Estimation of Radial Basis Function Network Centers via Information Forces
The determination of The Radial Basis Function Network centers is an open problem. This work determines the cluster centers by a proposed gradient algorithm, using the information forces acting on each data point. These centers are applied to a Radial Basis Function Network for data classification....
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/24/10/1347 |
_version_ | 1797473457560092672 |
---|---|
author | Edilson Sousa Júnior Antônio Freitas Ricardo Rabelo Welflen Santos |
author_facet | Edilson Sousa Júnior Antônio Freitas Ricardo Rabelo Welflen Santos |
author_sort | Edilson Sousa Júnior |
collection | DOAJ |
description | The determination of The Radial Basis Function Network centers is an open problem. This work determines the cluster centers by a proposed gradient algorithm, using the information forces acting on each data point. These centers are applied to a Radial Basis Function Network for data classification. A threshold is established based on Information Potential to classify the outliers. The proposed algorithms are analysed based on databases considering the number of clusters, overlap of clusters, noise, and unbalance of cluster sizes. Combined, the threshold, and the centers determined by information forces, show good results in comparison to a similar Network with a k-means clustering algorithm. |
first_indexed | 2024-03-09T20:15:43Z |
format | Article |
id | doaj.art-a0f628338094499b89c18fd22aecb354 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-09T20:15:43Z |
publishDate | 2022-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-a0f628338094499b89c18fd22aecb3542023-11-24T00:02:10ZengMDPI AGEntropy1099-43002022-09-012410134710.3390/e24101347Estimation of Radial Basis Function Network Centers via Information ForcesEdilson Sousa Júnior0Antônio Freitas1Ricardo Rabelo2Welflen Santos3Technology Center, Universidade Federal do Piauí, Teresina 64049-550, PI, BrazilTechnology Center, Universidade Federal do Piauí, Teresina 64049-550, PI, BrazilTechnology Center, Universidade Federal do Piauí, Teresina 64049-550, PI, BrazilTechnology Center, Universidade Federal do Piauí, Teresina 64049-550, PI, BrazilThe determination of The Radial Basis Function Network centers is an open problem. This work determines the cluster centers by a proposed gradient algorithm, using the information forces acting on each data point. These centers are applied to a Radial Basis Function Network for data classification. A threshold is established based on Information Potential to classify the outliers. The proposed algorithms are analysed based on databases considering the number of clusters, overlap of clusters, noise, and unbalance of cluster sizes. Combined, the threshold, and the centers determined by information forces, show good results in comparison to a similar Network with a k-means clustering algorithm.https://www.mdpi.com/1099-4300/24/10/1347information theoryEntropyRadial Basis Functions Networksclassificationclustering and outliers |
spellingShingle | Edilson Sousa Júnior Antônio Freitas Ricardo Rabelo Welflen Santos Estimation of Radial Basis Function Network Centers via Information Forces Entropy information theory Entropy Radial Basis Functions Networks classification clustering and outliers |
title | Estimation of Radial Basis Function Network Centers via Information Forces |
title_full | Estimation of Radial Basis Function Network Centers via Information Forces |
title_fullStr | Estimation of Radial Basis Function Network Centers via Information Forces |
title_full_unstemmed | Estimation of Radial Basis Function Network Centers via Information Forces |
title_short | Estimation of Radial Basis Function Network Centers via Information Forces |
title_sort | estimation of radial basis function network centers via information forces |
topic | information theory Entropy Radial Basis Functions Networks classification clustering and outliers |
url | https://www.mdpi.com/1099-4300/24/10/1347 |
work_keys_str_mv | AT edilsonsousajunior estimationofradialbasisfunctionnetworkcentersviainformationforces AT antoniofreitas estimationofradialbasisfunctionnetworkcentersviainformationforces AT ricardorabelo estimationofradialbasisfunctionnetworkcentersviainformationforces AT welflensantos estimationofradialbasisfunctionnetworkcentersviainformationforces |