RT Journal Article
T1 Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications
A1 Trujillo, José Antonio
A1 De la Bandera Cascales, Isabel
A1 Burgueño Romero, Jesús
A1 Palacios, David
A1 Baena-Martínez, Eduardo
K1 Aprendizaje automático (Inteligencia artificial)
AB Due to the great complexity, heterogeneity, and variety of services, anomaly detection is becoming an increasingly important challenge in the operation of new generations of mobile communications. In many cases, the underlying relationships between the multiplicity of parameters and factors that can cause anomalous behavior are only determined by human expert knowledge. On the other hand, although automatic algorithms have a great capacity to process multiple sources of information, they are not always able to correctly signal such abnormalities. In this sense, this paper proposes the integration of both components in a framework based on Active Learning that enables enhanced performance in anomaly detection tasks. A series of tests have been conducted using an online anomaly detection algorithm comparing the proposed solution with a method based on the algorithm output alone. The obtained results demonstrate that a hybrid anomaly detection model that automates part of the process and includes the knowledge of an expert following the described methodology yields increased performance.
PB IOAP-MDPI
YR 2022
FD 2022-12-23
LK https://hdl.handle.net/10630/25959
UL https://hdl.handle.net/10630/25959
LA eng
NO Trujillo JA, de-la-Bandera I, Burgueño J, Palacios D, Baena E, Barco R. Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications. Sensors. 2023; 23(1):126. https://doi.org/10.3390/s23010126
NO This project is partially funded by the Junta de Andalucía through the UMA-CEIATECH-11 (DAMA-5G) project. It is also framed in the PENTA Excellence Project (P18-FR-4647) by the Consejería de Transformación Económica, Industria, Conocimiento y Universidades (Regional Ministry of Economic Transformation, Industry, Knowledge and Universities), and in part by the European Union–Next Generation EU within the Framework of the Project “Massive AI for the Open RadIo b5G/6G Network (MAORI)”. Partial funding for open access charge: Universidad de Málaga
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026