Title: Efficient Algorithms for Local Density Based Anomaly Detection
Abstract: Anomaly detection is a crucial problem in the field of data mining. However, prevailing anomaly detection algorithms are serial in nature which fail to handle huge volume of data. In this paper, we propose two parallel local density based algorithms namely, MapReduce based Local Outlier Factor (MRLOF) and Spark based Local Outlier Factor (SLOF). The proposed algorithms have time complexity of O(N) for each. This is an improvement over the Simplified LOF (Local Outlier Factor) which has time complexity of $$ O(\textit{N}^{2}) $$ , where N is the data size. We conducted extensive experiments with MRLOF and SLOF on various real life and synthetic datasets. The proposed algorithms are shown to outperform the serial Simplified LOF.
Publication Year: 2017
Publication Date: 2017-11-28
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
Cited By Count: 3
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot