Home > Research > Publications & Outputs > A Massively Parallel Deep Rule-Based Ensemble C...

Electronic data

  • RSletter_DRBensemble_final

    Rights statement: ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 683 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

A Massively Parallel Deep Rule-Based Ensemble Classifier for Remote Sensing Scenes

Research output: Contribution to journalJournal article

Published

Standard

A Massively Parallel Deep Rule-Based Ensemble Classifier for Remote Sensing Scenes. / Gu, Xiaowei; Angelov, Plamen Parvanov; Zhang, Ce; Atkinson, Peter Michael.

In: IEEE Geoscience and Remote Sensing Letters, Vol. 15, No. 3, 03.2018, p. 345-349.

Research output: Contribution to journalJournal article

Harvard

APA

Vancouver

Author

Bibtex

@article{89df8a34cfb042e49b12f2504c7449b1,
title = "A Massively Parallel Deep Rule-Based Ensemble Classifier for Remote Sensing Scenes",
abstract = "In this letter, we propose a new approach for remote sensing scene classification by creating an ensemble of the recently introduced massively parallel deep (fuzzy) rule-based (DRB) classifiers trained with different levels of spatial information separately. Each DRB classifier consists of a massively parallel set of human-interpretable, transparent zero-order fuzzy IF...THEN... rules with a prototype-based nature. The DRB classifier can self-organize {"}from scratch{"} and self-evolve its structure. By employing the pretrained deep convolution neural network as the feature descriptor, the proposed DRB ensemble is able to exhibit human-level performance through a transparent and parallelizable training process. Numerical examples using benchmark data set demonstrate the superior accuracy of the proposed approach together with human-interpretable fuzzy rules autonomously generated by the DRB classifier.",
keywords = "Deep learning (DL), fuzzy rules, rule-based classifier, scene classification",
author = "Xiaowei Gu and Angelov, {Plamen Parvanov} and Ce Zhang and Atkinson, {Peter Michael}",
note = "{\circledC}2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",
year = "2018",
month = "3",
doi = "10.1109/LGRS.2017.2787421",
language = "English",
volume = "15",
pages = "345--349",
journal = "IEEE Geoscience and Remote Sensing Letters",
issn = "1545-598X",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",
number = "3",

}

RIS

TY - JOUR

T1 - A Massively Parallel Deep Rule-Based Ensemble Classifier for Remote Sensing Scenes

AU - Gu, Xiaowei

AU - Angelov, Plamen Parvanov

AU - Zhang, Ce

AU - Atkinson, Peter Michael

N1 - ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2018/3

Y1 - 2018/3

N2 - In this letter, we propose a new approach for remote sensing scene classification by creating an ensemble of the recently introduced massively parallel deep (fuzzy) rule-based (DRB) classifiers trained with different levels of spatial information separately. Each DRB classifier consists of a massively parallel set of human-interpretable, transparent zero-order fuzzy IF...THEN... rules with a prototype-based nature. The DRB classifier can self-organize "from scratch" and self-evolve its structure. By employing the pretrained deep convolution neural network as the feature descriptor, the proposed DRB ensemble is able to exhibit human-level performance through a transparent and parallelizable training process. Numerical examples using benchmark data set demonstrate the superior accuracy of the proposed approach together with human-interpretable fuzzy rules autonomously generated by the DRB classifier.

AB - In this letter, we propose a new approach for remote sensing scene classification by creating an ensemble of the recently introduced massively parallel deep (fuzzy) rule-based (DRB) classifiers trained with different levels of spatial information separately. Each DRB classifier consists of a massively parallel set of human-interpretable, transparent zero-order fuzzy IF...THEN... rules with a prototype-based nature. The DRB classifier can self-organize "from scratch" and self-evolve its structure. By employing the pretrained deep convolution neural network as the feature descriptor, the proposed DRB ensemble is able to exhibit human-level performance through a transparent and parallelizable training process. Numerical examples using benchmark data set demonstrate the superior accuracy of the proposed approach together with human-interpretable fuzzy rules autonomously generated by the DRB classifier.

KW - Deep learning (DL)

KW - fuzzy rules

KW - rule-based classifier

KW - scene classification

U2 - 10.1109/LGRS.2017.2787421

DO - 10.1109/LGRS.2017.2787421

M3 - Journal article

VL - 15

SP - 345

EP - 349

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

IS - 3

ER -