A confident learning-based support vector machine for robust ground classification in noisy label environments

•A confident learning-based support vector machine is proposed for robust ground classification.•The model recognizes and removes noisy labels by ranking optimized confidence values.•The model still exhibits nearly 90% accuracy and 0.8 credibility under a noise ratio of up to 35%.•A confidence crite...

Full description

Saved in:
Bibliographic Details
Published in:Tunnelling and underground space technology Vol. 155; p. 106128
Main Authors: Zhang, Xin-Yue, Zhang, Xiao-Ping, Yu, Hong-Gan, Liu, Quan-Sheng
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.01.2025
Subjects:
Confident learning
Ground classification
Model robustness
Noisy label
Support vector machine
Model robustness
Noisy label
Confident learning
Support vector machine
Ground classification
ISSN:0886-7798
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A confident learning-based support vector machine is proposed for robust ground classification.•The model recognizes and removes noisy labels by ranking optimized confidence values.•The model still exhibits nearly 90% accuracy and 0.8 credibility under a noise ratio of up to 35%.•A confidence criterion is established to evaluate the classification credibility of individual samples. Geological labels obtained from field exploration have potential errors due to technique limitations and subjective interference, leading to noisy labels when developing ground-machine interaction models for TBM tunneling. The present study proposes a novel confident learning-based support vector machine (CL-SVM) to eliminate label noise, thereby improving the accuracy and credibility of ground classification. The proposed model optimizes confidence values for each label and recognizes those with low confidence values as potential noise. Its effectiveness and superiority are confirmed through a noise test. The results indicate that the maximum acceptable noise ratio of the CL-SVM is 35%, while that of the conventional SVM is only 10%. In addition, the CL-SVM consistently emerges as a superior performer compared to the SVM in noisy label environments. The CL-SVM is further verified through its application on a class-imbalanced dataset collected from a metro tunnel project in Wuhan, China. Here, the accuracy metric F1-score for the most noise-interfered class is significantly improved from 0.7273 to 0.88. To enhance the model’s practical value, a confidence criterion is established to evaluate the credibility of individual predictions, which requires reliable predictions to have higher confidence values than specified thresholds. Without prior knowledge of true sample labels, this criterion distinguishes mispredictions from correct predictions with a remarkable precision of 99.08%. In summary, the proposed CL-SVM exhibits significantly better robustness to noisy labels than conventional models, demonstrating great potential for ground perception in tunnel projects.
ISSN:0886-7798
DOI:10.1016/j.tust.2024.106128