A novel classification algorithm to noise data

Authors:
Hong Li;Yu Zong;Kunlun Wang;Buxiao Wu
Affiliations:
Key Laboratory of Network and Intelligent Information Processing, Department of Computer Science and Technology, Hefei University, China;Department of Information and Engineering, West Anhui University, China;Key Laboratory of Network and Intelligent Information Processing, Department of Computer Science and Technology, Hefei University, China;Key Laboratory of Network and Intelligent Information Processing, Department of Computer Science and Technology, Hefei University, China
Venue:
ICSI'12 Proceedings of the Third international conference on Advances in Swarm Intelligence - Volume Part II
Year:
2012

Citing 19
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Discovering informative patterns and data cleaning

Advances in knowledge discovery and data mining
Data quality and systems theory

Communications of the ACM
The impact of poor data quality on the typical enterprise

Communications of the ACM
Data Quality for the Information Age

Data Quality for the Information Age
Correcting Noisy Data

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Experiments with Noise Filtering in a Medical Domain

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Mining with rarity: a unifying framework

ACM SIGKDD Explorations Newsletter - Special issue on learning from imbalanced datasets
The Necessity of Assuring Quality in Software Measurement Data

METRICS '04 Proceedings of the Software Metrics, 10th International Symposium
Class Noise vs. Attribute Noise: A Quantitative Study

Artificial Intelligence Review
Dealing with predictive-but-unpredictable attributes in noisy data sources

PKDD '04 Proceedings of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques
Identifying Noise in an Attribute of Interest

ICMLA '05 Proceedings of the Fourth International Conference on Machine Learning and Applications
The pairwise attribute noise detection algorithm

Knowledge and Information Systems - Special Issue on Mining Low-Quality Data
Enhancing software quality estimation using ensemble-classifier based noise filtering

Intelligent Data Analysis
Error detection and impact-sensitive instance ranking in noisy datasets

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Approximate weighted frequent pattern mining with/without noisy environments

Knowledge-Based Systems
A novel hybrid data mining method based on the RS and BP

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
Mining With Noise Knowledge: Error-Aware Data Mining

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is a significant challenge to discover knowledge from noise data. Most of previous works have focused on the data cleansing and the correction for the benefit of the subsequent mining process. When the training data contains noise, the classification accuracy was being affected dramatically. In this paper, we present a novel classification algorithm named ESC (Error-Sensitive Classification) to cover this problem. We materialize our main idea by constructing Attribute-Decision tree and measuring correlation among attributes. Experimental results show that our algorithm has ability to significantly improve the quality of data mining results.