Class noise vs. attribute noise: A quantitative study of their impacts

DOI10.1007/s10462-004-0751-8zbMath1069.68587OpenAlexW2034841618MaRDI QIDQ1768897

Xingquan Zhu, Xindong Wu

Publication date: 15 March 2005

Published in: Artificial Intelligence Review (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10462-004-0751-8

zbMATH Keywords

machine learningclass noiseattribute noisenoise impacts

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (20)

Semi-supervised classification method through oversampling and common hidden space ⋮ Robust variable selection for model-based learning in presence of adulteration ⋮ A lightweight data preprocessing strategy with fast contradiction analysis for incremental classifier learning ⋮ A polyhedral conic functions based classification method for noisy data ⋮ A non-intrusive correction algorithm for classification problems with corrupted data ⋮ A statistical testing procedure for validating class labels ⋮ Distance-based directional depth classifiers: a robustness study ⋮ Classification trees with mismeasured responses ⋮ A study on relationship between prediction uncertainty and robustness to noisy data ⋮ A new multi-view multi-label model with privileged information learning ⋮ A robust approach to model-based classification based on trimming and constraints. Semi-supervised learning in presence of outliers and label noise ⋮ Ensemble-based noise detection: noise ranking and visual performance evaluation ⋮ Pointwise probability reinforcements for robust statistical inference ⋮ Belief rule-based classification system: extension of FRBCS in belief functions framework ⋮ The efficiency of logistic regression compared to normal discriminant analysis under class-conditional classification noise ⋮ Feature selection for Bayesian network classifiers using the MDL-FS score ⋮ Anomaly and novelty detection for robust semi-supervised learning ⋮ Belief-based chaotic algorithm for support vector data description ⋮ Core clustering as a tool for tackling noise in cluster labels ⋮ Relating instance hardness to classification performance in a dataset: a visual approach

Uses Software

• UCI-ml
• alr3
• C4.5

Cites Work

• Very simple classification rules perform well on most commonly used datasets
• PRISM: An algorithm for inducing modular rules
• Understanding the crucial role of attribute interaction in data mining
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Class noise vs. attribute noise: A quantitative study of their impacts