Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Probabilistic quantum clustering

Casaña-Eslava, RV, Lisboa, P, Ortega-Martorell, S, Jarman, I and Martin-Guerrera, J (2020) Probabilistic quantum clustering. Knowledge-Based Systems. ISSN 0950-7051

[img] Text
Probabilistic Quantum Clustering.pdf - Accepted Version
Restricted to Repository staff only until 24 January 2021.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB)

Abstract

Quantum Clustering is a powerful method to detect clusters with complex shapes. However, it is very sensitive to a length parameter that controls the shape of the Gaussian kernel associated with a wave function, which is employed in the Schrödinger equation with the role of a density estimator. In addition, linking data points into clusters requires local estimates of covariance which requires further parameters. This paper proposes a Bayesian framework that provides an objective measure of goodness-of-fit to the data, to optimise the adjustable parameters. This also quantifies the probabilities of cluster membership, thus partitioning the data into a specific number of clusters, where each cluster probability is estimated through an aggregated density function composed of the data samples that generate the cluster, having each cluster an associated probability density function P(K|X); this probability can be used as a measure of how well the clusters fit the data. Another main contribution of the work is the adaptation of the Schrödinger equation to deal with local length parameters for cluster discrimination by density. The proposed framework is tested on real and synthetic data sets, assessing its validity by measuring concordance with the Jaccard score.

Item Type: Article
Uncontrolled Keywords: 08 Information and Computing Sciences, 15 Commerce, Management, Tourism and Services, 17 Psychology and Cognitive Sciences
Subjects: Q Science > QA Mathematics
Divisions: Applied Mathematics
Publisher: Elsevier
Date Deposited: 29 Jan 2020 10:20
Last Modified: 29 Jan 2020 10:30
DOI or Identification number: 10.1016/j.knosys.2020.105567
URI: http://researchonline.ljmu.ac.uk/id/eprint/12131

Actions (login required)

View Item View Item