News

Banca de DEFESA: PAULO TADEU RESQUE DE SOUZA

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
DISCENTE: PAULO TADEU RESQUE DE SOUZA
DATA: 30/11/2020
HORA: 09:00
LOCAL: online
TÍTULO:

A Machine Learning Framework to detect epileptic seizures and prioritize data transmission in Internet of Medical Things


PALAVRAS-CHAVES:

Wearable Devices; Machine Learning; Communication


PÁGINAS: 52
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Ciência da Computação
SUBÁREA: Sistemas de Computação
ESPECIALIDADE: Teleinformática
RESUMO:

New technologies come on stage every day, and the technological advances en-hance the user’s experience. In this context, wearable devices are an emerging technologythat delivers better user experience in many daily activities. In the healthcare indus-try, the Internet of Medical Things (IoMT) relies on wearable devices to sense, collect,and continuously transmit the patient’s physiological information to a medical crew. Inthis scenario, chronic patients, such as people with epilepsy, are continuously monitoredoutside hospital premises. However, medical diagnosis and treatment for syndromes likeepilepsy require data availability, transmission reliability, low network latency, and fastdetection procedure. Thus, epileptic seizure detection in-device or on the edge nodes us-ing Machine Learning (ML) algorithms fulfill such requirements. Furthermore, ML in thecontext of the wireless network provides traffic type awareness and prioritization, enhanc-ing the Quality of Service (QoS) for IoMT application. In this thesis, we propose an MLframework to identify a physiological traffic flow, proceed with a clinical diagnostic on anedge node, and prioritize the data transmission in a Wireless Fidelity (WiFi) network toa hospital cloud server. Our proposal achieve 91.57% accuracy in detecting and assigninga priority tag to a physiological stream, 97.76% accuracy in detecting epileptic seizuresfrom Electroencephalography (EEG) signal, and 60% improvement in Packet DeliveryRate (PDR) for physiological data transmission in a WiFi.


MEMBROS DA BANCA:
Presidente - 2244893 - DENIS LIMA DO ROSÁRIO
Interno - 1700540 - EDUARDO COELHO CERQUEIRA
Externo ao Programa - 1085349 - ANDRE FIGUEIRA RIKER
Externo ao Programa - 3138738 - HELDER MAY NUNES DA SILVA OLIVEIRA
Externo à Instituição - THAIS LIRA TAVARES DOS SANTOS
Notícia cadastrada em: 27/11/2020 13:18
SIGAA | Centro de Tecnologia da Informação e Comunicação (CTIC) - (91)3201-7793 | Copyright © 2006-2024 - UFPA - morango.ufpa.br.morango2