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

Xiaowei Gu, Plamen Parvanov Angelov, Ce Zhang, Peter Michael Atkinson

Research output: Contribution to journalArticlepeer-review

46 Citations (SciVal)
26 Downloads (Pure)


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.
Original languageEnglish
Pages (from-to)345-349
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
Issue number3
Early online date05 Feb 2018
Publication statusPublished - 01 Mar 2018
Externally publishedYes


  • Deep learning (DL)
  • fuzzy rules
  • rule-based classifier
  • scene classification


Dive into the research topics of 'A Massively Parallel Deep Rule-Based Ensemble Classifier for Remote Sensing Scenes'. Together they form a unique fingerprint.

Cite this