Mixed Pattern Matching-Based Traffic Abnormal Behavior Recognition

A motion trajectory is an intuitive representation form in time-space domain for a micromotion behavior of moving target. Trajectory analysis is an important approach to recognize abnormal behaviors of moving targets. Against the complexity of vehicle trajectories, this paper first proposed a trajectory pattern learning method based on dynamic time warping (DTW) and spectral clustering. It introduced the DTW distance to measure the distances between vehicle trajectories and determined the number of clusters automatically by a spectral clustering algorithm based on the distance matrix. Then, it clusters sample data points into different clusters. After the spatial patterns and direction patterns learned from the clusters, a recognition method for detecting vehicle abnormal behaviors based on mixed pattern matching was proposed. The experimental results show that the proposed technical scheme can recognize main types of traffic abnormal behaviors effectively and has good robustness. The real-world application verified its feasibility and the validity.

Download Full-text

Instruction Clustering Analysis for Unknown Network Protocol's Abnormal Behavior

Journal of Interconnection Networks ◽

10.1142/s0219265915400022 ◽

2015 ◽

Vol 15 (03n04) ◽

pp. 1540002

Author(s):

YANJING HU ◽

QINGQI PEI ◽

LIAOJUN PANG

Keyword(s):

Clustering Analysis ◽

Clustering Algorithm ◽

High Efficiency ◽

Abnormal Behavior ◽

Automatic Clustering ◽

Reverse Analysis ◽

Message Format ◽

Instruction Sequences ◽

Analysis Platform ◽

Abnormal Behaviors

Protocol's abnormal behavior analysis is an important task in protocol reverse analysis. Traditional protocol reverse analysis focus on the protocol message format, but protocol behavior especially the abnormal behavior is rare studied. In this paper, protocol behavior is represented by the labeled behavior instruction sequences. Similar behavior instruction sequences mean the similar protocol behavior. Using our developed virtual analysis platform HiddenDisc, we can capture a variety of known or unknown protocols' behavior instruction sequences. All kinds of executed or unexecuted instruction sequences can automatic clustering by our designed instruction clustering algorithm. Thereby we can distinguish and mine the unknown protocols' potential abnormal behavior. The mined potential abnormal behavior instruction sequences are executed, monitored and analyzed on HiddenDisc to determine whether it is an abnormal behavior and what is the behavior's nature. Using the instruction clustering algorithm, we have analyzed 1297 protocol samples, mined 193 potential abnormal instruction sequences, and determined 187 malicious abnormal behaviors by regression testing. Experimental results show that our proposed instruction clustering algorithm has high efficiency and accuracy, can mine unknown protocols' abnormal behaviors effectively, and enhance the initiative defense capability of network security.

Download Full-text

IKM-NCS: A Novel Clustering Scheme Based on Improved K-Means Algorithm

International Journal of Mathematical Models and Methods in Applied Sciences ◽

10.46300/9101.2020.14.20 ◽

2020 ◽

Vol 14 ◽

Keyword(s):

Clustering Algorithm ◽

User Behavior ◽

Abnormal Behavior ◽

Cluster Center ◽

Initial Sample ◽

Initial Cluster ◽

Weight Calculation ◽

Data Points ◽

Abnormal Behaviors ◽

Better Than

Aiming at the problems of distorted center selection and slow iteration convergence in traditional clustering analysis algorithm, a novel clustering scheme based on improved k-means algorithm is proposed. In this paper, based on the analysis of all user behavior sets contained in the initial sample, a weight calculation method for abnormal behaviors and an eigenvalue extraction method for abnormal behavior set are proposed and a set of abnormal behaviors is constructed for each user according to the behavior data generated by abnormal users. Then, on the basis of the traditional k-means clustering algorithm, an improved algorithm is proposed. By calculating the compactness of all data points and selecting the initial cluster center among the data points with high and low compactness, the clustering performance is enhanced. Finally, the eigenvalues of the abnormal behavior set are used as the input of the algorithm to output the clustering results of the abnormal behavior. Experimental results show that the clustering performance of this algorithm is better than the traditional clustering algorithm, and can effectively improve the clustering performance of abnormal behavior

Download Full-text

Audit Analysis of Abnormal Behavior of Social Security Fund Based on Adaptive Spectral Clustering Algorithm

Complexity ◽

10.1155/2021/4969233 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Yan Wu ◽

Yonghong Chen ◽

Wenhao Ling

Keyword(s):

Social Security ◽

Spectral Clustering ◽

Clustering Algorithm ◽

Gaussian Function ◽

Abnormal Behavior ◽

Stage Of Development ◽

Laplace Matrix ◽

Abnormal Behavior Detection ◽

Data Points ◽

Spectral Clustering Algorithm

Abnormal behavior detection of social security funds is a method to analyze large-scale data and find abnormal behavior. Although many methods based on spectral clustering have achieved many good results in the practical application of clustering, the research on the spectral clustering algorithm is still in the early stage of development. Many existing algorithms are very sensitive to clustering parameters, especially scale parameters, and need to manually input the number of clustering. Therefore, a density-sensitive similarity measure is introduced in this paper, which is obtained by introducing new parameters to transform the Gaussian function. Under this metric, the distance between data points belonging to different classes will be effectively amplified, while the distance between data points belonging to the same class will be reduced, and finally, the distribution of data will be effectively clustered. At the same time, the idea of Eigen gap is introduced into the spectral clustering algorithm, and the verified gap sequence is constructed on the basis of Laplace matrix, so as to solve the problem of the number of initial clustering. The strong global search ability of artificial bee colony algorithm is used to make up for the shortcoming of spectral clustering algorithm that is easy to fall into local optimal. The experimental results show that the adaptive spectral clustering algorithm can better identify the initial clustering center, perform more effective clustering, and detect abnormal behavior more accurately.

Download Full-text

A Novel Unsupervised Classification Method for Sandy Land Using Fully Polarimetric SAR Data

Remote Sensing ◽

10.3390/rs13030355 ◽

2021 ◽

Vol 13 (3) ◽

pp. 355

Author(s):

Weixian Tan ◽

Borong Sun ◽

Chenyu Xiao ◽

Pingping Huang ◽

Wei Xu ◽

...

Keyword(s):

Spectral Clustering ◽

Large Scale ◽

Clustering Algorithm ◽

Feature Vector ◽

Unsupervised Classification ◽

Classification Method ◽

Sandy Land ◽

Classification Methods ◽

The Many ◽

Representative Points

Classification based on polarimetric synthetic aperture radar (PolSAR) images is an emerging technology, and recent years have seen the introduction of various classification methods that have been proven to be effective to identify typical features of many terrain types. Among the many regions of the study, the Hunshandake Sandy Land in Inner Mongolia, China stands out for its vast area of sandy land, variety of ground objects, and intricate structure, with more irregular characteristics than conventional land cover. Accounting for the particular surface features of the Hunshandake Sandy Land, an unsupervised classification method based on new decomposition and large-scale spectral clustering with superpixels (ND-LSC) is proposed in this study. Firstly, the polarization scattering parameters are extracted through a new decomposition, rather than other decomposition approaches, which gives rise to more accurate feature vector estimate. Secondly, a large-scale spectral clustering is applied as appropriate to meet the massive land and complex terrain. More specifically, this involves a beginning sub-step of superpixels generation via the Adaptive Simple Linear Iterative Clustering (ASLIC) algorithm when the feature vector combined with the spatial coordinate information are employed as input, and subsequently a sub-step of representative points selection as well as bipartite graph formation, followed by the spectral clustering algorithm to complete the classification task. Finally, testing and analysis are conducted on the RADARSAT-2 fully PolSAR dataset acquired over the Hunshandake Sandy Land in 2016. Both qualitative and quantitative experiments compared with several classification methods are conducted to show that proposed method can significantly improve performance on classification.

Download Full-text

An Enhanced Spectral Clustering Algorithm with S-Distance

Symmetry ◽

10.3390/sym13040596 ◽

2021 ◽

Vol 13 (4) ◽

pp. 596

Author(s):

Krishna Kumar Sharma ◽

Ayan Seal ◽

Enrique Herrera-Viedma ◽

Ondrej Krejcar

Keyword(s):

Spectral Clustering ◽

Clustering Algorithm ◽

Spatial Clustering ◽

Clustering Algorithms ◽

Rank Test ◽

Customer Churn ◽

Signed Rank ◽

Signed Rank Test ◽

Spectral Clustering Algorithm ◽

Industrial Databases

Calculating and monitoring customer churn metrics is important for companies to retain customers and earn more profit in business. In this study, a churn prediction framework is developed by modified spectral clustering (SC). However, the similarity measure plays an imperative role in clustering for predicting churn with better accuracy by analyzing industrial data. The linear Euclidean distance in the traditional SC is replaced by the non-linear S-distance (Sd). The Sd is deduced from the concept of S-divergence (SD). Several characteristics of Sd are discussed in this work. Assays are conducted to endorse the proposed clustering algorithm on four synthetics, eight UCI, two industrial databases and one telecommunications database related to customer churn. Three existing clustering algorithms—k-means, density-based spatial clustering of applications with noise and conventional SC—are also implemented on the above-mentioned 15 databases. The empirical outcomes show that the proposed clustering algorithm beats three existing clustering algorithms in terms of its Jaccard index, f-score, recall, precision and accuracy. Finally, we also test the significance of the clustering results by the Wilcoxon’s signed-rank test, Wilcoxon’s rank-sum test, and sign tests. The relative study shows that the outcomes of the proposed algorithm are interesting, especially in the case of clusters of arbitrary shape.

Download Full-text

The Spectrum Segmentation Algorithm of Multimode Vibration Signal Based on Spectral Clustering

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.121-126.2372 ◽

2011 ◽

Vol 121-126 ◽

pp. 2372-2376

Author(s):

Dan Dan Wang ◽

Yu Zhou ◽

Qing Wei Ye ◽

Xiao Dong Wang

Keyword(s):

Wave Packet ◽

Frequency Domain ◽

Spectral Clustering ◽

Clustering Algorithm ◽

Wave Packets ◽

Vibration Signal ◽

Segmentation Algorithm ◽

Frequency Curve ◽

Macroscopic Observation ◽

Spectral Clustering Algorithm

The mode peaks in frequency domain of vibration signal are strongly interfered by strong noise, causing the inaccuracy mode parameters. According to this situation, this paper comes up with the thought of mode-peak segmentation based on the spectral clustering algorithm. First, according to the concept of wave packet, the amplitude-frequency of vibration signal is divided into wave packets. Taking each wave packet as a sample of clustering algorithm, the spectral clustering algorithm is used to classify these wave packets. The amplitude-frequency curve of a mode peak becomes a big wave packet in macroscopic. The experiment to simulation signals indicates that this spectral clustering algorithm could accord with the macroscopic observation of mode segmentation effectively, and has outstanding performance especially in strong noise.

Download Full-text

Research on Spectral Clustering

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.687-691.1350 ◽

2014 ◽

Vol 687-691 ◽

pp. 1350-1353

Author(s):

Li Li Fu ◽

Yong Li Liu ◽

Li Jing Hao

Keyword(s):

Spectral Clustering ◽

Clustering Algorithm ◽

Theoretical Foundation ◽

Clustering Algorithms ◽

Spectral Graph Theory ◽

Graph Partition ◽

Mining Areas ◽

Spectral Graph ◽

Definition Of ◽

Spectral Clustering Algorithm

Spectral clustering algorithm is a kind of clustering algorithm based on spectral graph theory. As spectral clustering has deep theoretical foundation as well as the advantage in dealing with non-convex distribution, it has received much attention in machine learning and data mining areas. The algorithm is easy to implement, and outperforms traditional clustering algorithms such as K-means algorithm. This paper aims to give some intuitions on spectral clustering. We describe different graph partition criteria, the definition of spectral clustering, and clustering steps, etc. Finally, in order to solve the disadvantage of spectral clustering, some improvements are introduced briefly.

Download Full-text