CVNov 25, 2014
Similarity- based approach for outlier detection
arXiv:1411.6850v17 citations
Originality Synthesis-oriented
AI Analysis
This addresses outlier detection for data analysis applications, but appears incremental as it builds on existing similarity concepts.
The paper tackles outlier detection by proposing a similarity-based method that identifies outliers based on an object's proximity to its neighbors, and it demonstrates performance on real datasets.
This paper presents a new approach for detecting outliers by introducing the notion of object's proximity. The main idea is that normal point has similar characteristics with several neighbors. So the point in not an outlier if it has a high degree of proximity and its neighbors are several. The performance of this approach is illustrated through real datasets