Multi-core based Parallel N-path labeling HKM clustering algorithm

An adaptive parallel algorithm for hierarchical clustering based on PRAM model was presented. Performing the data preprocessing depended on ldquo90-10rdquo rule to decrease the numbers of data set, performing the parallel algorithm for creating Euclid Minimum Spanning Trees on absolute graph, performing the algorithm for finding the disjoining strategies and non-collision memory, data set was clustered optimizedly. Data set was clustered on the conditions of non-collision memory, lowest-cost and weakest PRAM-EREW model. N data sets were clustered in O((lambdan) <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> /p) time (0.1leslambdales0.3) performing this algorithm on p processors (1lesplesn/log(n)). The parallel clustering algorithm based on PRAM model is an adaptive non-collision memory parallel hierarchical clustering algorithm. The calculating time will be greatly reduced after original inputing data are effectually preprocessed through improved preprocessing methods of this thesis.

Clustering is one of the basic data mining tasks. Clustering high-dimensional and massive data points is a particularly important task in cluster analysis. But some existing clustering algorithms are merely suitable for small and medium sized datasets. Meanwhile, clustering multi-density datasets is also a very difficult task for some clustering methods. In this paper, to address these issues, we present a novel parallel grid-based clustering algorithm for multi-density datasets, called PGMCLU, based on the idea of data parallelism and merging local clusters. The proposed algorithm uses new measure, called grid compactness, which reflects the degree of tightness between data points within grid. Furthermore, it introduces the notion of grid feature for summarizing the information about grid, and proposes the novel approaches of data partition, local clustering and merging local clusters. Extensive theoretical analysis and experiment results on both real and synthetic datasets show that PGMCLU algorithm is effective and scalable, and has approximately linear speedup.

We present a fast point cloud clustering technique which is suitable for outlier detection, object segmentation and region labeling for large multi-dimensional data sets. The basis is a minimal data structure similar to a kd-tree which enables us to detect connected subsets very fast. The proposed algorithms utilizing this tree structure are parallelizable which further increases the computation speed for very large data sets. The procedures given are a vital part of the data preprocessing. They improve the input data properties for a more reliable computation of surface measures, polygonal meshes and other visualization techniques. In order to show the effectiveness of our techniques we evaluate sets of point clouds from different 3D scanning devices.

A new approach of fast color character extraction was proposed. Clustering algorithm was adopted in our method to differentiate between objective character regions and background regions on the premise that character regions are nearly monochromatic. However, the key point of this approach was how to select suitable elements' features based upon the original image information and character's information; it directly determined extraction results. We brought forward a means for feature selection to resolve clustering's key problem, and proved the means is effective. Furthermore, in order to overcome the non-ignorable computational overhead of clustering, parallel clustering algorithm was designed and realized by CUDA. Experiments illustrated color character could be extracted satisfactorily even if these characters are surrounded by complex background; meanwhile, parallel improved method that executed by assist of GPU was more efficient than former method that executed by CPU only.

Remote sensing big data (RSBD) is generally characterized by huge volumes, diversity, and high dimensionality. Mining hidden information from RSBD for different applications imposes significant computational challenges. Clustering is an important data mining technique widely used in processing and analyzing remote sensing imagery. However, conventional clustering algorithms are designed for relatively small datasets. When applied to problems with RSBD, they are, in general, too slow or inefficient for practical use. In this paper, we proposed a parallel subsampling-based clustering (PARSUC) method for improving the performance of RSBD clustering in terms of both efficiency and accuracy. PARSUC leverages a novel subsampling-based data partitioning (SubDP) method to realize three-step parallel clustering, effectively solving the notable performance bottleneck of the existing parallel clustering algorithms; that is, they must cope with numerous repeated calculations to get a reasonable result. Furthermore, we propose a centroid filtering algorithm (CFA) to eliminate subsampling errors and to guarantee the accuracy of the clustering results. PARSUC was implemented on a Hadoop platform by using the MapReduce parallel model. Experiments conducted on massive remote sensing imageries with different sizes showed that PARSUC (1) provided much better accuracy than conventional remote sensing clustering algorithms in handling larger image data; (2) achieved notable scalability with increased computing nodes added; and (3) spent much less time than the existing parallel clustering algorithm in handling RSBD.

Under the background of big data, network data presents a complex and multi structural feature. In the computer network, clustering is the key feature of big data hiding in heterogeneous network. In a word, the data chain in the network is more compact, and the data link between structures is more evacuation. As an important network data application method and traditional data development tool, clustering algorithm has been widely used in academia and society. Based on this, a parallel clustering algorithm for feature hiding big data in heterogeneous networks is proposed. On the premise of establishing the fuzzy equivalent constraint Association of hidden data, the heterogeneous measurement of mixed data is calculated, and online clustering is realized by reconstructing data structure. The experimental results show that the parallel clustering algorithm designed in this paper can achieve good clustering results in data sets, and can measure the differences between data and classes more accurately and reasonably. The new algorithm overcomes the shortcomings of traditional clustering algorithm which classifies attributes according to the overall size of data set or the dispersion degree within the cluster. Compared with other data clustering algorithms, the algorithm proposed in this paper has higher practicability and higher clustering quality.

Data clustering is the first step for future applications of big data analysis. It is a driving model for Artificial Intelligence and Machine Learning architectures. Processing large volumes of data in faster mode is a big challenge in these applications. which requires fast and efficient algorithms for handling big data. Parallel clustering algorithms are one promising design, which increases the speed of handling such big data. In this paper, a parallel algorithm for clustering a spatial dataset called the P-DBSCAN algorithm is implemented using Hadoop map-reduce framework. This research paper signifies the improvement for data clustering in data analytic applications. The new P-DBSCAN algorithm is executed over generated dataset. The result of this parallel algorithm is compared with existing DBSCAN algorithm to show improvement of runtime performance. This work offers an increase in the performance of execution time. In addition, the outcome of P-DBSCAN shows how to resolve the scalability problem of a large data set.

&lt;p&gt;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.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

In this paper, we present a bottom-up clustering algorithm based on recursive collapsing of small cliques in a graph. The sizes of the small cliques are derived using random graph theory. This clustering algorithm leads to a natural parallel implementation in which multiple processors are used to identify clusters simultaneously. We also present a cluster-based partitioning method in which our clustering algorithm is used as a preprocessing step to both the bisection algorithm by Fiduccia and Mattheyses and a ratio-cut algorithm by Wei and Cheng. Our results show that cluster-based partitioning obtains cut sizes up to 49.6% smaller than the bisection algorithm, and obtains ratio cut sizes up to 66.8% smaller than the ratio-cut algorithm. Moreover, we show that cluster-based partitioning produces much stabler results than direct partitioning.

Parallel squared error clustering on hypercube arrays

In this paper we present a new parallel clustering algorithm based on the extended star clustering method. This algorithm can be used for example to cluster massive data sets of documents on distributed memory multiprocessors. The algorithm exploits the inherent data-parallelism in the extended star clustering algorithm. We implemented our algorithm on a cluster of personal computers connected through a Myrinet network. The code is portable to different architectures and it uses the MPI message-passing library. The experimental results show that the parallel algorithm clearly improves its sequential version with large data sets. We show that the speedup of our algorithm approaches the optimal as the number of objects increases.

The data-classification process can possibly involve a huge amount of data in today's cloud computing environment. It could take a long time for processing, and could consume many resources for computation and storage. This study focuses on the problem of using the traditional hierarchical agglomerative clustering algorithm on a distributed environment since hierarchical agglomerative clustering has high applicability and efficiency. A parallel hierarchical ag-glomerative clustering algorithm is proposed in this study. The proposed algorithm divides the whole computation into several small tasks, distribute the tasks to message-passing processes, and merge the results to form a hierarchical cluster. A threshold is used to reduce the storage requirement during the computation. To evaluate the performance and limitation of our algorithm, this study has conducted several experiments using real astronomical data, the main asteroid belt catalog. The experimental results confirm that the proposed parallel algorithm is efficient.

The density-based applied spatial clustering algorithm is an algorithm based on high-density interconnected regions, which discovers class clusters of arbitrary shapes in noisy data sets and is widely used. However, it suffers from slow computation speed due to large-scale disk I/O and clustering bias due to uneven density class clusters and poor parameter search ability. To address these problems, a parallel density clustering algorithm based on an improved fruit fly optimization algorithm and Spark memory iteration is proposed. The proposed algorithm first divides the data grid using an irregular dynamic density region partitioning strategy. Then, a hybrid fruit fly particle swarm algorithm based on a genetic optimization mechanism is proposed to achieve dynamic optimization seeking for parameters in local clustering to improve the clustering effect of local clustering. Finally, the local merging of samples in irregularly bounded grid cells under each partition is achieved by designing a custom clustering merging strategy. The experiments show that the improved algorithm is generally applicable to the clustering of different shape class clusters and larger scale data and has obvious improvement in accuracy and parallel efficiency.

This paper presents a numerical technique for path planning inside the workspace of parallel manipulators avoiding singularity. A generic numerical algorithm for generating the reachable workspace of parallel manipulators is described. The singularity points are determined inside the workspace. These points are grouped into several clusters and modeled as obstacles. Subsequently, a path planning algorithm is used to find an optimal path avoiding these obstacle. If any singularity point lies on or very close to the path, the path is restructured to avoid the singularity point by a local routing method based on Grassmann's line geometry. The path planning algorithm is uniformly applicable to parallel manipulators with any combinations of revolute and prismatic joints. An example is demonstrated for the effectiveness of the algorithm.

We present a parallel hierarchical graph clustering algorithm that uses modularity as clustering criteria to effectively extract community structures in large graphs of different types. In order to process a large complex graph (whose vertex number and edge number are around 1 billion), we design our algorithm based on the Louvain method by investigating graph partitioning and distribution schemes on distributed memory architectures and conducting clustering in a divide-and-conquer manner. We study the relationship between graph structure property and clustering quality, carefully deal with ghost vertices between graph partitions, and propose a heuristic partition method suitable for the Louvain method. Compared to the existing solutions, our method can achieve nearly well-balanced workload among processors and higher accuracy of graph clustering on real-world large graph datasets.