Computer Science
2 years ago

New algorithm uncovers hidden anomalies in categorical data for better decision-making.

International Journal of Wireless and Mobile Computing
A hybrid algorithm for mining local outliers in categorical data
Meiling Liu, Mingxuan Huang, Weidong Tang

Paper Summary

Related papers

Theme background image
Computer Science
2 years ago

New algorithm uncovers hidden anomalies in categorical data for better decision-making.

Anomaly Detection
Ecosystem Assessment
Process Fault Detection
1 view
Theme background image
Computer Science
4 years ago

New method reveals why anomalies occur, revolutionizing outlier detection.

Anomaly Detection
Intrusion Detection
Adversarial Robustness
2 views
Theme background image
Computer Science
5 years ago

New method revolutionizes outlier detection in data mining tasks.

Anomaly Detection
Intrusion Detection
Time Series Clustering
2 views

The article presents a new method for finding unusual data points in categorical data. Instead of looking for outliers in the whole dataset, this method focuses on finding outliers within smaller groups. By using a combination of clustering and statistical analysis, the researchers were able to identify clusters with unusual data points and individual data points that stand out. The results from testing this method on real datasets showed that it is accurate and effective in finding local outliers.