EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Toward transparent intelligence: Explainable stacked ensembles learning for LiDAR point cloud segmentation

Afridi Rahman Bondhon iD, Emon Kumar Dey

PLOS One · 20.05.2026 · 21 (5) · e0345125

DOI: 10.1371/journal.pone.0345125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 20.05.2026. Verfasst von Afridi Rahman Bondhon und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Technology, University of Dhaka, Dhaka, Bangladesh. Hauptthemen laut MEDLINE: Machine Learning, Cloud Computing, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Segmentation of LiDAR point cloud data has various applications, ranging from urban planning to environmental monitoring. Although machine learning approaches have achieved impressive segmentation performance, their black-box nature often limits their interpretability. While stacked ensemble learning improves segmentation accuracy by combining multiple classifiers, it further increases model complexity and obscures decision transparency. To address this gap, this study proposes an explainable stacked ensemble framework for LiDAR point cloud segmentation that integrates multiple base learners with Logistic Regression as a meta-model and incorporates model-agnostic Explainable Artificial Intelligence (XAI) techniques. Experimental results on two benchmark datasets demonstrate segmentation accuracies of 91.13% and 95.71%. The study also identifies the most effective base models within the ensemble to facilitate optimal model selection. Furthermore, XAI-driven feature analysis enables effective feature reduction, achieving a minimum 7% reduction in training time while maintaining consistent accuracy. In addition, variants of the SHAP algorithm are employed to investigate the relevance of features and the impact of neighborhood selection strategies on the segmentation performance of each base model. The experimental results demonstrate that the proposed approach achieves competitive segmentation performance while improving interpretability and computational efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningCloud ComputingArtificial IntelligenceAlgorithmsEnsemble LearningLogistic Models

Autor:innen und Institutionen

  • Institute of Information Technology, University of Dhaka, Dhaka, Bangladesh.

ORCID-Profile: Afridi Rahman Bondhon

Zitieren

APA

Bondhon, A. R., & Dey, E. K. (2026). Toward transparent intelligence: Explainable stacked ensembles learning for LiDAR point cloud segmentation. PLOS One, 21(5), e0345125. https://doi.org/10.1371/journal.pone.0345125

Vancouver

Bondhon AR, Dey EK. Toward transparent intelligence: Explainable stacked ensembles learning for LiDAR point cloud segmentation. PLOS One. 2026;21(5):e0345125. doi:10.1371/journal.pone.0345125

BibTeX
@article{Bondhon2026,
  author = {Bondhon, Afridi Rahman and Dey, Emon Kumar},
  title = {Toward transparent intelligence: Explainable stacked ensembles learning for LiDAR point cloud segmentation},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0345125},
  doi = {10.1371/journal.pone.0345125}
}
Kostenlos starten →