DA-LSTM-VAE: Dual-Stage Attention-Based LSTM-VAE for KPI Anomaly Detection

To ensure the normal operation of the system, the enterprise’s operations engineer will monitor the system through the KPI (key performance indicator). For example, web page visits, server memory utilization, etc. KPI anomaly detection is a core technology, which is of great significance for rapid fault detection and repair. This paper proposes a novel dual-stage attention-based LSTM-VAE (DA-LSTM-VAE) model for KPI anomaly detection. Firstly, in order to capture time correlation in KPI data, long–short-term memory (LSTM) units are used to replace traditional neurons in the variational autoencoder (VAE). Then, in order to improve the effect of KPI anomaly detection, an attention mechanism is introduced into the input stage of the encoder and decoder, respectively. During the input stage of the encoder, a time attention mechanism is adopted to assign different weights to different time points, which can adaptively select important input sequences to avoid the influence of noise in the data. During the input stage of the decoder, a feature attention mechanism is adopted to adaptively select important latent variable representations, which can capture the long-term dependence of time series better. In addition, this paper proposes an adaptive threshold method based on anomaly scores measured by reconstruction probability, which can minimize false positives and false negatives and avoid adjustment of the threshold manually. Experimental results in a public dataset show that the proposed method in this paper outperforms other baseline methods.     

彩色立体像对的自适应匹配

提出了一种自适应权值的色彩相似性度量方法,有效地抑制了噪声对立体匹配的影响,提出以立体像对左、右图像间的颜色直方图相关系数为标准来调整权值的方法,并通过实验推导出具体的计算公式.对以灰度变化为基准的自适应窗选择方法进行改进,在边界提取过程中加入了彩色信息,使得提取的物体轮廓更为完整;用"米"字型窗口来代替原来的矩形窗口也使得窗口增长更为灵活,获得的匹配更为准确.实验结果表明,本文算法能够生成精确度较高的视差图,是一种较好的立体匹配算法.     

区域指导的自适应图像插值算法

提出了一种以图像区域的一致性为指导的自适应选择插值公式(简称ADA)的图像插值算法.首先将图像分割成不同区域,然后结合近邻法和众数法确定待插值点所属区域,将待插值点分类处理:对于区域内的点,采用线性插值;对于区域间的过渡点,设计非线性插值公式,分配较大的权值给与待插值点属于同一区域的邻域像素,分配较小的权值给其它邻域像素.实验表明,ADA图像插值算法得到的插值图像有较好的主观图像质量,其峰值信噪比(PSNR)比传统方法平均提高了3.11～4.39 dB.     

基于梯度相关性的红外微弱目标检测

提出了一种新的基于空域梯度相关性的图像杂波自适应预测算法.该算法能显著改善微小目标的邻域信杂比(SCNR).试验证明,本算法相对于已有的多种算法,有着更好的性能.对微弱目标SCNR的增益相对于传统算法提高3 dB以上.本文还引入了一种基于统计分析的微小目标检测算法.该算法考虑了微小目标在图像集成时的重叠特性,能在不增加系统运算负荷的情况下,获得更高的检测概率,相对于不考虑重叠特性的算法,在虚警概率小于10-4时,假设重叠系数为3,SCNR为4 dB,系统检测概率从小于20%,大幅提高到80%.理论分析及仿真表明,本文提出的检测系统存微小目标枪测中,具有很高的实用性.系统在原始信号的邻域信杂比(SCNR)小于0 dB的情况下,能有效检测出目标,在采用10帧集成检测,目标像素重叠参数为5的情况下,虚警概率小于10-7,系统检测概率大于80%,虚警概率小于10-4,系统检测概率大于95%. 标在图像集成时的重叠特性,能在不增加系统运算负荷的情况下,获得更高的检测概率,相对于不考虑重叠特性的算法,在虚警概率小于10-4时,假设重叠系数为3,SCNR为4 dB,系统检测概率从小于20%,大幅提高到80%.理论分析及仿真 明,本文提出的检测系统存微小目标枪测中,具有很高的实用性.系统在原始信号的邻域信杂比(SCNR)小于0 dB的情况卜,能有效检测出目标,在采用10帧集成检测,目标像素重叠参数为5的情况下,虚警概率小于10-7,系统检测概率大于80%,虚警概率小于10-4,系统检测概率大于95%. 标在图像集成时的重叠特性,能在不增加系统运算负荷的情况下,获得更高的检测概率,相对于不考虑重叠特性的算法,     

基于逆拉伸变换的脑血管减影图像非刚性配准

提出了一种基于逆拉伸空间变换的蒙片像素点灰度值映射求解方法。实验中使蒙片网格化以产生恰当的控制点,采用最大减影直方图能量相似性测度准则和鲍威尔优化搜索方法,对蒙片图像和活片图像进行局部变形非刚性配准。该算法有效保证了蒙片图像变形前后灰度值变化的拓扑一致,使变形后的蒙片图像仍保持清晰准确的轮廓,配准后的减影图像质量良好,噪声和伪影明显减少,同时省去插值计算过程,配准速度明显提高,为临床中的脑血管病变诊断提供了有力支持。     

群体决策随机偏爱数映射的若干性质

1引言近年来,群体决策在社会选择、福利、经济和军事等领域得到广泛应用,从而其理论研究越来越被人们所重视.20世纪中叶,K.J,Arrow提出了偏爱公理系和不可能性定理,并     

Schwarz Lemma at the Boundary on the Classical Domain of Type Ⅲ

Let R_Ⅲ(n) be the classical domain of type Ⅲ with n≥2. This article is devoted to a deep study of the Schwarz lemma on R_Ⅲ(n) via not only exploring the smooth boundary points of R_Ⅲ(n) but also proving the Schwarz lemma at the smooth boundary point for holomorphic self-mappings of R_Ⅲ(n).     

Community Detection in Semantic Networks: A Multi-View Approach

The semantic social network is a complex system composed of nodes, links, and documents. Traditional semantic social network community detection algorithms only analyze network data from a single view, and there is no effective representation of semantic features at diverse levels of granularity. This paper proposes a multi-view integration method for community detection in semantic social network. We develop a data feature matrix based on node similarity and extract semantic features from the views of word frequency, keyword, and topic, respectively. To maximize the mutual information of each view, we use the robustness of L21-norm and F-norm to construct an adaptive loss function. On this foundation, we construct an optimization expression to generate the unified graph matrix and output the community structure with multiple views. Experiments on real social networks and benchmark datasets reveal that in semantic information analysis, multi-view is considerably better than single-view, and the performance of multi-view community detection outperforms traditional methods and multi-view clustering algorithms.     

椭圆形孔扩张弹性分析

圆孔扩张理论作为一种相对成熟的理论工具已经广泛运用于岩土工程中的各类问题,但是对于初始孔为椭圆孔的扩孔问题,圆孔扩张理论并不适用.基于保角变换的方法将原物理平面上初始椭圆孔洞的外部映射到像平面上的单位圆外部,将原物理平面上由于椭圆孔洞扩张所产生的位移边界条件转换到像平面上,利用平面复变弹性理论,得到初始椭圆形孔洞孔扩张的弹性解.将论文椭圆孔扩张的退化解与传统圆孔扩张的弹性解进行对比分析,验证椭圆孔扩张弹性解的正确性.续而,针对一算例详细分析了椭圆孔扩张的弹性力学特性.研究结果表明,椭圆孔的退化解与传统的圆孔扩张弹性解完全一致,椭圆孔在弹性扩张过程中长轴方向比短轴方向较难扩张,长轴方向需要的扩张压力比短轴方向的要大.此外,当扩张率a2/a1=0.11/0.1=1.1时,扩张的影响半径为10倍的孔径左右.     

Logistic混沌映射性能分析与改进

混沌系统是基于混沌的数据加密领域的一个重要研究对象,Logistic混沌映射是最简单和有效的混沌系统,被广泛应用在大多数混沌加密算法中,Logistic映射的安全性成为研究的热点。针对Logistic序列存在的吸引子与空白区问题,该文提出一种基于初始值和分形控制参数之间关系的Logistic映射改进方法。利用两者之间关系对映射自变量区间进行合理分段,扩大了混沌控制参数区域,将满射范围扩大到整个控制参数区间,使产生的序列分布更均匀,解决了稳定窗与空白区等问题。通过将改进Logistic与其它分段Logistic映射进行仿真对比,实验结果表明改进后的映射产生的序列混沌特性得到显著加强,分布更均匀,具有更好的随机性能测试指标。另外,改进Logistic映射计算复杂度低,实现简单,在扩频通信与混沌密码等领域有广阔的应用前景。