Automated Operational Modal Analysis Based on DBSCAN Clustering

DBSCAN is a density-based clustering algorithm that is especially useful for finding clusters of arbitrary shapes. As opposed to other clustering techniques, like K-means, it does not require the number of clusters to be specified as an input parameter, and it is highly robust to outliers. However, DBSCAN has a worst-case quadratic time complexity, which makes it difficult to handle large dataset sizes. To address this problem, several works have been proposed that exploit the massive parallelism of GPUs in DBSCAN clustering. Nonetheless, none of these works have been experimentally compared against each other. In this paper, we review the existing GPU algorithms for DBSCAN clustering and conduct the first experimental study comparing these GPU algorithms using three real-world datasets to identify the best performing algorithm. Our results show that CUDA-DClust is the best performing GPU algorithm in terms of execution time and memory requirements.

<p>Clustering is an important technique for data analysis and knowledge discovery. In the context of big data, the density-based clustering algorithm faces three challenging problems: unreasonable division of data gridding, poor parameter optimization ability and low efficiency of parallelization. In this study, a density-based clustering algorithm by using improve fruit fly optimization based on MapReduce (MR-DBIFOA) is proposed to tackle these three problems. Firstly, based on KD-Tree, a division strategy (KDG) is proposed to divide the cell of grid adaptively. Secondly, an improve fruit fly optimization algorithm (IFOA) which use the step strategy based on knowledge learn (KLSS) and the clustering criterion function (CFF) is designed. In addition, based on IFOA algorithm, the optimal parameters of local clustering are dynamically selected, which can improve the clustering effect of local clustering. Meanwhile, in order to improve the parallel efficiency, the density-based clustering algorithm using IFOA (MR-QRMEC) are proposed to parallel compute the local clusters of clustering algorithm. Finally, based on QR-Tree and MapReduce, a cluster merging algorithm (MR-QRMEC) is proposed to get the result of clustering algorithm more quickly, which improve the core clusters merging efficiency of density-based clustering algorithm. The experimental results show that the MR-DBIFOA algorithm has better clustering results and performs better parallelization in big data.</p> <p> </p>

We adopt clustering algorithm to improve segmentation accuracy. In this paper, 3D laser scanning platform was built to obtain the spatial 3D point cloud data. And then we extracted the point cloud data for two planar features. K-means algorithm, density-based clustering algorithm and density peak clustering algorithm were employed to split the 3D point cloud of the two planes. After clustering, we compared and analyzed the clustering results of the three clustering algorithms. More importantly, we also found that for peak density clustering, the threshold value is related to its sensitivity to noise points. After fitting the two planes, the verticality of two planes was also calculated. We analyzed the results and summarized the criterion for selecting thresholds.

Frequency stability-based controlled islanding scheme based on clustering algorithm and electrical distance using real-time dynamic criteria from WAMS data

This research thoroughly examines the importance and potential of applying clustering algorithms in the context of human resource management. It is noted that personnel segmentation is a strategic component for companies of any size and industry, as it allows for more effective adaptation of management strategies to the needs and characteristics of different groups of employees. It is emphasized that clustering algorithms can automate the segmentation process, providing objective and consistent results. Various types of clustering algorithms are described in detail, including their principles of operation and application peculiarities in the context of personnel management. In particular, it is highlighted how clustering can be based on different criteria such as skills, professional experience, motivation, and others, and how these clusters can be used to improve hiring processes, career planning, performance evaluation, and personnel development. Successful case examples of implementing clustering algorithms in human resource management practices are also provided, demonstrating their positive impact on company efficiency and strategic development. Finally, the need for further research in this area is emphasized to refine personnel segmentation methodologies and expand their application in various business sectors. This research conducted a cluster analysis of a dataset with marketing data using three different clustering methods: k-means, DBSCAN, and agglomerative clustering. The results of the evaluation showed that DBSCAN demonstrated the best performance both with the full and reduced dataset, indicating its effectiveness in identifying densely populated clusters with irregular distributions of points. In contrast, the k-means method proved to be less effective for data with irregular distributions and outliers. Agglomerative clustering yielded moderate results but was found to be vulnerable to outliers and demanding in terms of computational resources. Overall, the study allows us to conclude on the effectiveness of different clustering methods in identifying data structures in marketing research.

<div class="section abstract"><div class="htmlview paragraph">Driver steering feature clustering aims to understand driver behavior and the decision-making process through the analysis of driver steering data. It seeks to comprehend various steering characteristics exhibited by drivers, providing valuable insights into road safety, driver assistance systems, and traffic management. The primary objective of this study is to thoroughly explore the practical applications of various clustering algorithms in processing driver steering data and to compare their performance and applicability. In this paper, principal component analysis was employed to reduce the dimension of the selected steering feature parameters. Subsequently, K-means, fuzzy C-means, the density-based spatial clustering algorithm, and other algorithms were used for clustering analysis, and finally, the Calinski-Harabasz index was employed to evaluate the clustering results. Furthermore, the driver steering features were categorized into lateral and longitudinal categories. Different clustering algorithms were selected for clustering analysis to assess potential differences between lateral and longitudinal steering features and to determine the applicability of various algorithms for this purpose. In the comparative analysis, we comprehensively evaluate the performance of various algorithms in terms of clustering quality, interpretability, computational efficiency, and applicability. Selecting algorithms suitable for specific tasks and datasets is crucial to enhancing computational efficiency and the quality of clustering results. Through the comparative analysis of the driver steering feature clustering algorithm, a deeper understanding of the steering behavior mode can be obtained, providing support for optimizing the driver assistance system, advancing automatic driving technology, enhancing the driving experience, optimizing traffic management, and ultimately realizing a more intelligent and safer road traffic system.</div></div>

Emergence of modern techniques for scientific data collection has resulted in large scale accumulation of data pertaining to diverse fields. Cluster analysis is one of the major data analysis methods. It is the art of detecting group of similar objects in large data sets without having specified groups by means of explicit features. The problem of detecting clusters is challenging when the clusters are of different size, density and shape. This paper gives a new approach towards density based clustering approach. DBSCAN which is considered a pioneer of density based clustering technique, this paper gives a new move towards detecting clusters that exists within a cluster. Based on various parameters needed for a good clustering the algorithm is evaluated such as number of clusters formed, noise ratio on distance change, time elapsed to form cluster, unclustered instances as well as incorrectly clustered instances.

APSCAN: A parameter free algorithm for clustering

This paper presents a clustering algorithm based on Voronoi diagrams. The algorithm firstly constructs irregular grids in plane by Voronoi diagrams, then assign the points among different grids to different clusters according to the property of the Voronoi diagrams' “the nearest neighbor”. It is able to automatically modify the final clustering number based on the grid points' density, and it can adjust the locations for the Voronoi's seeds by the changes of the centroids, and the final Voronoi cells becomes the clustering result. The algorithm is able to settle down the clustering numbers automatically and also can recognize the low density points automatically. The experiments prove that the algorithm can cluster effectively the data points in plane, and its performance is similar to the X-means algorithm which is improved on the K-means algorithm. It is more effective than the DBSCAN and the OPTICS which are density-based clustering algorithms. The algorithm proved to be obviously more effective while the experimental data is in a larger scale.

A data stream is a continuously arriving sequence of data and clustering data streams requires additional considerations to traditional clustering. A stream is potentially unbounded, data points arrive online and each data point can be examined only once. This imposes limitations on available memory and processing time. Furthermore, streams can be noisy and the number of clusters in the data and their statistical properties can change over time. This paper presents an online, bio-inspired approach to clustering dynamic data streams. The proposed ant colony stream clustering (ACSC) algorithm is a density-based clustering algorithm, whereby clusters are identified as high-density areas of the feature space separated by low-density areas. ACSC identifies clusters as groups of micro-clusters. The tumbling window model is used to read a stream and rough clusters are incrementally formed during a single pass of a window. A stochastic method is employed to find these rough clusters, this is shown to significantly speeding up the algorithm with only a minor cost to performance, as compared to a deterministic approach. The rough clusters are then refined using a method inspired by the observed sorting behavior of ants. Ants pick-up and drop items based on the similarity with the surrounding items. Artificial ants sort clusters by probabilistically picking and dropping micro-clusters based on local density and local similarity. Clusters are summarized using their constituent micro-clusters and these summary statistics are stored offline. Experimental results show that the clustering quality of ACSC is scalable, robust to noise and favorable to leading ant clustering and stream-clustering algorithms. It also requires fewer parameters and less computational time.

Density peaks clustering (DPC) is a density-based clustering algorithm with excellent clustering performance including accuracy, automatically detecting the number of clusters, and identifying center points. However, DPC has some shortcomings to be addressed before it can be widely applied. For example, sensitive predefined parameter is not suitable for manifold datasets, and decision graph easily causes the wrong center points. To address these issues, a new DPC algorithm based on weighted k-nearest neighbors and geodesic distance (DPC-WKNN-GD) is proposed in this article to improve the clustering performance for manifold and non-manifold datasets. The DPC-WKNN-GD introduces the weighted k-nearest neighbors based on Euclidean distance to optimize the local density <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\rho $ </tex-math></inline-formula> . Inspired by DPC-GD, the DPC-WKNN-GD redefines the distance <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> based on geodesic distance. The experimental results on artificial and real-world datasets, including image datasets, show that the DPC-WKNN-GD outperforms the state-of-the-art comparison algorithms on both manifold and non-manifold datasets. In addition, the DPC-WKNN-GD completely overcomes the DPC-GD defect, in which the decision graph displays misleading center points.

A number of clustering algorithms can be employed to find clusters in multivariate data. However, the effectiveness and efficiency of the existing algorithms are limited, since the respective data has high dimension, contain large amount of noise and consist of clusters with arbitrary shapes and densities. In this paper, a new kernel density-based clustering algorithm, called Local Triangular Kernel-based Clustering (LTKC), is proposed to deal with these conditions. LTKC is based on combination of k-nearest-neighbor density estimation and triangular kernel density-based clustering. The advantages of our LTKC approach are: (1) it has a firm mathematical basis; (2) it requires only one parameter, number of neighbors; (3) it defines the number of cluster automatically; (4) it allows discovering clusters with arbitrary shapes and densities ;and (5) it is significantly faster than existing algorithms. LTKC is tested using artificial data and applied to some UCI data. A comparison with k-means, KFCM and well known density-based clustering algorithms including ILGC, DBSCAN, and DENCLUE shows the superiority of our proposed LTKC algorithm.

As a relatively novel density-based clustering algorithm, Density peak clustering (DPC) has been widely studied in recent years. DPC sorts all points in descending order of local density and finds neighbors for each point in turn to assign all points to the appropriate clusters. The algorithm is simple and effective but has some limitations in applicable scenarios. If the density difference between clusters is large or the data distribution is in a nested structure, the clustering effect of this algorithm is poor. This study incorporates the idea of connectivity into the original algorithm and proposes an improved density peak clustering algorithm ConDPC. ConDPC modifies the strategy of obtaining clustering center points and assigning neighbors and improves the clustering accuracy of the original density peak clustering algorithm. In this study, clustering comparison experiments were conducted on synthetic data sets and real-world data sets. The compared algorithms include original DPC, DBSCAN, K-means and two improved algorithms over DPC. The comparison results prove the effectiveness of ConDPC.

Clustering by fast search and detection of density peaks (DPC, Density Peaks Clustering) is a relatively novel clustering algorithm published in the Science journal. As a density-based clustering algorithm, DPC produces better clustering results while using less parameters than other relevant algorithms. However, we found that the DPC algorithm does not perform well if clusters with different densities are very close. To address this problem, we propose a new DPC algorithm by incorporating an improved mutual k-nearest-neighbor graph (Mk-NNG) into DPC. Our Mk-NNG-DPC algorithm leverages the distance matrix of data samples to improve the Mk-NNG, and then utilizes DPC to constrain and select cluster centers. The proposed Mk-NNG-DPC algorithm ensures an instance to be allocated to the fittest cluster. Experimental results on synthetic and real world datasets show that our Mk-NNG-DPC algorithm can effectively and efficiently improve clustering performance, even for clusters with arbitrary shapes.

Protocol Reverse Engineering (PRE) is of great significance to the research of cyber security and it is helpful to understand protocol specifications. There has been many researches on PRE but most of them need additional manual analysis, which is not available for private and unknown protocols. We propose a protocol state analysis and annotation method, which extracts the feature information of binary-based protocol data through an auto-encoder model. Moreover, density-based clustering algorithm is only used to distinguish protocol types in existing studies, we propose an improved algorithm and apply it to protocol state analysis. Finally, we apply alignment algorithm to get state information and do annotation. We run simulation to verify the effectiveness of proposed method and prove its feasibility in private and unknown protocols. The results of clustering algorithms are compared to show the improvement. Then the application of proposed method is summarized based on the simulation results, which provides a novel idea for the protocol analysis.