Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/1/126 |
| _version_ | 1827617215433670656 |
|---|---|
| author | José Antonio Trujillo Isabel de-la-Bandera Jesús Burgueño David Palacios Eduardo Baena Raquel Barco |
| author_facet | José Antonio Trujillo Isabel de-la-Bandera Jesús Burgueño David Palacios Eduardo Baena Raquel Barco |
| author_sort | José Antonio Trujillo |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T09:41:42Z |
| format | Article |
| id | doaj.art-6c557d14c21d46fb95ca4a8ef0a10072 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T09:41:42Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6c557d14c21d46fb95ca4a8ef0a100722023-12-02T00:53:29ZengMDPI AGSensors1424-82202022-12-0123112610.3390/s23010126Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile CommunicationsJosé Antonio Trujillo0Isabel de-la-Bandera1Jesús Burgueño2David Palacios3Eduardo Baena4Raquel Barco5Instituto de Telecomunicación (TELMA), Universidad de Málaga, CEI Andalucía TECH E.T.S. Ingeniería de Telecomunicación, Bulevar Louis Pasteur 35, 29010 Málaga, SpainInstituto de Telecomunicación (TELMA), Universidad de Málaga, CEI Andalucía TECH E.T.S. Ingeniería de Telecomunicación, Bulevar Louis Pasteur 35, 29010 Málaga, SpainTupl Spain, Tupl Inc., Campus de Teatinos, 29071 Málaga, SpainTupl Spain, Tupl Inc., Campus de Teatinos, 29071 Málaga, SpainInstituto de Telecomunicación (TELMA), Universidad de Málaga, CEI Andalucía TECH E.T.S. Ingeniería de Telecomunicación, Bulevar Louis Pasteur 35, 29010 Málaga, SpainInstituto de Telecomunicación (TELMA), Universidad de Málaga, CEI Andalucía TECH E.T.S. Ingeniería de Telecomunicación, Bulevar Louis Pasteur 35, 29010 Málaga, SpainDue 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.https://www.mdpi.com/1424-8220/23/1/126active learninganomaly detection5Gmachine learningself-organizing networks |
| spellingShingle | José Antonio Trujillo Isabel de-la-Bandera Jesús Burgueño David Palacios Eduardo Baena Raquel Barco Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications Sensors active learning anomaly detection 5G machine learning self-organizing networks |
| title | Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications |
| title_full | Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications |
| title_fullStr | Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications |
| title_full_unstemmed | Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications |
| title_short | Active Learning Methodology for Expert-Assisted Anomaly Detection in Mobile Communications |
| title_sort | active learning methodology for expert assisted anomaly detection in mobile communications |
| topic | active learning anomaly detection 5G machine learning self-organizing networks |
| url | https://www.mdpi.com/1424-8220/23/1/126 |
| work_keys_str_mv | AT joseantoniotrujillo activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications AT isabeldelabandera activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications AT jesusburgueno activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications AT davidpalacios activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications AT eduardobaena activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications AT raquelbarco activelearningmethodologyforexpertassistedanomalydetectioninmobilecommunications |