FEMa-FS: Finite Element Machines for Feature Selection

• Published in: 2022 26th International Conference on Pattern Recognition (ICPR) pp. 1784 - 1791
• Main Authors: Biaggi, Lucas, Papa, Joao P., Costa, Kelton A. P, Pereira, Danillo R., Passos, Leandro A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21-08-2022
• Subjects: Anomaly detection; Computer networks; Computer Networks Security; Feature extraction; Feature Selection; Finite element analysis; Finite Element Method; Learning systems; Machine Learning; Pattern recognition; Security
• ISSN: 2831-7475
• DOI: 10.1109/ICPR56361.2022.9956112

Identifying anomalies has become one of the primary strategies towards security and protection procedures in computer networks. In this context, machine learning-based methods emerge as an elegant solution to identify such scenarios and learn irrelevant information so that a reduction in the identification time and possible gain in accuracy can be obtained. This paper proposes a novel feature selection approach called Finite Element Machines for Feature Selection (FEMa-FS), which uses the framework of finite elements to identify the most relevant information from a given dataset. Although FEMa-FS can be applied to any application domain, it has been evaluated in the context of anomaly detection in computer networks. The outcomes over two datasets showed promising results.