摘要

Outlier mining is one of the main research contents in data mining and it has been widely applied in many fields. Most existed outlier mining algorithms depend on several beforehand parameters or thresholds which increase human impact. A new outlier mining algorithm based on Gini index is presented in the paper. The algorithm automatically detects outliers by adopting revised Gini index as outlier measure factor of each object. The experimental results validate the feasibility and efficiency of the algorithm by adopting the spectrum as data sets.

  • 出版日期2013

全文