Refereed article in conference proceedings (A4)
IoT platform for real-time multichannel ECG monitoring and classification with neural networks
List of Authors: Jose Granados, Tomi Westerlund, Lirong Zheng, Zhuo Zou
Editors: A Min Tjoa, Li-Rong Zheng, Zhuo Zou, Maria Raffai, Li Da Xu, Niina Maarit Novak
Conference name: International Conference on Research and Practical Issues of Enterprise Information Systems
Publisher: Springer Verlag
Publication year: 2018
Journal: Lecture Notes in Business Information Processing
Book title *: Research and Practical Issues of Enterprise Information Systems. 11th IFIP WG 8.9 Working Conference, CONFENIS 2017 Shanghai, China, October 18–20, 2017. Revised Selected Papers
Journal name in source: Lecture Notes in Business Information Processing
Title of series: Lecture Notes in Business Information Processing
Volume number: 310
Start page: 181
End page: 191
ISBN: 978-3-319-94844-7
eISBN: 978-3-319-94845-4
ISSN: 1865-1348
DOI: http://dx.doi.org/10.1007/978-3-319-94845-4_16
Internet of Things (IoT) platforms applied to health promise to offer solutions to the challenges in healthcare systems by providing tools for lowering costs while increasing efficiency in diagnostics and treatment. Many of the works on this topic focus on explaining the concepts and interfaces between different parts of an IoT platform, including the generation of knowledge based on smart sensors gathering bio-signals from the human body which are processed by data mining and more recently, deep neural networks hosted on cloud computing infrastructure. These techniques are designed to serve as useful intelligent companions to healthcare professionals in their practice. In this work we present details about the implementation of an IoT Platform for real-time analysis and management of a network of bio-sensors and gateways, as well as the use of a cloud deep neural network architecture for the classification of ECG data into multiple cardiovascular conditions.