Exploiting smart e-Health gateways at the edge of healthcare Internet-of-Things: A fog computing approach

https://doi.org/10.1016/j.future.2017.02.014Get rights and content

Abstract

Current developments in ICTs such as in Internet-of-Things (IoT) and Cyber–Physical Systems (CPS) allow us to develop healthcare solutions with more intelligent and prediction capabilities both for daily life (home/office) and in-hospitals. In most of IoT-based healthcare systems, especially at smart homes or hospitals, a bridging point (i.e., gateway) is needed between sensor infrastructure network and the Internet. The gateway at the edge of the network often just performs basic functions such as translating between the protocols used in the Internet and sensor networks. These gateways have beneficial knowledge and constructive control over both the sensor network and the data to be transmitted through the Internet. In this paper, we exploit the strategic position of such gateways at the edge of the network to offer several higher-level services such as local storage, real-time local data processing, embedded data mining, etc., presenting thus a Smart e-Health Gateway. We then propose to exploit the concept of Fog Computing in Healthcare IoT systems by forming a Geo-distributed intermediary layer of intelligence between sensor nodes and Cloud. By taking responsibility for handling some burdens of the sensor network and a remote healthcare center, our Fog-assisted system architecture can cope with many challenges in ubiquitous healthcare systems such as mobility, energy efficiency, scalability, and reliability issues. A successful implementation of Smart e-Health Gateways can enable massive deployment of ubiquitous health monitoring systems especially in clinical environments. We also present a prototype of a Smart e-Health Gateway called UT-GATE where some of the discussed higher-level features have been implemented. We also implement an IoT-based Early Warning Score (EWS) health monitoring to practically show the efficiency and relevance of our system on addressing a medical case study. Our proof-of-concept design demonstrates an IoT-based health monitoring system with enhanced overall system intelligence, energy efficiency, mobility, performance, interoperability, security, and reliability.

Introduction

Internet of Things (IoT) is getting a wide acceptance and a growing adoption in many aspects of our daily life [1], [2]. IoT technology provides a competent and structured approach to improve health and wellbeing of mankind. It is predicted that IoT-based systems will remodel the healthcare sector in terms of social benefits and penetration as well as cost-efficiency [3], [4]. Due to the ubiquitous computing nature of IoT, all the healthcare system entities (individuals, appliances, medicine) can be monitored and managed continuously. By applying IoT technologies to healthcare, the quality and cost of medical care can be improved by automating tasks previously performed by humans [5], [6], [7]. In that sense, IoT enables Electronic Health (eHealth), Mobile Health (mHealth) and Ambient Assisted Living (AAL) that allow remote monitoring and tracking of patients living alone at home or treated in hospitals, and creates a continuum among these through cloud access [4], [8].

It is no longer sufficient enough to design just standalone wearable devices, instead it becomes vital to create a complete ecosystem in which sensors in a body area network seamlessly synchronize data to cloud services through the IoT infrastructure [9], [10], [11]. The architectural elements generally needed in healthcare IoT systems (Health-IoT) are illustrated in Fig. 1. The architecture includes three main components: (i) body area sensor network, (ii) Internet-connected gateways, and (iii) cloud and big data support. Various applications provide services to different stakeholders in the system through this platform. Data generated from sensors attached to users is made available to caregivers, family members and authorized parties giving them the ability to check the subject’s vital signs from anywhere at any time.

According to predictions, the current hospital-centered healthcare systems will evolve first to hospital–home-balanced in 2020, and then ultimately to home-centered in 2030 [12]. In order to realize such evolution, new system architectures, technologies, and computing paradigms are required, particularly in the smart spaces and e-Health domains. It should be noted that the paradigm shift towards smart ubiquitous healthcare systems results in new challenges to manifest themselves in fulfilling different system requirements such as reliability, interoperability, energy-efficiency, low-latency response, mobility, security, etc.

Gateways generally act as a hub between a sensor layer and cloud services. With an in-depth observation of a gateway’s role in a smart home/hospital, where the mobility and location of users and things are confined to the hospital premises or the building, it can be noticed that the stationary nature of gateways empowers them with the luxury of being non-resource constrained in terms of processing power, power consumption and communication bandwidth. Such a valuable characteristics can be exploited by reinforcing the gateways with sufficient processing power, intelligence, and orchestrated networking capabilities, thus becoming a smart e-Health gateway.

However, the advantageous services that can be potentially offered by a smart gateway will be limited if the gateway is deployed in a standalone and independent fashion. Scalability and mobility issues can easily arise and the efficacy of the solution will be significantly limited. This reveals the demand for an intermediary layer of computation where a geo-distributed network of smart gateways provides intelligence at the edge of the network and facilitates the interplay between sensors layer and cloud layer. This paradigm, which is also called fog or edge computing [13], [14], [15], enables the system to support seamless mobility, load balancing, efficient scalability, low-latency response, and developing applications utilizing services offered by multiple sensors and gateways, just to mention a few.

In this paper, which is a major extension of our recent works published in [16], we present a fog computing-based solution to enhance different characteristics of IoT architectures used for healthcare applications in terms of energy-efficiency, performance, reliability, interoperability, to name a few. The main contributions of this article are as follows:

  • Presenting a practical solution to take advantage of fog computing in IoT-health systems.

  • Elaborating the features of a fog computing based health-IoT system and its services from different perspectives.

  • Proposing fog-based mobility support to enable seamless connectivity for mobile sensors.

  • Providing a proof of concept full-system implementation from development of cloud services to hardware–software demonstration of our prototype of Smart e-Health Gateways.

  • Demonstrating the system with a medical case study called Early Warning Scores (EWS) with hierarchical fog-assisted cloud computing.

The rest of the paper is organized as follows: In Section 2, related work and motivation of this paper are presented. Section 3 describes the architecture of a fog-assisted IoT based e-Health platform using Smart e-Health Gateways. The properties and features of the networked smart e-Health gateways are presented in more detail in Section 4. Demonstration of our Smart e-Health Gateways on a medical case study along with experimental results are provided and discussed in Section 5. Finally, Section 6 concludes the paper.

Section snippets

Related work and motivation

In the healthcare context, designing an efficient IoT-based system is a challenging task due to the following main issues. First, the chosen sensor networking technology must be resource-efficient and customized for e-Health applications. Medical sensor nodes, especially implanted ones, have much lower processing power, memory, transmission speed, and energy supply than sensors in other sensor networks domain. Second, unlike common sensor networks where interval-based data transmission is used

System architecture and the role of fog computing

The large scale implementation of IoT is expected to introduce billions of additional resource-constrained devices connected to the Internet. The majority of these devices, for example wearable and implantable medical sensors, are not capable of storing data they generate. A straightforward design approach is to transfer this data to a cloud for processing. Given the large number of connected devices, the latency of the connection with the cloud could be significant. Moreover, these devices are

Properties and features of smart e-Health gateways at the fog layer

As mentioned before, the main role of a gateway is to support various wireless protocols and take care of inter-device communication. In this section, we extend its role to become fog enabler by (i) forming an orchestrated network of gateways and (ii) implementing several features such as acting as repository (i.e., local database) to temporarily store sensors’ and users’ data, and incorporating it with data fusion, aggregation, and interpretation techniques. These are essential to provide

Demonstration and evaluation

To demonstrate our hypothesis, an enhanced healthcare IoT system realized through the use of a network of smart e-Health gateways at the fog layer, a set of demonstrations and evaluations are presented in this section. It starts with demonstrators and evaluations that show the characteristics and performance of the smart gateway and the benefits they provide. These demonstrations show the behavior of a single gateway in a standalone condition as well as the collaborative benefits which can be

Conclusions

In this paper, the concept of fog computing and Smart e-Health Gateways in the context of Internet-of-Things based healthcare systems was presented. Smart gateways at the close proximity of sensor nodes in smart home or hospital premises can exploit their unique strategic position to tackle many challenges in IoT-based health systems such as mobility, energy efficiency, scalability, interoperability, and reliability issues. We investigated in detail a range of high level services which can be

Amir M. Rahmani received his Master’s degree from Department of Electrical and Computer Engineering, University of Tehran, Iran, in 2009 and Ph.D. degree from Department of Information Technology, University of Turku, Finland, in 2012. He also received his MBA jointly from Turku School of Economics and European Institute of Innovation & Technology (EIT) ICT Labs, in 2014. He is currently an EU Marie Curie Global Fellow at University of California Irvine, USA, and TU Wien, Austria. He is also

References (76)

  • FanY.J. et al.

    IoT-based smart rehabilitation system

    IEEE Trans. Ind. Inf.

    (2014)
  • FarahaniB. et al.

    Towards fog-driven IoT eHealth: Promises and challenges of IoT in medicine and healthcare

    Elsevier Future Generation Computer Systems

    (2017)
  • European Research Cluster on the Internet of Things, IoT semantic interoperability: research challenges, best...
  • XuB. et al.

    Ubiquitous data accessing method in IoT-based information system for emergency medical services

    IEEE Trans. Ind. Inf.

    (2014)
  • JiangL. et al.

    An IoT-oriented data storage framework in cloud computing platform

    IEEE Trans. Ind. Inf.

    (2014)
  • KoopC.E. et al.

    Future delivery of health care: Cybercare

    IEEE Eng. Med. Biol. Mag.

    (2008)
  • BonomiF. et al.

    Fog computing and its role in the internet of things

  • AazamM. et al.

    Fog computing micro datacenter based dynamic resource estimation and pricing model for IoT

  • AazamM. et al.

    Fog computing and smart gateway based communication for cloud of things

  • RahmaniA.-M. et al.

    Smart e-Health gateway: Bringing intelligence to IoT-based ubiquitous healthcare systems

  • EmaraK.A et al.

    A gateway-based framework for transparent interconnection between WSN and IP network

  • ZhuQ. et al.

    IoT gateway: Bridging wireless sensor networks into internet of things

  • MuellerR. et al.

    Demo: A generic platform for sensor network applications

  • BimschasD. et al.

    Middleware for smart gateways connecting sensornets to the internet

  • YoonJ.-W. et al.

    Sensor network middleware for distributed and heterogeneous environments

  • WuL. et al.

    Plug-configure-play service-oriented gateway - for fast and easy sensor network application development

  • GuoqiangS. et al.

    Design and implementation of a smart IoT gateway

  • BianJ. et al.

    The new intelligent home control system based on the dynamic and intelligent gateway

  • ShenW. et al.

    Smart border routers for eHealthCare wireless sensor networks

  • SatyanarayananM. et al.

    The case for VM-based cloudlets in mobile computing

    IEEE Perv. Comput.

    (2009)
  • StantchevVladimir et al.

    Smart items, fog and cloud computing as enablers of servitization in healthcare

    Sensors Transducers

    (2015)
  • NunnaS. et al.

    Enabling real-time context-aware collaboration through 5G and mobile edge computing

  • WangShiqiang et al.

    Mobility-Induced service migration in mobile micro-clouds

  • LinYi et al.

    Enhancing edge computing with database replication

  • LaneyD.

    3D Data Management: Controlling Data Volume, Velocity, and Variety, Technical Report

    (2001)
  • M. Beyer, Gartner Says Solving ‘Big Data’ Challenge Involves More Than Just Managing Volumes of Data, 2016....
  • GranadosJ. et al.

    Towards energy-efficient HealthCare: An internet-of-things architecture using intelligent gateways

  • HiltonM.L.

    Wavelet and wavelet packet compression of electrocardiograms

    IEEE Trans. Biomed.

    (1997)
  • Cited by (0)

    Amir M. Rahmani received his Master’s degree from Department of Electrical and Computer Engineering, University of Tehran, Iran, in 2009 and Ph.D. degree from Department of Information Technology, University of Turku, Finland, in 2012. He also received his MBA jointly from Turku School of Economics and European Institute of Innovation & Technology (EIT) ICT Labs, in 2014. He is currently an EU Marie Curie Global Fellow at University of California Irvine, USA, and TU Wien, Austria. He is also adjunct professor in embedded parallel and distributed computing at University of Turku, Finland. He is the author of more than 120 peer-reviewed publications. His research interests span Self-aware Computing, Energy-efficient Many-core Systems, Runtime Resource Management, Healthcare Internet of Things, and Fog Computing.

    Tuan Nguyen Gia : received his B.Sc. (Tech.) degree in Information technology from Department of Information Technology, Helsinki Metropolia University of Applied Sciences, Helsinki, Finland in 2012, and M.Sc. (Tech.) degree in Information Technology, Embedded Computing from the Department of Information Technology and Communication Systems, University of Turku, Finland in 2014. He is currently working towards his Ph.D. degree at the University of Turku, Finland. His research interests include Internet of Things (IoT), Smart Healthcare, and Medical cyber–physical system, FPGA and Wireless Body Sensor Networks.

    Behailu Negash received B.Sc. degree in Electrical Engineering from Mekelle University (Ethiopia) and M.Sc. (Tech.) degree in Embedded Computing from University of Turku (Finland) in 2006 and 2015, respectively. He is currently a Ph.D. student in Embedded Electronics laboratory, IoT4Health research group, at University of Turku. His research focuses on architecture and interoperability of Internet of Things, network architecture and embedded software.

    Arman Anzanpour is Ph.D. student in “IoT for Health” group at University of Turku since September, 2014. He received his Master in Biomedical Engineering from Amirkabir University of Technology, Iran and his Bachelor in Material Engineering from Ferdwosi University of Mashhad. His current research focuses on Internet of Things and smart health monitoring frameworks.

    Iman Azimi received his bachelor degree in Biomedical Engineering at University of Isfahan (Iran) in 2010, and his master degree in Artificial Intelligence and Robotics at Sapienza, University of Rome (Italy) in 2014. He started his Ph.D. research in IoT4health group, department of Information Technology at University of Turku in August 2015. His current research area is intelligent health big data analytics based on Internet-of-Things.

    Mingzhe Jiang is currently a Ph.D. student in IoT4Health research group in University of Turku. She received her M.Sc and B.Sc degree in Instrument Science and Technology from Harbin Institute of Technology in the year 2014 and 2012. Her current research is related with bio-signal processing and pattern recognition in Healthcare Internet of Things.

    Pasi Liljeberg received the M.Sc. and Ph.D. degrees in Electronics and Information Technology from the University of Turku, Turku, Finland, in 1999 and 2005, respectively. He is a Senior University Lecturer in Embedded Electronics Laboratory and an adjunct professor in embedded computing architectures at the University of Turku, Embedded Computer Systems laboratory. During the period 2007–2009, he held an Academy of Finland researcher position. He is the author of more than 200 peer-reviewed publications, has supervised nine Ph.D. theses. Liljeberg is the leader of the Internet-of-Things for Healthcare (IoT4Health) research group.

    View full text