Fog computing architectures for healthcare. Wireless performance and semantic opportunities
| Pages | 334-349 |
| Published date | 14 November 2016 |
| Date | 14 November 2016 |
| DOI | https://doi.org/10.1108/JICES-05-2016-0014 |
| Author | Lisardo Prieto González,Corvin Jaedicke,Johannes Schubert,Vladimir Stantchev |
| Subject Matter | Information & knowledge management,Information management & governance,Information & communications technology |
Fog computing architectures
for healthcare
Wireless performance and
semantic opportunities
Lisardo Prieto González
Institute of Information Systems (IIS), SRH Hochschule Berlin, Berlin,
Germany and Computer Science (SEL), Universidad Carlos III de Madrid
Escuela Politecnica Superior, Leganes, Spain, and
Corvin Jaedicke, Johannes Schubert and Vladimir Stantchev
Institute of Information Systems (IIS), SRH Hochschule Berlin, Berlin, Germany
Abstract
Purpose – The purpose of this study is to analyze how embedding of self-powered wireless sensors
into cloud computing further enables such a system to become a sustainable part of work environment.
Design/methodology/approach – This is exemplied by an application scenario in healthcare that
was developed in the context of the OpSIT project in Germany. A clearly outlined three-layer
architecture, in the sense of Internet of Things, is presented. It provides the basis for integrating a broad
range of sensors into smart healthcare infrastructure. More specically, by making use of short-range
communication sensors (sensing layer), gateways which implement data transmission and low-level
computation (fog layer) and cloud computing for processing the data (application layer).
Findings – A technical in-depth analysis of the rst two layers of the infrastructure is given to prove
reliability and to determine the communication quality and availability in real-world scenarios.
Furthermore, two example use-cases that directly apply to a healthcare environment are examined,
concluding with the feasibility of the presented approach.
Practical implications – Finally, the next research steps, oriented towards the semantic tagging and
classication of data received from sensors, and the usage of advanced articial intelligence-based
algorithms on this information to produce useful knowledge, are described together with the derived social
benets.
Originality/value – The work presents an innovative, extensible and scalable system, proven to be
useful in healthcare environments.
Keywords Healthcare, Internet of Things, Cloud computing, Ontologies, Fog computing,
Knowledge representation
Paper type Research paper
1. Introduction
The Internet of Things (IoT) utilizes many different technologies such as radio
frequency identication (RFID), Bluetooth, global positioning system (GPS) and
The preparation of this article has been partially supported by the German Federal Ministry of
Education and Research (BMBF) through project OpSIT – Optimaler Einsatz von
Smart-Items-Technologien in der Stationären Pege (16SV6048).
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1477-996X.htm
JICES
14,4
334
Received 2 May 2016
Revised 29 July 2016
Accepted 17 August 2016
Journalof Information,
Communicationand Ethics in
Society
Vol.14 No. 4, 2016
pp.334-349
©Emerald Group Publishing Limited
1477-996X
DOI 10.1108/JICES-05-2016-0014
short-range communication, thereby connecting everyday objects to the internet and
automating tasks like identication, localization, management and scheduling.
Insofar, smart healthcare forms a subpart of the IoT concept, which is regarded as a
promising tool for data acquisition (Ko et al., 2010) inherently. By introducing the
fog-computing paradigm, we can identify a three-layer architecture (Stantchev et al.,
2015) which is common to IoT: sensors (sensing layer), gateways or fog-devices (fog
layer) and cloud computing (application layer). Fog-computing delegates certain tasks
to the edges of the network (fog devices), thus reducing data ow to and from the cloud
(Bonomi et al., 2012). As a cross-discipline approach, it integrates short-range
communication, microelectronics and embedded systems. However, one of the biggest
constraints in such systems is energy consumption. Rechargeable batteries can solve
this problem, but they also introduce a higher need for maintenance. An alternative is
featured using energy harvesting sensors, which makes the sensor layer self-sustaining.
Cloud computing, as the basis of IoT and smart items, can show immense benets in a
healthcare application (Stantchev et al., 2014). It enables healthcare providers to cure and
care more effectively and prevent illnesses from reaching a critical state by introducing new
ways to manage and monitor patients (Verzijl and Dervojeda, 2015). The World Health
Organization (WHO) found that a majority of patients do not adhere to their medical
prescription, which often results in a failure of their therapy (Sabate, 2003). Consequently,
this gives an immediate scenario, a smart item monitoring the pill intake time.
The project “Optimaler Einsatz von Smart-Items Technologien in der Stationaren
Pege”, Germany (OpSIT), builds on existing works and is conducting literature
research, workshops and expert interviews with healthcare specialists and IT
professionals to model reference processes for practice-oriented cloud applications in the
healthcare domain. Figure 1 shows a general overview of the systems architecture
established throughout the project. Smart items equipped with sensors, or even
actuators, are appropriately placed around patients and the work environment of
caregivers, thus monitoring different vital signs of human health and managing the
work process of caregivers. Gateways collect the data and, if possible, perform low-level
processing, e.g. ltering, aggregation and digitally signing the collected data to provide
a higher security level, compliant with the requirements in the healthcare sector. They
also can interact with each other to provide additional information based on the received
signals, e.g. indoor positioning of emergency attendance buttons, or smart blister
dispensers. From this fog layer, the data are then uploaded and updated to the respective
cloud server, where the data are rened, processed and stored from a high-level
Figure 1.
Fog computing –
architectural layers
as utilized by OpSIT
335
Fog
computing
architectures
To continue reading
Request your trial