Cluster center initialization algorithm for K-modes clustering

Abstract

a b s t r a c tPartitional clustering of categorical data is normally performed by using K-modes clustering algorithm, which works well for large datasets. Even though the design and implementation of K-modes algorithm is simple and efficient, it has the pitfall of randomly choosing the initial cluster centers for invoking every new execution that may lead to non-repeatable clustering results. This paper addresses the randomized center initialization problem of K-modes algorithm by proposing a cluster center initialization algorithm. The proposed algorithm performs multiple clustering of the data based on attribute values in different attributes and yields deterministic modes that are to be used as initial cluster centers. In the paper, we propose a new method for selecting the most relevant attributes, namely Prominent attributes, compare it with another existing method to find Significant attributes for unsupervised learning, and perform multiple clustering of data to find initial cluster centers. The proposed algorithm ensures fixed initial cluster centers and thus repeatable clustering results. The worst-case time complexity of the proposed algorithm is log-linear to the number of data objects. We evaluate the proposed algorithm on several categorical datasets and compared it against random initialization and two other initialization methods, and show that the proposed method performs better in terms of accuracy and time complexity. The initial cluster centers computed by the proposed approach are close to the actual cluster centers of the different data we tested, which leads to faster convergence of K-modes clustering algorithm in conjunction to better clustering results.

Comparison of Internal Clustering Validation Indices for Prototype-Based Clustering

“…First, they start with an initial partition of the data, and second, the quality of this partition is improved by a local search algorithm during the search phase. The initial partition can be obtained based on many different principles [4,8], but a common strategy is to use distinct prototypes [9]. Most typically, the globalization of the whole algorithm is based on random initialization with several regenerations [10].…”

“…The initial prototypes should be separated from each other [4,8]. Lately, the K-means++ algorithm [9], where the random initialization is based on a density function favoring distinct prototypes, has become the most popular variant to initialize the K-means-type of an algorithm.…”

An Anomaly Detection Based on Optimization

“…Due to sensitivity of the algorithm to the initial parameters, it is important to ensure K-modes clustering with good initial cluster centers [33]. However, there are still no generally accepted initialization methods for kmeans clustering.…”

Deep Data Anaylizing Application Based on Scale Space Theory in Big Data Environment

“…This section will detail describe the scaling mechanism, namely the theoretical foundation of knowledge scaling [16][17][18][19].…”