OUTLIER DATA MINING WITH IMPERFECT DATA LABELS

Computer Engineering

Clustering is a technique that group a similar object in a cluster some objects are different .which differently behaves to identify data objects that are markedly different from or inconsistent with the normal set of data is done by the outlier detection. Most existing solutions build a model using normal data and also identify outlier that do not fit represented model very proper. However, in addition to normal data, there also exist some limited negative examples or outliers in many applications that data and information may be corrupted such that the outlier detection data is imperfectly labeled. It creates outlier detection very different than compared to that of traditional ones. To address data with imperfect labels and incorporate limited abnormal example into learning is done by a novel outlier detection approach we are implementing RBF kernel and SVDD for the outlier detection. We are combining these two things and generate a best output for outlier detection.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.