Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ IEEE Accessarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
IEEE Access
Article . 2021 . Peer-reviewed
License: CC BY
Data sources: Crossref
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
IEEE Access
Article
License: CC BY
Data sources: UnpayWall
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
IEEE Access
Article . 2021
Data sources: DOAJ
https://dx.doi.org/10.60692/k0...
Other literature type . 2021
Data sources: Datacite
https://dx.doi.org/10.60692/5h...
Other literature type . 2021
Data sources: Datacite
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

F1-ECAC: Enhanced Evolutionary Clustering Using an Ensemble of Supervised Classifiers

F1 - ECAC: تعزيز التجميع التطوري باستخدام مجموعة من المصنفات الخاضعة للإشراف
Authors: Benjamin Mario Sainz-Tinajero; Andres E. Gutierrez-Rodríguez; Héctor G. Ceballos; Francisco J. Cantú-Ortiz;

F1-ECAC: Enhanced Evolutionary Clustering Using an Ensemble of Supervised Classifiers

Abstract

Le clustering est une technique d'apprentissage non supervisée utilisée dans l'exploration de données pour trouver des groupes présentant une similitude accrue entre les objets, mais pas entre eux. Cependant, l'absence de connaissances a priori sur le critère de clustering optimal, et le fort biais des algorithmes traditionnels vers des clusters avec une forme, une taille ou une densité spécifique, soulèvent le besoin de solutions plus flexibles pour trouver les structures sous-jacentes des données. En tant que solution, le clustering a été modélisé comme un problème d'optimisation utilisant des méta-heuristiques pour générer un espace de recherche afin de favoriser les groupes de tout critère souhaité. F1-ECAC est un algorithme de clustering évolutif avec une fonction objective conçue comme un problème d'apprentissage supervisé, qui évalue la qualité d'une partition en fonction de son degré de généralisation, ou de sa capacité à former un ensemble de classificateurs. Notre algorithme montre une augmentation significative des performances et de l'efficacité par rapport à sa version précédente et est très compétitif par rapport aux algorithmes de clustering de pointe. Les résultats démontrent les avantages de la F1-ECAC en termes d'utilisabilité dans une grande variété de problèmes en raison de son critère de clustering innovant.

El agrupamiento es una técnica de aprendizaje no supervisado utilizada en la minería de datos para encontrar grupos con mayor similitud de objetos dentro de ellos, pero no entre ellos. Sin embargo, la ausencia de conocimiento a priori sobre el criterio de agrupación óptimo y el fuerte sesgo de los algoritmos tradicionales hacia grupos con una forma, tamaño o densidad específicos, plantean la necesidad de soluciones más flexibles para encontrar las estructuras subyacentes de los datos. Como solución, el agrupamiento se ha modelado como un problema de optimización utilizando metaheurísticas para generar un espacio de búsqueda para favorecer grupos de cualquier criterio deseado. F1-ECAC es un algoritmo de agrupamiento evolutivo con una función objetiva diseñada como un problema de aprendizaje supervisado, que evalúa la calidad de una partición en términos de su grado de generalización, o su capacidad para entrenar un conjunto de clasificadores. Nuestro algoritmo muestra un aumento significativo en el rendimiento y la eficiencia con respecto a su versión anterior y es altamente competitivo frente a los algoritmos de clúster de última generación. Los resultados demuestran los beneficios de F1-ECAC en la usabilidad en una amplia variedad de problemas debido a su innovador criterio de agrupación.

Clustering is an unsupervised learning technique used in data mining for finding groups with increased object similarity within but not between them. However, the absence of a-priori knowledge on the optimal clustering criterion, and the strong bias of traditional algorithms towards clusters with a specific shape, size, or density, raise the need for more flexible solutions to find the underlying structures of the data. As a solution, clustering has been modeled as an optimization problem using meta-heuristics for generating a search space to favor groups of any desired criterion. F1-ECAC is an evolutionary clustering algorithm with an objective function designed as a supervised learning problem, which evaluates the quality of a partition in terms of its generalization degree, or its capability to train an ensemble of classifiers. Our algorithm shows a significant increase in performance and efficiency to its previous version and is highly competitive to state-of-the-art clustering algorithms. The results demonstrate F1-ECAC's benefits in usability in a wide variety of problems due to its innovative clustering criterion.

التجميع العنقودي هو تقنية تعلم غير خاضعة للإشراف تستخدم في استخراج البيانات للعثور على مجموعات ذات تشابه متزايد في الأشياء داخلها ولكن ليس بينها. ومع ذلك، فإن عدم وجود معرفة مسبقة بمعيار التجميع الأمثل، والتحيز القوي للخوارزميات التقليدية نحو المجموعات ذات الشكل أو الحجم أو الكثافة المحددة، يزيد من الحاجة إلى حلول أكثر مرونة للعثور على الهياكل الأساسية للبيانات. كحل، تم نمذجة التجميع العنقودي كمشكلة تحسين باستخدام الاستدلال التلوي لإنشاء مساحة بحث لتفضيل مجموعات من أي معيار مرغوب فيه. F1 - ECAC هي خوارزمية تجميع تطورية ذات وظيفة موضوعية مصممة كمشكلة تعلم خاضعة للإشراف، والتي تقيم جودة القسم من حيث درجة تعميمه، أو قدرته على تدريب مجموعة من المصنفات. تظهر خوارزميتنا زيادة كبيرة في الأداء والكفاءة إلى إصدارها السابق وهي ذات قدرة تنافسية عالية على خوارزميات التجميع الحديثة. تُظهر النتائج فوائد F1 - ECAC في قابلية الاستخدام في مجموعة واسعة من المشكلات بسبب معيار التجميع المبتكر.

Keywords

Cluster Validation, Artificial intelligence, Data stream clustering, Pattern recognition (psychology), Unsupervised learning, classifier ensembles, evolutionary clustering, Clustering Algorithms, Constrained clustering, Cluster analysis, Artificial Intelligence, Document Clustering, Machine learning, FOS: Mathematics, Swarm Intelligence Optimization Algorithms, CURE data clustering algorithm, Canopy clustering algorithm, Data mining, Data Clustering Techniques and Algorithms, Fuzzy clustering, Correlation clustering, Semi-supervised Clustering, Computer science, TK1-9971, Application of Genetic Programming in Machine Learning, Computer Science, Physical Sciences, Electrical engineering. Electronics. Nuclear engineering, optimization, Density-based Clustering, Mathematics, clustering

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold