Self-Adjusting Variable Neighborhood Search Algorithm for Near-Optimal k-Means Clustering

Abstract

The k-means problem is one of the most popular models in cluster analysis that minimizes the sum of the squared distances from clustered objects to the sought cluster centers (centroids). The simplicity of its algorithmic implementation encourages researchers to apply it in a variety of engineering and scientific branches. Nevertheless, the problem is proven to be NP-hard which makes exact algorithms inapplicable for large scale problems, and the simplest and most popular algorithms result in very poor values of the squared distances sum. If a problem must be solved within a limited time with the maximum accuracy, which would be difficult to improve using known methods without increasing computational costs, the variable neighborhood search (VNS) algorithms, which search in randomized neighborhoods formed by the application of greedy agglomerative procedures, are competitive. In this article, we investigate the influence of the most important parameter of such neighborhoods on the computational efficiency and propose a new VNS-based algorithm (solver), implemented on the graphics processing unit (GPU), which adjusts this parameter. Benchmarking on data sets composed of up to millions of objects demonstrates the advantage of the new algorithm in comparison with known local search algorithms, within a fixed time, allowing for online computation.

Study of Mathematical Models of Dynamic Systems

“…However, modern achievements in the field of solving such problems make it possible to apply several methods for problem solving. One or another method implies the need to invest a different volume of resources for problem solving (and in the case of comparing these methods, even at the a priori stage of research, methods that are obviously more or less resource-intensive in relation to other methods can be identified) (Kazakovtsev et al, 2020;Rozhnov et al, 2021). Moreover, it is natural to assert that the choice of a method for problem solving will affect the result of its final solution and the possibility of achieving purposes set by a researcher.…”

A Multiobjective Variable Neighborhood Strategy Adaptive Search to Optimize the Dynamic EMS Location–Allocation Problem

“…Previously, the EMS relocation problem has been integrated with other NP-hard problems, such as the dispatching problem [6] and the vehicle routing problem [7,[20][21][22][23]. The methodology used to solve the EMS and location/relocation problem has included set covering and its extension [24,25], tabu search [4], linear programming [26], variable neighborhood search (VNS) [8,27], hybridization of simulated annealing algorithm and tabu search [5,28], particle swarm optimization [29], and ant colony optimization [7].…”

Entropy Approach in Methods of Electroencephalogram Automatic Analysis

“…The accumulation of large volumes of biomedical data has provided new opportunities for the development of algorithms for automatic data analysis and the creation of high-performance software for their automatic interpretation. Data mining algorithms make it possible to search for and reveal hidden and non-trivial patterns in data and gain new knowledge about the objects under study (Kazakovtsev et al, 2020). Currently, it is impossible to imagine the further development of medical technologies without the use of machine learning technologies.…”