size of the reference window. False alarm rate performance of these processors has been evaluated for different strengths of interfering signal and the effect of correlation among the target returns on the detection and false alarm performances has also been studied. Our numerical results show that, with a proper choice of trimming parameters,the novel model CAM presents an ideal detection performance outweighing that of the Neyman-Pearson detector on condition that the tested target obeys the SWII model in its fluctuation. Although the new models CAS and CAM can be treated as special cases of the CATM algorithm, their multi-target performance is modest even it has an enhancement relative to that of the classical CAcheme. Additionally, they fail to maintain the false alarm rate constant when the operating environment is of type target multiplicity. Moreover, the non-coherent integration of M pulses ameliorates the processor performance either it operates in homogeneous or multi-target environment.展开更多
面向分布式小型化磁感前端阵列接收长波信号场景,针对长波频段噪声复杂的特性,提出了一种宽带多信号智能联合检测方法。该方法基于已知参考信号样本预训练神经网络,通过神经网络在预训练阶段学习分布式接收样本矢量在各维度上的潜在复...面向分布式小型化磁感前端阵列接收长波信号场景,针对长波频段噪声复杂的特性,提出了一种宽带多信号智能联合检测方法。该方法基于已知参考信号样本预训练神经网络,通过神经网络在预训练阶段学习分布式接收样本矢量在各维度上的潜在复杂关联性规律,进而部署网络后可输出基于输入样本矢量联合概率的置信度量,用于判断当前样本是否存在目标信号从而得到检测结果。基于宽带信号仿真数据集进行实验,结果表明算法可直接对宽带数据进行处理,并能有效完成频谱感知,能够在低信噪比和相关噪声条件下获得接近理论处理增益的检测性能,达到80%以上的检测率。在此基础上,采用中科院空天信息创新研究院布设于内蒙古的超短基线电磁探测阵列(Mini-array by Chinese Academy of Sciences,CASMA)采集的实际长波信号数据进行性能验证,算法性能测试结果同样验证了其有效性。该方法不限于长波信号,也适用于其他具备参考信号条件下的信号盲检测的场景,实现在信道参数未知、信号微弱等盲环境条件下获得更优的目标信号检测性能。展开更多
漏洞检测是软件系统安全领域的关键技术.近年来,深度学习凭借其代码特征提取的卓越能力,在漏洞检测领域取得了显著进展.然而,当前基于深度学习的方法仅关注于代码实例自身的独立结构特征,而忽视了不同漏洞代码间存在的结构特征相似关联...漏洞检测是软件系统安全领域的关键技术.近年来,深度学习凭借其代码特征提取的卓越能力,在漏洞检测领域取得了显著进展.然而,当前基于深度学习的方法仅关注于代码实例自身的独立结构特征,而忽视了不同漏洞代码间存在的结构特征相似关联,限制了漏洞检测技术的性能.针对这一问题,提出了一种基于函数间结构特征关联的软件漏洞检测方法(vulnerability detection method based on correlation of structural features between functions,CSFF-VD).该方法首先将函数解析为代码属性图,并通过门控图神经网络提取函数内的独立结构特征.在此基础之上,利用特征之间的相似性构建函数间的关联网络并构建基于图注意力网络进一步提取函数间关联信息,以此提升漏洞检测的性能.实验结果显示,CSFF-VD在3个公开的漏洞检测数据集上超过了当前基于深度学习的漏洞检测方法.此外,在函数内各独立特征提取的基础上,通过增加CSFF-VD中函数间关联特征提取方法的实验,证明了集成函数间关联信息的有效性.展开更多
基金supported by the National Natural Science Foundation of China(61472443)the Basic Research Priorities Program of Shaanxi Province Natural Science Foundation of China(2013JQ8042)
文摘As an important application research topic of the intelligent aviation multi-station, collaborative detecting must overcome the problem of scouting measurement with status of 'fragmentation', and the NP-hardness problem of matching association between target and measurement in the process of scouting to data-link, which has complicated technical architecture of network construction. In this paper, taking advantage of cooperation mechanism on signal level in the aviation multi-station sympathetic network, a method of obtaining target time difference of arrival (TDOA) measurement using multi-station collaborative detecting based on time-frequency association is proposed. The method can not only achieve matching between target and its measurement, but also obtain TDOA measurement by further evolutionary transaction through refreshing sequential pulse time of arrival (TOA) measurement matrix for matching and correlating. Simulation results show that the accuracy of TDOA measurement has significant superiority over TOA, and detection probability of false TDOA measurement introduced by noise and fake measurement can be reduced effectively.
文摘Three-dimensional (3-D) matched filtering has been suggested as a powerful processing technique for detecting weak, moving IR point target immersed in a noisy field. Based on the theory of the 3-D matched filtering and the optimal linear processing, the optimal point target detector is being analyzed in this paper. The performance of the detector is introduced in detail. The results provide a standard reference to evaluate the performance of any other point target detection algorithms.
文摘To mitigate the deleterious effects of clutter and jammer, modern radars have adopted adaptive processing techniques such as constant false alarm rate(CFAR) detectors which are widely used to prevent clutter and noise interference from saturating the radar’s display and preventing targets from being obscured.This paper concerns with the detection analysis of the novel version of CFAR schemes(cell-averaging generalized trimmed-mean,CATM) in the presence of additional outlying targets other than the target under research. The spurious targets as well as the tested one are assumed to be fluctuating in accordance with the χ~2-model with two-degrees of freedom. In this situation, the processor performance is enclosed by the swerling models(SWI and SWII). Between these bounds, there is an important class of target fluctuation which is known as moderately fluctuating targets. The detection of this class has many practical applications. Structure of the CATM detector is described briefly. Detection performances for optimal, CAM, CA, trimmed-mean(TM) and ordered-statistic(OS) CFAR strategies have been analyzed and compared for desired probability of false alarm and determined size of the reference window. False alarm rate performance of these processors has been evaluated for different strengths of interfering signal and the effect of correlation among the target returns on the detection and false alarm performances has also been studied. Our numerical results show that, with a proper choice of trimming parameters,the novel model CAM presents an ideal detection performance outweighing that of the Neyman-Pearson detector on condition that the tested target obeys the SWII model in its fluctuation. Although the new models CAS and CAM can be treated as special cases of the CATM algorithm, their multi-target performance is modest even it has an enhancement relative to that of the classical CAcheme. Additionally, they fail to maintain the false alarm rate constant when the operating environment is of type target multiplicity. Moreover, the non-coherent integration of M pulses ameliorates the processor performance either it operates in homogeneous or multi-target environment.
文摘面向分布式小型化磁感前端阵列接收长波信号场景,针对长波频段噪声复杂的特性,提出了一种宽带多信号智能联合检测方法。该方法基于已知参考信号样本预训练神经网络,通过神经网络在预训练阶段学习分布式接收样本矢量在各维度上的潜在复杂关联性规律,进而部署网络后可输出基于输入样本矢量联合概率的置信度量,用于判断当前样本是否存在目标信号从而得到检测结果。基于宽带信号仿真数据集进行实验,结果表明算法可直接对宽带数据进行处理,并能有效完成频谱感知,能够在低信噪比和相关噪声条件下获得接近理论处理增益的检测性能,达到80%以上的检测率。在此基础上,采用中科院空天信息创新研究院布设于内蒙古的超短基线电磁探测阵列(Mini-array by Chinese Academy of Sciences,CASMA)采集的实际长波信号数据进行性能验证,算法性能测试结果同样验证了其有效性。该方法不限于长波信号,也适用于其他具备参考信号条件下的信号盲检测的场景,实现在信道参数未知、信号微弱等盲环境条件下获得更优的目标信号检测性能。
文摘传感器作为复杂装备监测系统的关键组成部分,若发生故障会引起误报警,极大影响复杂机械系统状态监测的可靠性。针对该难题,笔者从系统角度出发,提出一种基于去趋势互相关分析(detrended cross-correlation analysis,简称DCCA)和双尺度自编码器(dual auto encoder,简称DAE)的传感器故障检测方法,记作DCCA-DAE。首先,采用DCCA方法建立耦合网络,将数据从欧氏空间扩展到拓扑空间,实现对系统多源多态监测数据蕴含信息的全面表征;其次,构建基于DAE的异常检测方法,消除工况变化对传感器监测序列产生的影响,实现工况复杂变化下的系统传感器故障准确检测;最后,利用某电厂汽轮机组历史数据,验证所提方法的综合性能。结果表明,DCCA-DAE模型特征提取能力强,检测精度显著优于传统支持向量描述和自编码器等方法,在工业场景中传感器故障检测领域具有良好的应用前景。
文摘漏洞检测是软件系统安全领域的关键技术.近年来,深度学习凭借其代码特征提取的卓越能力,在漏洞检测领域取得了显著进展.然而,当前基于深度学习的方法仅关注于代码实例自身的独立结构特征,而忽视了不同漏洞代码间存在的结构特征相似关联,限制了漏洞检测技术的性能.针对这一问题,提出了一种基于函数间结构特征关联的软件漏洞检测方法(vulnerability detection method based on correlation of structural features between functions,CSFF-VD).该方法首先将函数解析为代码属性图,并通过门控图神经网络提取函数内的独立结构特征.在此基础之上,利用特征之间的相似性构建函数间的关联网络并构建基于图注意力网络进一步提取函数间关联信息,以此提升漏洞检测的性能.实验结果显示,CSFF-VD在3个公开的漏洞检测数据集上超过了当前基于深度学习的漏洞检测方法.此外,在函数内各独立特征提取的基础上,通过增加CSFF-VD中函数间关联特征提取方法的实验,证明了集成函数间关联信息的有效性.
