Clustering, which explores the visualization and distribution of data, has recently been studied widely. Although the existing clustering algorithms can well detect arbitrary shape clusters, most of them face the limitation that they cluster points on the basis of two physical metrics, distance and density, but ignore the orientation relationship of data distribution. Beside, they have a difficulty of selecting suitable parameters, which are important inputs of the clustering algorithms. In this paper, we firstly introduce a new physical metric, namely direction. Then, based on this new metric, we propose an adaptive direction-based clustering algorithm, namely ADC, which can automatically calculate appropriate parameters. Finally, we develop a parallel ADC algorithm based on multi-processors to improve the performance of the ADC algorithm. Compared with other clustering algorithms, experimental results demonstrate that the proposed algorithms are more general and can get much better clustering results. In addition, the parallel ADC algorithm has the best scalability over large data sets.

探索数据可视化和分布的聚类最近已得到广泛研究。尽管现有的聚类算法可以很好地检测任意形状的聚类，但是大多数聚类算法都面临着以下限制：它们基于距离和密度这两个物理指标对点进行聚类，但忽略了数据分布的方向关系。另外，它们难以选择合适的参数，这是聚类算法的重要输入。在本文中，我们首先介绍一种新的物理指标，即方向。然后，基于这一新指标，我们提出了一种自适应的基于方向的聚类算法，即ADC，可以自动计算适当的参数。最后，我们开发了一种基于多处理器的并行ADC算法，以提高ADC算法的性能。与其他聚类算法相比，实验结果表明，所提算法更加通用，可以得到更好的聚类结果。此外，并行ADC算法在大型数据集上具有最佳的可扩展性。