A Novel DBSCAN Based on Binary Local Sensitive Hashing and Binary-KNN Representation. (7th December 2017)

• Record Type: Journal Article
• Authors: He, Qing; Gu, Hai Xia; Wei, Qin; Wang, Xu
• Other Names: Shen Fumin Academic Editor.
• Is Part Of: Advances in multimedia. Volume 2017(2017)
• Publication Date: 2017-12-07
• Subjects: Multimedia systems -- Periodicals; Computer networks -- Periodicals; Multimédia; Réseaux d'ordinateurs; Computer networks; Multimedia systems; Periodicals; 006.7
• DOI: 10.1155/2017/3695323
• Languages: English
• ISSNs: 1687-5680

Abstract

Abstract : We revisit the classic DBSCAN algorithm by proposing a series of strategies to improve its robustness to various densities and its efficiency. Unlike the original DBSCAN, we first use the binary local sensitive hashing (LSH) which enables faster region query for thek neighbors of a data point. The binary data representation method based onk neighborhood is then proposed to map the dataset into the Hamming space for faster cluster expansion. We define a core point based on binary influence space to enhance the robustness to various densities. Also, we propose a seed point selection method, which is based on influence space andk neighborhood similarity, to select some seed points instead of all the neighborhood during cluster expansion. Consequently, the number of region queries can be decreased. The experimental results show that the improved algorithm can greatly improve the clustering speed under the premise of ensuring better algorithm clustering accuracy, especially for large-scale datasets.