A background refinement method based on local density for hyperspectral anomaly detection

For anomaly detection,anomalies existing in the background will affect the detection performance.Accordingly,a background refinement method based on the local density is proposed to remove the anomalies from thebackground.In this work,the local density is measured by its spectral neighbors through a certain radius which is obtained by calculating the mean median of the distance matrix.Further,a two-step segmentation strategy is designed.The first segmentation step divides the original background into two subsets,a large subset composed by background pixels and a small subset containing both background pixels and anomalies.The second segmentation step employing Otsu method with an aim to obtain a discrimination threshold is conducted on the small subset.Then the pixels whose local densities are lower than the threshold are removed.Finally,to validate the effectiveness of the proposed method,it combines Reed-Xiaoli detector and collaborative-representation-based detector to detect anomalies.Experiments are conducted on two real hyperspectral datasets.Results show that the proposed method achieves better detection performance.

Intrusion Detection Algorithm Based on Density,Cluster Centers,and Nearest Neighbors

Intrusion detection aims to detect intrusion behavior and serves as a complement to firewalls.It can detect attack types of malicious network communications and computer usage that cannot be detected by idiomatic firewalls.Many intrusion detection methods are processed through machine learning.Previous literature has shown that the performance of an intrusion detection method based on hybrid learning or integration approach is superior to that of single learning technology.However,almost no studies focus on how additional representative and concise features can be extracted to process effective intrusion detection among massive and complicated data.In this paper,a new hybrid learning method is proposed on the basis of features such as density,cluster centers,and nearest neighbors(DCNN).In this algorithm,data is represented by the local density of each sample point and the sum of distances from each sample point to cluster centers and to its nearest neighbor.k-NN classifier is adopted to classify the new feature vectors.Our experiment shows that DCNN,which combines K-means,clustering-based density,and k-NN classifier,is effective in intrusion detection.

Multi-Layer Reconstruction Errors Autoencoding and Density Estimate for Network Anomaly Detection

Anomaly detection is an important method for intrusion detection.In recent years,unsupervised methods have been widely researched because they do not require labeling.For example,a nonlinear autoencoder can use reconstruction errors to attain the discrimination threshold.This method is not effective when the model complexity is high or the data contains noise.The method for detecting the density of compressed features in a hidden layer can be used to reduce the influence of noise on the selection of the threshold because the density of abnormal data in hidden layers is smaller than normal data.However,compressed features may lose some of the high-dimensional distribution information of the original data.In this paper,we present an efficient anomaly detection framework for unsupervised anomaly detection,which includes network data capturing,processing,feature extraction,and anomaly detection.We employ a deep autoencoder to obtain compressed features and multi-layer reconstruction errors,and feeds them the same to the Gaussian mixture model to estimate the density.The proposed approach is trained and tested on multiple current intrusion detection datasets and real network scenes,and performance indicators,namely accuracy,recall,and F1-score,are better than other autoencoder models.

Density-based trajectory outlier detection algorithm

With the development of global position system（GPS）,wireless technology and location aware services,it is possible to collect a large quantity of trajectory data.In the field of data mining for moving objects,the problem of anomaly detection is a hot topic.Based on the development of anomalous trajectory detection of moving objects,this paper introduces the classical trajectory outlier detection（TRAOD） algorithm,and then proposes a density-based trajectory outlier detection（DBTOD） algorithm,which compensates the disadvantages of the TRAOD algorithm that it is unable to detect anomalous defects when the trajectory is local and dense.The results of employing the proposed algorithm to Elk1993 and Deer1995 datasets are also presented,which show the effectiveness of the algorithm.

An Aircraft Trajectory Anomaly Detection Method Based on Deep Mixture Density Network

The timely and accurately detection of abnormal aircraft trajectory is critical to improving flight safety.However,the existing anomaly detection methods based on machine learning cannot well characterize the features of aircraft trajectories.Low anomaly detection accuracy still exists due to the high-dimensionality,heterogeneity and temporality of flight trajectory data.To this end,this paper proposes an abnormal trajectory detection method based on the deep mixture density network(DMDN)to detect flights with unusual data patterns and evaluate flight trajectory safety.The technique consists of two components:Utilization of the deep long short-term memory(LSTM)network to encode features of flight trajectories effectively,and parameterization of the statistical properties of flight trajectory using the Gaussian mixture model(GMM).Experiment results on Guangzhou Baiyun International Airport terminal airspace show that the proposed method can effectively capture the statistical patterns of aircraft trajectories.The model can detect abnormal flights with elevated risks and its performance is superior to two mainstream methods.The proposed model can be used as an assistant decision-making tool for air traffic controllers.

Anomalous Cell Detection with Kernel Density-Based Local Outlier Factor

Since data services are penetrating into our daily life rapidly, the mobile network becomes more complicated, and the amount of data transmission is more and more increasing. In this case, the traditional statistical methods for anomalous cell detection cannot adapt to the evolution of networks, and data mining becomes the mainstream. In this paper, we propose a novel kernel density-based local outlier factor(KLOF) to assign a degree of being an outlier to each object. Firstly, the notion of KLOF is introduced, which captures exactly the relative degree of isolation. Then, by analyzing its properties, including the tightness of upper and lower bounds, sensitivity of density perturbation, we find that KLOF is much greater than 1 for outliers. Lastly, KLOFis applied on a real-world dataset to detect anomalous cells with abnormal key performance indicators(KPIs) to verify its reliability. The experiment shows that KLOF can find outliers efficiently. It can be a guideline for the operators to perform faster and more efficient trouble shooting.

Outlier detection based on multi-dimensional clustering and local density

Outlier detection is an important task in data mining. In fact, it is difficult to find the clustering centers in some sophisticated multidimensional datasets and to measure the deviation degree of each potential outlier. In this work, an effective outlier detection method based on multi-dimensional clustering and local density(ODBMCLD) is proposed. ODBMCLD firstly identifies the center objects by the local density peak of data objects, and clusters the whole dataset based on the center objects. Then, outlier objects belonging to different clusters will be marked as candidates of abnormal data. Finally, the top N points among these abnormal candidates are chosen as final anomaly objects with high outlier factors. The feasibility and effectiveness of the method are verified by experiments.

Nested grazing incidence optics for x ray detection

Grazing incidence optics （GIO） is the most important compound in an x-ray detection system; it is used to concentrate the x-ray photons from outer space. A nested planar GIO for x-ray concentration is designed and developed by authors in this paper; planar segments are used as the reflection mirror instead of curved segments because of the simple process and low cost. After the complex assembling process with a special metal supporter, a final circle light spot of φ 12 mm was obtained in the visible light testing experiment of GIO; the effective area of 1710.51 mm^2@ 1 keV and 530 mm^2@8 keV is obtained in the x-ray testing experiment with the GIO-SDD combination, which is supposed to be a concentrating detector in xray detection systems.

The potential of FAST in detecting celestial hydroxyl masers and related science topics

The Five-hundred-meter Aperture Spherical radio Telescope(FAST) will make contributions to studies of Galactic and extragalactic masers. This telescope, with construction finished and now undergoing commissioning, has an innovative design that leads to the highest sensitivity of any single dish radio telescope in the world. FAST's potential for OH megamaser research is discussed, including the sky density of masers detectable in surveys. The scientific impact expected from FAST maser studies is also discussed.

Density-based rough set model for hesitant node clustering in overlapping community detection

Overlapping community detection in a network is a challenging issue which attracts lots of attention in recent years.A notion of hesitant node（HN） is proposed. An HN contacts with multiple communities while the communications are not strong or even accidental, thus the HN holds an implicit community structure.However, HNs are not rare in the real world network. It is important to identify them because they can be efficient hubs which form the overlapping portions of communities or simple attached nodes to some communities. Current approaches have difficulties in identifying and clustering HNs. A density-based rough set model（DBRSM） is proposed by combining the virtue of densitybased algorithms and rough set models. It incorporates the macro perspective of the community structure of the whole network and the micro perspective of the local information held by HNs, which would facilitate the further ＂growth＂ of HNs in community. We offer a theoretical support for this model from the point of strength of the trust path. The experiments on the real-world and synthetic datasets show the practical significance of analyzing and clustering the HNs based on DBRSM. Besides, the clustering based on DBRSM promotes the modularity optimization.

Vascular endothelial growth factor and microvessel density for detection and prognostic evaluation of invasive breast cancer

Objective The purpose of this study was to evaluate the distribution of vascular endothelial growth factor （VEGF） and CD105-microvessel density （MVD）in invasive breast carcinomas. We also aimed to analyze the relationship between VEGF and MVD expression with other standard prognostic parameters associated with invasive breast cancer, such as size, grade, stage of the cancer, metastases, and tumor recurrence. Methods immunohistochemistry via the Ultra SensitiveTM S-P method was used to detect VEGF and MVD expression in 128 cases of invasive breast carcinoma. Specimens were evaluated for CD105 expression. Positively stained microvessels were counted in dense vascular loci under 400x magnification, MVD in the peripheral area adjacent to the lesion and in the central, area within the lesion in invasive breast carcinomas and benign leisions groups were also assessed. Fifty cases of benign breast disease tissue were selected as the control group. Results Results showed that 64.1% of invasive breast cancer samples were VEGF-positive, higher than in benign breast disease tissue （22.0%, P 〈 0.05）. There was a positive correlation between VEGF overexpression and histological grade, lymph node metastasis, and distant metastasis of invasive breast cancer. VEGF expression was not related to age or size of the tumor （P 〉 0.05）. MVD of the peripheral area adjacent to the lesion was significantly higher than those central area within the lesion in both invasive breast cancer and benignbreast disease groups （P 〈 0.01 for each group）. There were significant differences in the mean CD105-MVD, between invasive breast tumors with a histological grade of Ⅰ or Ⅱ and grade Ⅲ; between tumors with lymph node or distant metastasis; and between patients with or without recurrence （P 〈 0.05）. However, there was no difference in the mean MVD between the two age groups （≤ 50 years vs. 〉 50 years） or the two tumor diameter groups （〈 2 cm vs. 〉 2 cm）, P 〉 0.05. Conclusion Overexpression of VEGF and MVD may be important biological.markers for invasion and lymph node and distant metastases of invasive breast cancer. Combined detection of the two tumor markers could provide better prognostic monitoring for disease recurrence and metastasis, as well as aid with clinical staging of breast tumors. Prediction of the risk for metastasis and recurrence, as well as recurrence patterns based on VEGF and MVD post-surgery, could aid design of better follow-up regimens and appropriate treatment strategies for breast cancer patients.

Improved Density Peaking Algorithm for Community Detection Based on Graph Representation Learning

There is a large amount of information in the network data that we canexploit. It is difficult for classical community detection algorithms to handle network data with sparse topology. Representation learning of network data is usually paired with clustering algorithms to solve the community detection problem.Meanwhile, there is always an unpredictable distribution of class clusters outputby graph representation learning. Therefore, we propose an improved densitypeak clustering algorithm (ILDPC) for the community detection problem, whichimproves the local density mechanism in the original algorithm and can betteraccommodate class clusters of different shapes. And we study the communitydetection in network data. The algorithm is paired with the benchmark modelGraph sample and aggregate (GraphSAGE) to show the adaptability of ILDPCfor community detection. The plotted decision diagram shows that the ILDPCalgorithm is more discriminative in selecting density peak points compared tothe original algorithm. Finally, the performance of K-means and other clusteringalgorithms on this benchmark model is compared, and the algorithm is proved tobe more suitable for community detection in sparse networks with the benchmarkmodel on the evaluation criterion F1-score. The sensitivity of the parameters ofthe ILDPC algorithm to the low-dimensional vector set output by the benchmarkmodel GraphSAGE is also analyzed.

BACKGROUND RECTIFICATION AND FEATURE EXTRACTION OF IMAGE IN A SPOT WELD OF AL ALLOY X-RAY DETECTION

A primary study on Processing in X - ray inspection of spot weld for aluminum alloy spot welding,in- cluding for background simulation,acquisition of ideal binary image, and extraction and identifi- cation of defect features was presented.

Implementation of Network Intrusion Detection System Based on Density-based Outliers Mining

The paper puts forward a new method of density-based anomaly data mining, the method is used to design the engine of network intrusion detection system (NIDS), thus a new NIDS is constructed based on the engine. The NIDS can find new unknown intrusion behaviors, which are used to updated the intrusion rule-base, based on which intrusion detections can be carried out online by the BM pattern match algorithm. Finally all modules of the NIDS are described by formalized language.

基于深度学习SSD算法的高密度电法智能解译方法技术研究

高密度电法在探测灰岩区地下溶洞病害体方面得到广泛应用,但高密度电法反演结果依赖于初始模型,存在多解性,地质解译容易受专业人员主观因素影响。为此,本文从具有唯一性的视电阻率数据出发,研究了基于深度学习的SSD(Single Shot Multi-box Detector)目标检测算法的视电阻率异常智能解译方法技术。针对岩溶地质病害,设计了不同填充类型、形状、规模、数量的溶洞电性异常模型,利用Res2dmod软件进行视电阻率正演计算,构建了包含1400个样本的高密度电法视电阻率智能解译学习样本库(样本和标签)。基于TensorFlow框架,建立了基于深度学习SSD算法的高密度电法视电阻率异常智能解译方法技术,使用学习样本库训练网络权值,训练结束后对高密电法温纳装置视电阻率异常进行智能解译,单个视电阻率剖面异常智能解译耗时不到1 s,各类目标(填充型溶洞、未填充型溶洞)平均准确率为90.68%。研究结果表明:基于SSD算法的高密度电法视电阻率异常智能解译技术可显著提高高密度电法视电阻率解译效率,避免专业人员主观因素影响。

结合密度图回归与检测的密集计数研究

针对基于检测以及基于密度图两种主流的密集计数方法中,基于检测的方法召回率较低、基于密度图的方法缺失目标物体位置信息的问题,将检测任务与回归任务相结合后提出一种基于密度图回归的检测计数方法,可以实现对密集场景中目标物体的计数以及定位,对两种方法进行优势互补,在提高召回率的同时,实现标定所有目标物体的位置信息。为提取出更加丰富的特征信息以面对复杂的数据场景,网络提出特征金字塔优化模块,该模块纵向融合底层高分辨特征与顶层抽象语义特征,横向融合同尺寸的特征,丰富目标物体的语义表达;考虑到密集计数场景中目标物体所占像素比例较低的问题,提出一种针对小目标的注意力机制,通过对输入图像构建掩膜以增强网络对目标物体的注意力,从而提高网络的检测敏感性。实验结果表明,所提出方法在保持准确率基本不变的情况下,大幅度提高了召回率,同时可准确标定目标物体位置,有效提供输入目标图像的计数以及定位信息,在工业以及生态等各种领域具有广泛的应用前景。

新拌混凝土均匀度的超声检测

混凝土均匀度检测是混凝土施工质量控制中的关键技术之一。基于超声技术开展了不同搅拌时间下的新拌混凝土均匀度检测试验,得出不同点位的混凝土密度,从而计算出不同搅拌时间下混凝土的均匀度指数。试验结果表明,新拌混凝土使用单卧轴搅拌机的合理搅拌时间为100~150 s,通过分析3种拟合函数的回归曲线与实测关系曲线的符合程度,确定了符合程度较高的专用均匀度检测曲线拟合函数。由此可见,超声技术可有效检测混凝土的均匀度,在一定程度上可指导新拌混凝土的现场施工。

基于增量式等距映射同双重局部密度方法的工业过程故障检测

针对工业过程的非线性和动态性问题,提出一种基于流形学习下的增量式等距映射(IISOMAP)与双重局部密度(DLD)相结合的故障检测方法(IISOMAP-DLD).利用IISOMAP将原始数据映射到低维流形特征子空间和剩余子空间;然后,在两个子空间中分别引入双重局部密度方法构建统计量对过程进行监控;最后,将IISOMAP-DLD方法应用到田纳西-伊斯曼(TE)过程.实验结果表明,IISOMAP-DLD对比其他方法有更高的故障检测率.IISOMAP在保留数据内在特征的同时,解决了过程的非线性问题,而双重局部密度方法可消除过程的动态性.

改进DPC聚类算法的离群点检测与解释方法

为解决全局离群点检测方法无法对局部离群点进行检测,以及局部异常因子在面对大量局部离群点时性能下降的问题,利用k近邻(KNN)和核密度估计方法(KDE)提出一种基于改进快速搜索和发现密度峰值聚类算法(KDPC)的离群点检测与解释方法,该方法能够同时对数据点的全局和局部进行分析。首先,利用k近邻和核密度估计方法计算数据点的局部密度,代替传统DPC算法中根据截断距离计算的局部密度。其次,将数据点的k近邻距离之和作为全局异常值,并通过KDPC聚类算法计算簇密度以及数据点的局部异常值。最后,将数据点的全局与局部异常值进行乘积作为最终异常得分,选取异常得分最高的Top-n作为离群点,通过构建全局-局部异常值决策图对全局和局部离群点进行解释。利用人工数据集和UCI数据集进行实验并与10种常用离群点检测方法进行比较。结果表明,该方法对全局和局部离群点都有着较高的检测精度和检测性能,并且AUC方面受k值影响较小。同时,利用该方法对NBA球员数据进行分析讨论,进一步证明了该方法的实用性和有效性。

环氧复合绝缘内部缺陷超声自动检测系统

环氧复合绝缘子密度不均匀和内部集中缺陷严重威胁着气体绝缘金属封闭开关设备(gas insulated metal-enclosed switchgear, GIS)的安全运行,目前超声检测方法存在缺陷检测不直观、效率低等问题。针对此,基于超声反射原理研制环氧复合绝缘材料内部缺陷超声自动成像系统。首先采用小波分析对非重复性超声回波信号进行降噪;然后对回波波形的相邻波峰时间差、电压峰值和电压相邻波峰间的零信号时间进行特征融合识别,得到试样缺陷的位置-超声特征数据集;最后实现环氧复合绝缘缺陷超声自动成像。分别用本文检测系统和传统检测方式对密度不均匀和不同深度、取向裂纹的环氧复合绝缘试样进行检测和对比分析。结果表明:该系统与质量体积法测量的局部密度误差小于4.8%;内部集中性缺陷检测结果和缺陷原貌具有一致性;检测效率较传统人工超声检测提升近6倍。该系统实现了环氧复合绝缘材料的内部集中缺陷和密度不均匀检测的统一,在绝缘子出厂试验和故障分析缺陷定位方面较传统人工检测方式在检测效率和直观性上具有一定优势。