DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2019-01-16 - Article/Dans un journal avec peer-review - Anglais - page(s)

Patel Warish D., Patel Chirag, Valderrama Carlos , "IoMT based Efficient Vital Signs Monitoring System for Elderly Healthcare Using Neural Network" in International Journal of Research, VIII, I, 239-244, DOI:16.10089.IJR.2018.V8I1.285311.234454

  • Codes CREF : Sciences de l'ingénieur (DI2000), Techniques d'imagerie et traitement d'images (DI2770), Technologies de l'information et de la communication (TIC) (DI4730), Semi-conducteurs (DI2512), Electronique et électrotechnique (DI2411), Instrumentation médicale (DI2760), Conception assistée par ordinateur (DI1247), Electronique générale (DI2510), Electricité (DI1230)
  • Unités de recherche UMONS : Electronique et Microélectronique (F109)
  • Instituts UMONS : Institut de Recherche en Technologies de l’Information et Sciences de l’Informatique (InforTech), Institut NUMEDIART pour les Technologies des Arts Numériques (Numédiart)
  • Centres UMONS : Centre de Recherche en Technologie de l’Information (CRTI)
Texte intégral :

Abstract(s) :

(Anglais) Internet of Things is a new emerging technology by which devices can communicate using the internet. The proposed work, An Efficient Vital Signs Monitoring System for Elderly, states that how to apply Internet of Things in Healthcare using Machine Learning Techniques. Indeed, connecting the Internet of Medical Things (IoMT) to the patient/elderly will be helping Doctors and Caregivers to monitor him or her in real-time around the globe. The IoMT devices will collect Vital Signs data such as body temperature, pulse rate, heartbeats (signals), using ECG (Electrocardiogram) sensor, Temperature sensor, etc. That will be stored in the Cloud System and it will synchronize with the local server. Machine Learning comes to analyze those data to identify health risks and estimate severity in real-time by using its Algorithms. The Proposed System, based on Deep Neural Networks (DNN) and IoMT can differentiate between Normal and Abnormal Heartbeats and classify different Abnormal Rhythms. Such techniques will be very useful for physicians to detect possible health problems and deliver appropriate medical assistance on time to serve elderly in a better way. Keywords —Abnormal Rhythms, ECG, Raspberry Pi 3, IoMT, Heartbeats, Electrocardiogram, Deep Neural Networks, Machine Learning, TensorFlow GPU.

Notes :
  • (Anglais) WEBJournal: http://ijrpublisher.com/CURRENT-ISSUE/
  • (Anglais) WEB: http://ijrpublisher.com/gallery/34-january-822.pdf
Identifiants :
  • DOI : DOI:16.10089.IJR.2018.V8I1.285311.234454

Mots-clés :
  • (Anglais) ECG
  • (Anglais) Machine Learning
  • (Anglais) Deep Neural Networks
  • (Anglais) IoT