Evolving ensemble fuzzy classifier

The concept of ensemble learning offers a promising avenue in learning from data streams under complex environments because it better addresses the bias and variance dilemma than its single-model counterpart and features a reconfigurable structure, which is well suited to the given context. While va...

Full description

Saved in:
Bibliographic Details
Main Authors: Pratama, Mahardhika, Pedrycz, Witold, Lughofer, Edwin
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/10356/105667
http://hdl.handle.net/10220/48715
https://doi.org/10.21979/N9/9QM7H6
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-105667
record_format dspace
spelling sg-ntu-dr.10356-1056672021-01-18T04:50:20Z Evolving ensemble fuzzy classifier Pratama, Mahardhika Pedrycz, Witold Lughofer, Edwin School of Computer Science and Engineering Fuzzy Neural Network Evolving Fuzzy Systems DRNTU::Engineering::Computer science and engineering The concept of ensemble learning offers a promising avenue in learning from data streams under complex environments because it better addresses the bias and variance dilemma than its single-model counterpart and features a reconfigurable structure, which is well suited to the given context. While various extensions of ensemble learning for mining nonstationary data streams can be found in the literature, most of them are crafted under static base-classifier and revisit preceding samples in the sliding window for a retraining step. This feature causes computationally prohibitive complexity and is not flexible enough to cope with rapidly changing environments. Their complexities are often demanding because they involve a large collection of offline classifiers due to the absence of structural complexities reduction mechanisms and lack of an online feature selection mechanism. A novel evolving ensemble classifier, namely Parsimonious Ensemble (pENsemble), is proposed in this paper. pENsemble differs from existing architectures in the fact that it is built upon an evolving classifier from data streams, termed Parsimonious Classifier. pENsemble is equipped by an ensemble pruning mechanism, which estimates a localized generalization error of a base classifier. A dynamic online feature selection scenario is integrated into the pENsemble. This method allows for dynamic selection and deselection of input features on the fly. pENsemble adopts a dynamic ensemble structure to output a final classification decision where it features a novel drift detection scenario to grow the ensemble's structure. The efficacy of the pENsemble has been numerically demonstrated through rigorous numerical studies with dynamic and evolving data streams, where it delivers the most encouraging performance in attaining a tradeoff between accuracy and complexity. MOE (Min. of Education, S’pore) Accepted version 2019-06-13T04:24:40Z 2019-12-06T21:55:30Z 2019-06-13T04:24:40Z 2019-12-06T21:55:30Z 2018 Journal Article Pratama, M., Pedrycz, W., & Lughofer, E. (2018). Evolving Ensemble Fuzzy Classifier. IEEE Transactions on Fuzzy Systems, 26(5), 2552-2567. doi:10.1109/TFUZZ.2018.2796099 1063-6706 https://hdl.handle.net/10356/105667 http://hdl.handle.net/10220/48715 10.1109/TFUZZ.2018.2796099 en IEEE Transactions on Fuzzy Systems https://doi.org/10.21979/N9/9QM7H6 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TFUZZ.2018.2796099. 15 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Fuzzy Neural Network
Evolving Fuzzy Systems
DRNTU::Engineering::Computer science and engineering
spellingShingle Fuzzy Neural Network
Evolving Fuzzy Systems
DRNTU::Engineering::Computer science and engineering
Pratama, Mahardhika
Pedrycz, Witold
Lughofer, Edwin
Evolving ensemble fuzzy classifier
description The concept of ensemble learning offers a promising avenue in learning from data streams under complex environments because it better addresses the bias and variance dilemma than its single-model counterpart and features a reconfigurable structure, which is well suited to the given context. While various extensions of ensemble learning for mining nonstationary data streams can be found in the literature, most of them are crafted under static base-classifier and revisit preceding samples in the sliding window for a retraining step. This feature causes computationally prohibitive complexity and is not flexible enough to cope with rapidly changing environments. Their complexities are often demanding because they involve a large collection of offline classifiers due to the absence of structural complexities reduction mechanisms and lack of an online feature selection mechanism. A novel evolving ensemble classifier, namely Parsimonious Ensemble (pENsemble), is proposed in this paper. pENsemble differs from existing architectures in the fact that it is built upon an evolving classifier from data streams, termed Parsimonious Classifier. pENsemble is equipped by an ensemble pruning mechanism, which estimates a localized generalization error of a base classifier. A dynamic online feature selection scenario is integrated into the pENsemble. This method allows for dynamic selection and deselection of input features on the fly. pENsemble adopts a dynamic ensemble structure to output a final classification decision where it features a novel drift detection scenario to grow the ensemble's structure. The efficacy of the pENsemble has been numerically demonstrated through rigorous numerical studies with dynamic and evolving data streams, where it delivers the most encouraging performance in attaining a tradeoff between accuracy and complexity.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Pratama, Mahardhika
Pedrycz, Witold
Lughofer, Edwin
format Article
author Pratama, Mahardhika
Pedrycz, Witold
Lughofer, Edwin
author_sort Pratama, Mahardhika
title Evolving ensemble fuzzy classifier
title_short Evolving ensemble fuzzy classifier
title_full Evolving ensemble fuzzy classifier
title_fullStr Evolving ensemble fuzzy classifier
title_full_unstemmed Evolving ensemble fuzzy classifier
title_sort evolving ensemble fuzzy classifier
publishDate 2019
url https://hdl.handle.net/10356/105667
http://hdl.handle.net/10220/48715
https://doi.org/10.21979/N9/9QM7H6
_version_ 1690658362985807872