Admission control with long-range dependence traffic input

The admission control scheme is investigated for a FIFO self-similar queuing system with Quality of Service (QoS) performance guarantees. Since the self-similar queuing system performance analysis is often carried out under the condition of infinite buffer, it is difficult to deduce the upper boundary of buffer overflow probability. To overcome this shortcoming, a simple overflow condition is proposed, which defines a buffer overflow occurrence whenever the arrival rate exceeds the service rate. The analytic formula for the buffer overflow probability upper boundary is easily obtained under this condition. The required bandwidth upper boundary with long-range dependence input and determined overflow probability is then derived from this formula. Based on the above analytic formulas, the upper boundaries of the admission control regions for homogeneous and heterogeneous long-range dependence traffic sources are separately obtained. Finally, an effective admission control scheme for long-range dependence input is proposed. Simulation studies with real traffic have confirmed the validity of these results.

Improved YOLOv7 Algorithm for Floating Waste Detection Based on GFPN and Long-Range Attention Mechanism

Floating wastes in rivers have specific characteristics such as small scale,low pixel density and complex backgrounds.These characteristics make it prone to false and missed detection during image analysis,thus resulting in a degradation of detection performance.In order to tackle these challenges,a floating waste detection algorithm based on YOLOv7 is proposed,which combines the improved GFPN(Generalized Feature Pyramid Network)and a long-range attention mechanism.Firstly,we import the improved GFPN to replace the Neck of YOLOv7,thus providing more effective information transmission that can scale into deeper networks.Secondly,the convolution-based and hardware-friendly long-range attention mechanism is introduced,allowing the algorithm to rapidly generate an attention map with a global receptive field.Finally,the algorithm adopts the WiseIoU optimization loss function to achieve adaptive gradient gain allocation and alleviate the negative impact of low-quality samples on the gradient.The simulation results reveal that the proposed algorithm has achieved a favorable average accuracy of 86.3%in real-time scene detection tasks.This marks a significant enhancement of approximately 6.3%compared with the baseline,indicating the algorithm's good performance in floating waste detection.

Trusted Anomaly Detection with Context Dependency

Anomaly detection of privileged processes is one of the most important means to safeguard the host and system security. The key problem for improving detection performance is to identify local behavior of the short sequences in traces of system calls accurately. An alternative modeling method was proposed based on the typical pattern matching of short sequences, which builds upon the concepts of short sequences with context dependency and the specially designed aggregation algorithm. The experimental results indicate that the modeling method considering the context dependency improves clearly the sensitive decision threshold as compared with the previous modeling method.

Long-Range Dependencies Learning Based on Nonlocal 1D-Convolutional Neural Network for Rolling Bearing Fault Diagnosis

In the field of data-driven bearing fault diagnosis,convolutional neural network(CNN)has been widely researched and applied due to its superior feature extraction and classification ability.However,the convolutional operation could only process a local neighborhood at a time and thus lack the ability of capturing long-range dependencies.Therefore,building an efficient learning method for long-range dependencies is crucial to comprehend and express signal features considering that the vibration signals obtained in a real industrial environment always have strong instability,periodicity,and temporal correlation.This paper introduces nonlocal mean to the CNN and presents a 1D nonlocal block(1D-NLB)to extract long-range dependencies.The 1D-NLB computes the response at a position as a weighted average value of the features at all positions.Based on it,we propose a nonlocal 1D convolutional neural network(NL-1DCNN)aiming at rolling bearing fault diagnosis.Furthermore,the 1D-NLB could be simply plugged into most existing deep learning architecture to improve their fault diagnosis ability.Under multiple noise conditions,the 1D-NLB improves the performance of the CNN on the wheelset bearing data set of high-speed train and the Case Western Reserve University bearing data set.The experiment results show that the NL-1DCNN exhibits superior results compared with six state-of-the-art fault diagnosis methods.

Labeling Algorithm for Face Detection Using Skin and Hair Characteristics

This research presents an algorithm for face detection based on color images using three main components： skin color characteristics, hair color characteristics, and a decision structure which converts the obtained information from skin and hair regions to labels for identifying the object dependencies and rejecting many of the incorrect decisions. Here we use face color characteristics that have a good resistance against the face rotations and expressions. This algorithm is also capable of being combined with other methods of face recognition in each stage to improve the detection.

ADS-B Anomaly Data Detection Model Based on Deep Learning and Difference of Gaussian Approach

Due to the influence of terrain structure,meteorological conditions and various factors,there are anomalous data in automatic dependent surveillance-broadcast(ADS-B)message.The ADS-B equipment can be used for positioning of general aviation aircraft.Aim to acquire the accurate position information of aircraft and detect anomaly data,the ADS-B anomaly data detection model based on deep learning and difference of Gaussian(DoG)approach is proposed.First,according to the characteristic of ADS-B data,the ADS-B position data are transformed into the coordinate system.And the origin of the coordinate system is set up as the take-off point.Then,based on the kinematic principle,the ADS-B anomaly data can be removed.Moreover,the details of the ADS-B position data can be got by the DoG approach.Finally,the long short-term memory(LSTM)neural network is used to optimize the recurrent neural network(RNN)with severe gradient reduction for processing ADS-B data.The position data of ADS-B are reconstructed by the sequence to sequence(seq2seq)model which is composed of LSTM neural network,and the reconstruction error is used to detect the anomalous data.Based on the real flight data of general aviation aircraft,the simulation results show that the anomaly data can be detected effectively by the proposed method of reconstructing ADS-B data with the seq2seq model,and its running time is reduced.Compared with the RNN,the accuracy of anomaly detection is increased by 2.7%.The performance of the proposed model is better than that of the traditional anomaly detection models.

Capturing semantic features to improve Chinese event detection

Current Chinese event detection methods commonly use word embedding to capture semantic representation,but these methods find it difficult to capture the dependence relationship between the trigger words and other words in the same sentence.Based on the simple evaluation,it is known that a dependency parser can effectively capture dependency relationships and improve the accuracy of event categorisation.This study proposes a novel architecture that models a hybrid representation to summarise semantic and structural information from both characters and words.This model can capture rich semantic features for the event detection task by incorporating the semantic representation generated from the dependency parser.The authors evaluate different models on kbp 2017 corpus.The experimental results show that the proposed method can significantly improve performance in Chinese event detection.

TDLens:Toward an Empirical Evaluation of Provenance Graph-Based Approach to Cyber Threat Detection

To combat increasingly sophisticated cyber attacks,the security community has proposed and deployed a large body of threat detection approaches to discover malicious behaviors on host systems and attack payloads in network traffic.Several studies have begun to focus on threat detection methods based on provenance data of host-level event tracing.On the other side,with the significant development of big data and artificial intelligence technologies,large-scale graph computing has been widely used.To this end,kinds of research try to bridge the gap between threat detection based on host log provenance data and graph algorithm,and propose the threat detection algorithm based on system provenance graph.These approaches usually generate the system provenance graph via tagging and tracking of system events,and then leverage the characteristics of the graph to conduct threat detection and attack investigation.For the purpose of deeply understanding the correctness,effectiveness,and efficiency of different graph-based threat detection algorithms,we pay attention to mainstream threat detection methods based on provenance graphs.We select and implement 5 state-of-the-art threat detection approaches among a large number of studies as evaluation objects for further analysis.To this end,we collect about 40GB of host-level raw log data in a real-world IT environment,and simulate 6 types of cyber attack scenarios in an isolated environment for malicious provenance data to build our evaluation datasets.The crosswise comparison and longitudinal assessment interpret in detail these detection approaches can detect which attack scenarios well and why.Our empirical evaluation provides a solid foundation for the improvement direction of the threat detection approach.

基于Electra预训练模型并融合依存关系的中文事件检测模型

事件检测是信息提取领域的一个重要研究方向。现存的事件检测模型受到语言模型训练目标的限制,只能被动地获取词与词之间的依赖关系,使得模型在训练的过程中过多地关注与训练目标不相关的成分,从而导致检测结果错误。以往的研究表明,充分理解上下文信息对于基于深度学习的事件检测技术至关重要。因此,在Electra预训练模型的基础上,引入KVMN网络来捕捉单词之间的依赖关系,以增强单词的语义特征,并采用了一种门控机制来加权这些特征。然后,为了解决中文事件检测中模型识别错误决策的问题,在输入中加入负样本,对不同样本加入不同程度的噪声,使模型学习更好的嵌入表示,有效提高了模型对未知样本的泛化能力。最后,在公共数据集LEVEN上的实验结果表明,该方法优于现有方法,取得了93.43%的F1值。

面向多维时间序列异常检测的时空图卷积网络

针对现有多维时间序列异常检测模型对局部和全局时空依赖性捕获能力不足的问题,提出一种基于时空图卷积网络的多维时间序列异常检测模型。首先,在时间维度上利用扩张因果卷积和多头自注意力机制,分别捕获短期和长期时间依赖性,并且引入通道注意力来学习不同通道的重要性权重;其次,在空间维度上利用静态图学习层根据节点嵌入构建静态图邻接矩阵,旨在捕获多维时间序列数据的全局空间依赖性,同时利用动态图学习层构建一系列演化的图邻接矩阵,旨在建模局部动态的空间依赖性;最后,联合优化重构模型和预测模型,通过重构误差和预测误差计算异常分数,然后比较阈值和异常分数的关系,进而检测异常。在MSL、SMAP和SWaT三个公开数据集上的实验结果表明,该模型在异常检测性能指标F1分数方面优于OmniAnomaly、MTAD-GAT和GDN等相关的基线模型。

SaGE:基于句法感知图卷积神经网络和ELECTRA的中文隐喻识别模型

隐喻是人类语言中经常出现的一种特殊现象,隐喻识别对于自然语言处理各项任务来说具有十分基础和重要的意义。针对中文领域的隐喻识别任务,该文提出了一种基于句法感知图卷积神经网络和ELECTRA的隐喻识别模型(S yntax-a ware G CN with E LECTRA,SaGE)。该模型从语言学出发,使用ELECTRA和Transformer编码器抽取句子的语义特征,将句子按照依存关系组织成一张图并使用图卷积神经网络抽取其句法特征,在此基础上对两类特征进行融合以进行隐喻识别。该模型在CCL 2018中文隐喻识别评测数据集上以85.22%的宏平均F 1值超越了此前的最佳成绩,验证了融合语义信息和句法信息对于隐喻识别任务具有重要作用。

基于关系增强图卷积网络的机器阅读理解式事件检测

在面对具有复杂句法关系的长文本上下文时,现有机器阅读理解式事件检测模型难以挖掘关键词之间长距离依赖关系。针对上述问题,提出一种基于关系增强图卷积网络(REGCN)的机器阅读理解式事件检测模型(MRCREGCN)。首先,利用预训练语言模型对问题和文本进行联合编码,得到融入先验信息的单词向量表示;其次,引入动态的关系增强标签信息,并利用REGCN深入学习单词之间的句法依存关系,增强模型对长文本句法结构的感知能力;最后,利用多分类器得到文本单词在所有事件类型下的概率分布。在ACE2005英文语料上的实验结果表明,所提模型在触发词分类上的F1分值相较于同类机器阅读理解模型EEQA(Event Extraction by Answering(almost)natural Questions)和最佳基线模型DEGREE(Data-Efficient GeneRation-based Event Extraction)分别提升了2.49%和1.23%,验证了MRC-REGCN具有更好的事件检测性能。

基于时空依赖关系和特征融合的弱监督视频异常检测

弱监督视频异常检测由于抗干扰性强、数据标注要求低,成为视频异常事件检测研究的热点。在现有的工作中,大多数弱监督视频异常检测方法认为各个视频段独立同分布,单独判断每个视频段是否异常,忽略了视频段间的时空依赖关系。为此,提出了一种基于时空依赖关系和特征融合的弱监督视频异常检测方法,在保留视频段原始特征的同时,使用视频段之间的索引距离和特征相似程度拟合视频段的时间和空间依赖关系,构建视频段的关系特征。通过融合原始特征和关系特征,更好地表达视频的动态特性和时序关系。在UCF-Crime和ShanghaiTech两个基准数据集上进行了大量实验,实验结果表明所提方法的AUC指标优于其他方法,AUC值分别达到了80.1%和94.6%。

有限相依随机序列的非贝叶斯变点最优监测

本文研究了有限相依样本序列的非贝叶斯变点检测问题.通过引入非负动态随机控制线,我们不仅构造并证明了两个最优控制图,而且还得到了比原定义更容易计算的Lorden测度和Pollak测度的最小值的表达式.

基于金字塔语义token全局信息增强的高分光学遥感影像变化检测

针对复杂背景、光谱变化等因素导致高分辨率遥感影像中细小地物检测缺失,几何结构检测不完整等问题,本文联合卷积网络和Transformer网络优势,提出一种基于金字塔语义token全局信息增强的变化检测网络(PST-GIENet)。首先,利用无最大池化层的ResNet18网络提取多时相影像深度特征以构建融合特征,并采用联合注意力机制和深监督策略提高融合特征表达能力;然后,通过空间金字塔池化将影像特征表示为多尺度语义token,进而利用Transformer编码器和解码器对融合特征空间进行全局上下文建模;最后,通过逐层上采样解码器生成最终变化图。为验证本文方法有效性,采用LEVIR-CD、CDD和WHU-CD 3个公开变化检测数据集进行对比试验与分析,定量结果表明PST-GIENet在3个数据集中均取得最优精度指标,其F 1值分别达到91.71%、96.16%和94.08%。目视结果表明PST-GIENet可有效抑制复杂背景、光谱变化等因素干扰,显著增强网络对地物边缘结构和多尺度变化的捕捉能力,取得最佳目视效果。

感光层厚度对a-GaO_(x)基日盲紫外光电探测器的性能影响研究

为制备高性能日盲紫外光电探测器,采用低温金属有机物化学气相沉积方法制备了非晶氧化镓薄膜。通过对薄膜结构特性测试证明了薄膜的非晶特性,并且薄膜表面较为平坦,光学吸收边位于深紫外波段范围内。在此基础上,研制了日盲紫外光电探测器。随非晶氧化镓感光层厚度由33.2 nm增至133.6 nm,探测器的光电流和暗电流均提升了2个数量级,并且响应度和外量子效率均随感光层厚度提升而增大,探测器的响应度和外量子效率的最大值分别达到2.91 A/W和1419.12%。探测器的厚度依赖特性可归因于界面高缺陷层、光吸收强度以及探测器的几何参数。此外,探测器展现出良好的波长选择性以及时间分辨响应稳定性。

基于语用交互的跨目标立场检测

针对缺乏足够的带标注意见数据、跨目标立场检测结果不佳且可解释性弱等问题,提出一种基于语用交互(pragmatic interaction graph convolution, PIGCN)的跨目标立场检测模型。考虑情感与立场在语义上的耦合关系,利用交互式图卷积神经网络(graphical convolutional network, GCN),增量式聚合单词在不同目标之间语用信息的相互作用,缓解目标间的信息孤岛问题。实验结果表明,该模型在平均F1值上达到了53.4%,优于基准模型,具有更好的可扩展性和适应性,在提升模型可解释性方面具有潜力。

基于数据依赖的跨架构二进制代码相似性分析

二进制代码相似性检测(Binary Code Similarity Detection,BCSD)技术在逆向工程、漏洞检测、恶意软件检测、软件抄袭以及补丁分析等学术应用领域发挥着重要作用。大多数研究已经集中在对二进制函数进行控制流嵌入和基于自然语言处理(Natural Language Processing,NLP)技术的底层代码嵌入技术的研究之中。然而,需要指出的是,函数在实际运行中不仅包含控制流信息,还包括数据流语义信息。因此,如何全面抽象函数的语义特征显得尤为关键。为此,该文提出了BS-DD模型,这是一个融合了控制流和数据依赖关系的二进制函数相似性判断框架。通过模拟执行二进制代码的方法来提取语义信息,并运用化简算法构建数据依赖关系图。最后,借助图神经网络进行相似性判别。对来自开源社区的7个广泛使用的软件进行了不同组合的编译,并在此基础上设计了3个不同的任务场景以及真实的漏洞检测实验,用以比较BS-DD方法与最新基于数据流的BCSD方法的性能。实验结果显示,该模型在召回率和MRR(Mean Reciprocal Rank)分数方面取得了显著的提高。在真实环境的漏洞检测中,该模型也始终优于其他方法。

基于到达时间间隔差的ADS-B位置消息验证方法

广播式自动相关监视(ADS-B)是一种新型的航空器监视技术,具有定位精度高、更新速度快及覆盖范围广等优势,在民用航空监视领域获得广泛应用。由于ADS-B消息以广播方式传输,未采用加密与认证机制,ADS-B系统易受外部欺骗源的干扰。为解决该问题,提出了一种基于到达时间间隔差(IDOA)的ADS-B位置消息验证方法。建立基于IDOA的ADS-B位置消息验证系统模型,理论分析给出检验统计量的表达式及其统计特性,进一步分析给出检测门限的确定方法,通过仿真验证所提方法的正确性与有效性。结果表明:所提方法与基于到达时间差(TDOA)的验证方法具有相同的检测性能,且对时间测量误差和ADS-B位置误差不敏感,但所提方法可克服基于TDOA的验证方法存在的对地面站时间同步误差敏感的缺点。

一种多用户协同的BOM数据一致性校核与检测算法设计

针对航空航天制造领域中多用户协同工作场景下,由人为错误操作或数据库共享异常导致的数据一致性较差问题,文中基于改进函数依赖和着色PETRI网构建了BOM数据一致性校核与检验模型。该模型根据多用户BOM数据的结构特点,界定了零部件的层次结构与关系定义。同时对传统函数依赖算法加以改进,并控制数据迁移规模及并行度以改善函数依赖发现效率,从而进行数据信息的不一致校核。通过解构HDFS系统数据写入流程,利用着色PETRI网进行数据共享流程建模,进而实现数据共享一致性校核算法的构建。经仿真验证,所述方案的两种耗时指标与对照组算法相比分别降低了26.61%和38.23%,且状态空间及强连通构建图中状态节点和变迁的数量一致,不存在回路,由此证明了该方案的可行性。