Banca de QUALIFICAÇÃO: RENAN MOURA DA SILVA

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : RENAN MOURA DA SILVA
DATE: 27/11/2025
TIME: 13:30
LOCAL: remoto
TITLE:

coustic Anomaly Detection in Data Centers: A Monitoring Framework Based on Low-Cost IoT Devices, Machine Learning, and Alert Systems

KEY WORDS:

data centers, acoustic monitoring, machine learning, sound anomalies, Internet of Things.

PAGES: 69
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

This work presents an acoustic monitoring framework designed for Information Technology (IT) infrastructures, with an emphasis on data centers, aimed at detecting sound anomalies related to failures in critical assets. The proposed approach stands out for being low-cost, non-invasive, and compatible with open monitoring systems, integrating Internet of Things devices, signal processing, machine learning techniques, and alert mechanisms. The methodology involved a systematic mapping of the literature to identify existing approaches and research gaps, followed by the design of a modular architecture composed of capture, audio pre-processing, feature extraction, machine learning application, and integration layers with open-source software. As partial results, the literature mapping, the definition of the architecture, and practical tests validating the framework’s applicability are highlighted.

COMMITTEE MEMBERS:
Presidente - 3139050 - ROGER KREUTZ IMMICH
Interno - 2180207 - ITAMIR DE MORAIS BARROCA FILHO
Externo ao Programa - 1802737 - GIBEON SOARES DE AQUINO JUNIOR - UFRNExterno ao Programa - 1678918 - NELIO ALESSANDRO AZEVEDO CACHO - UFRN