.png){kind=icon}
返回
Outlier detection using local density and global structure
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110947.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Outlier detection, a critical process for enhancing data quality, has been applied to a broad spectrum of real- world applications. This study introduces a novel and effective outlier detection method that incorporates both local density and global structural information. Specifically, we employ the concept of potential energy, a well- established principle in physics, to represent local densities or neighbor distributions of data. Additionally, we also exploit the notion of hubness, a measure explored in network science, to further capture global structural information of data. To facilitate this, we construct a strongly connected digraph by introducing a virtual node along with an associated set of virtual edges. This digraph underpins a tailored Markov random walk process that is used to estimate the hubness scores of data objects. Subsequently, the importance degrees of data objects are estimated according to their potential energies and hubness scores. The data objects with lower importance degrees are deemed to be outliers. Extensive experiments conducted on thirteen publicly accessible real-world datasets against nine popular outlier detection algorithms show that the proposed method achieved encouraging and competitive performance in comparing the state-of-the-art outlier detection algorithms.
Keyword:
Outlier detection
Potential energy
Data density
Data hub
Random walk
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Hyperspectral anomaly detection based on variational background inference and generative adversarial network.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A simple graph embedding for anomaly detection in a stream of heterogeneous labeled graphs用于异构标记图流中异常检测的简单图嵌入PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Local nonlinear dimensionality reduction via preserving the geometric structure of dataPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏
查看更多内容