A new hybridization of DBSCAN and fuzzy earthworm optimization algorithm for data cube clustering
- PDF / 3,672,024 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 63 Downloads / 187 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
A new hybridization of DBSCAN and fuzzy earthworm optimization algorithm for data cube clustering Mina Hosseini Rad1 • Majid Abdolrazzagh-Nezhad2
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Data aggregation from different databases into a data warehouse creates multidimensional data such as data cubes. With regard to the 3D structure of data, data cube clustering has significant challenges to perform on data cube. In this paper, new preprocessing techniques and a novel hybridization of DBSCAN and fuzzy earthworm optimization algorithm (EWOA) are proposed to solve the challenges. Proposed preprocessing consists of an assigned address to each cube cell and dimension move to create a related 2D data from the data cube and new similarity metric. The DBSCAN algorithm, as a density-based clustering algorithm, is adopted based on both Euclidean and newly proposed similarity metric, which are called DBSCAN1 and DBSCAN2 for the related 2D data. A new hybridization of the EWOA and DBSCAN is proposed to improve the DBSCAN, and it is called EWOA–DBSCAN. Also, to dynamically tune parameters of EWOA, a fuzzy logic controller is designed with two fuzzy group rules of Mamdani (EWOA–DBSCAN-Mamdani) and Sugeno (EWOA– DBSCAN-Sugeno), separately. These ideas are proposed to present efficient and flexible unsupervised analysis for a data cube by utilizing a meta-heuristic algorithm to optimize DBSCAN’s parameters and increasing the efficiency of the idea by applying dynamic tuning parameters of the algorithm. To evaluate the efficiency, the proposed algorithms are compared with DBSCAN1 and GA-DBSCAN1, GA-DBSCAN1-Mamdani and GA-DBSCAN1-Sugeno. The experimental results, consisting of 20 runs, indicate that the proposed ideas achieved their targets. Keywords Data cube Dimension move DBSCAN clustering Fuzzy logic controller Dynamic tuning parameters Earthworm optimization algorithm
1 Introduction There is a natural requirement for the effective methods for accessing data and extracting useful knowledge, with regard to the increasing expansion of data on different storage media. Data mining consists of the most effective methods in this field. The data mining is an iterative process in order to make the discovery of knowledge which is
Communicated by V. Loia. & Majid Abdolrazzagh-Nezhad [email protected] Mina Hosseini Rad [email protected] 1
Department of Computer Engineering, Birjand Branch, Islamic Azad University, Birjand, Iran
2
Department of Computer Engineering, Faculty of Engineering, Bozorgmehr University of Qaenat, Qaen, Iran
done manually and automatically. The data mining searches valuable and new information from the huge volume of data (Gnanapriya et al. 2010). Description and prediction are the main aims of the data mining. In the first category, data attributes are described in a dataset and its focus is about finding patterns from the dataset so that the found patterns can be described by h
Data Loading...
