Visually Interpretable Fuzzy Neural Classification Network With Deep Convolutional Feature Maps
IEEE Transactions on Fuzzy Systems · 2024-03 · 32 (3) · 1063-1077
DOI: 10.1109/tfuzz.2023.3318086 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Fuzzy Systems, 2024-03. Verfasst von Chia-Feng Juang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Science and Technology Council.
Abstract (Originalsprache)
This article proposes a deep feature map-based fuzzy neural classification network (DFM-FNCN) with applications to shape-based classification problems. The DFM-FNCN is characterized by compact and visually interpretable fuzzy if-then rules. Classification features in the DFM-FNCN are obtained from feature maps in a deep convolutional neural network. The DFM-FNCN employs the divide-and-conquer technique, where a feature map-based fuzzification operation is proposed to find the firing strength of a fuzzy rule, to address the curse of dimensionality problem. The structure and parameters of the DFM-FNCN are learned through online rule generation and gradient descent algorithms, respectively. For visual interpretation of the learned fuzzy rules, this article designs a deep decoder to map the antecedent of a fuzzy rule to an object-shaped image. The inference behavior of a fuzzy rule is interpreted by inspecting the relationship between the visualized antecedent and the classification levels of each class in the consequent. To speed up retraining of the DFM-FNCN in a new scenario, this article proposes a method to select representative retraining images in a low-dimensional fuzzy rule-mapped space. The DFM-FNCN is applied to classify human postures and moving objects. Experimental results show the advantages of high classification accuracy, model interpretability, and retraining abilities of the DFM-FNCN.
Förderung
- National Science and Technology Council
Zitieren
APA
Juang, C., Cheng, Y., & Lin, Y. (2024). Visually Interpretable Fuzzy Neural Classification Network With Deep Convolutional Feature Maps. IEEE Transactions on Fuzzy Systems, 32(3), 1063-1077. https://doi.org/10.1109/tfuzz.2023.3318086
Vancouver
Juang C, Cheng Y, Lin Y. Visually Interpretable Fuzzy Neural Classification Network With Deep Convolutional Feature Maps. IEEE Transactions on Fuzzy Systems. 2024;32(3):1063-1077. doi:10.1109/tfuzz.2023.3318086
BibTeX
@article{Juang2024,
author = {Juang, Chia-Feng and Cheng, Yun-Wei and Lin, Yeh-Ming},
title = {Visually Interpretable Fuzzy Neural Classification Network With Deep Convolutional Feature Maps},
journal = {IEEE Transactions on Fuzzy Systems},
year = {2024},
volume = {32},
number = {3},
pages = {1063--1077},
doi = {10.1109/tfuzz.2023.3318086}
}
EUVIMED