What type of study is this?

September 10, 2025SensorsOpen Access

Leakage Detection in Subway Tunnels Using 3D Point Cloud Data: Integrating Intensity and Geometric Features with XGBoost Classifier

View Full Paper

Ask AI

Bookmark

Authors

AZA Ying Zhang JHJunjun HuangHohai University ZSZexin SunZhejiang International Studies University

Discussion

Member takes

Implication

This study demonstrates improved leakage detection accuracy in subway tunnels by integrating geometric and intensity features with XGBoost, highlighting its efficiency.

Key Points

Integration of geometric features improved leakage detection accuracy, achieving an F1-score of 91.18%.
Experimental results show robust classification performance across four diverse datasets with an F1-score of 97.84%.
Applying the RANSAC algorithm effectively filtered out noise, thus improving initial separation of leakage regions.
XGBoost outperformed multiple classifiers, offering a superior balance of accuracy and computational efficiency.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68c1a40254b1d3bfb60de356 https://doi.org/10.3390/s25144475

View Full Paper

Ask AI

Bookmark

Implication

This study demonstrates improved leakage detection accuracy in subway tunnels by integrating geometric and intensity features with XGBoost, highlighting its efficiency.

Leakage Detection in Subway Tunnels Using 3D Point Cloud Data: Integrating Intensity and Geometric Features with XGBoost Classifier

Discussion

Member takes

Implication

Key Points

Cite This Study

Leakage Detection in Subway Tunnels Using 3D Point Cloud Data: Integrating Intensity and Geometric Features with XGBoost Classifier

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider