{"id":4141,"date":"2024-01-08T10:32:54","date_gmt":"2024-01-08T09:32:54","guid":{"rendered":"https:\/\/ssr.upm.es\/?p=4141"},"modified":"2026-01-16T14:15:58","modified_gmt":"2026-01-16T13:15:58","slug":"leveraging-mobile-crowdsourced-data-anomaly-detection-complex-radio-access-networks","status":"publish","type":"post","link":"https:\/\/ssr.upm.es\/en\/2024\/01\/08\/leveraging-mobile-crowdsourced-data-anomaly-detection-complex-radio-access-networks\/","title":{"rendered":"Leveraging Mobile Crowdsourced Data for Anomaly Detection in Complex Radio Access Networks"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t
Responsable: Zoraida Fr\u00edas\u00a0<\/strong>[zoraida.frias@upm.es<\/a>]<\/div>\n\n\t\t<\/div>\n\t<\/div>\n
<\/span><\/div><\/div><\/div><\/div><\/div>
\n\t
\n\t\t
\n\t\t\t

DATOS TFM:<\/strong>
\nTutores: Zoraida Fr\u00edas y Luis Mendo, Departamento de Se\u00f1ales, Sistemas y Radiocomunicaciones
\nFecha inicio: February 1, 2024
\nRemuneraci\u00f3n: Posibilidad de beca de 700\u20ac\/mes por 20h\/semana
\nRequisitos: Estudiante de M\u00e1ster de un t\u00edtulo oficial de la ETSIT, preferiblemente MUIT.
\nSolicitudes: Enviar CV y expediente acad\u00e9mico a zoraida.frias@upm.es<\/a> antes del 7 de enero de 2024.<\/p>\n

 <\/p>\n

Background:<\/strong>
\nThe evolution of Radio Access Networks (RAN) has led to increased complexity, characterized by the coexistence of multiple technologies, overlapping frequencies, varying cell sizes, and diverse network elements. This poses significant challenges in maintaining an optimal user experience.<\/p>\n

 <\/p>\n

Objectives:<\/strong>
\nThis Master Thesis aims to investigate the feasibility of utilizing mobile crowdsourced data to detect anomalies within the RAN. The study aims to address the challenges posed by the complex RAN architecture by assessing the extent to which mobile crowdsourced measurements can effectively identify and diagnose anomalies.<\/p>\n

 <\/p>\n

Methodology:<\/strong>
\nThis research will employ a quantitative approach, utilizing mobile crowdsourced data collected from diverse RAN environments. The methodology will involve data preprocessing, feature engineering, and anomaly detection algorithms tailored to analyze mobile crowdsourced measurements. Various statistical and machine-learning techniques will be applied to identify irregularities, deviations, or abnormalities within the collected data.<\/p>\n

 <\/p>\n

Expected Outcomes:<\/strong>
\nThe Thesis aims to present empirical findings regarding the potential of mobile crowdsourced data in detecting anomalies within complex RAN environments. The outcomes will contribute to a collaborative research project ongoing with mobile crowdsourced companies and mobile operators.<\/p>\n

 <\/p>\n\n\t\t<\/div>\n\t<\/div>\n<\/div><\/div><\/div><\/div>

<\/span><\/div>