Improving computing issues in Internet of Things driven e-health systems Mirjana Maksimović Faculty of Electrical Engineering University of East Sarajevo East Sarajevo, Bosnia and Herzegovina e-mail: mirjana@etf.unssa.rs.ba Abstract—The Internet of Things (IoT) progress shows a available, acceptable and high-quality all medical services. positive influence on all aspects of healthcare. Enabling access to Improving access to healthcare and quality of healthcare appear high-quality healthcare to anyone, from anywhere are the main as one of the primary objectives of the modern society. The advantages of the IoT-driven e-health systems. Increasing design of healthcare systems and their improvements are numbers of medical devices and sensors and 24/7 monitoring of guided by the key human rights standards such as: universal health parameters, consequently lead to enormous quantities and access, availability, dignity, acceptability, non-discrimination, varieties of data. Having in mind the amounts of generated data quality, transparency, participation, and accountability [1]. The and importance of on-time diagnosis and decision making as well recent intensive technology advancements have dramatically as a significance of fast reactions in a case of detected changed the healthcare of today. The Information and abnormalities, transmitting all data to the Cloud for analysis may Communication Technologies (ICTs) have an impact on many not be appropriate. For that reason, implementing a Fog computing, which realizes mini analytic processing centers at the aspects of healthcare, creating a new vision, namely e-health. edge of the network, appears as a better approach. This paper The term e-health, sometimes called health information analyzes the manners and benefits of implementing Fog technology, encompasses the utilization of modern ICTs computing in the IoT-driven e-health systems. It is expected that solutions to enable more accessible and high-quality healthcare the IoT and Fog computing together will revolutionize healthcare when and where it’s demanded. like nothing else before. The significant part in the realization of this vision has the Keywords—Internet of Things (IoT); e-health; Cloud; Fog Internet of Things (IoT). The IoT is a worldwide network of computing intercommunicating physical objects, devices or “things” that are connected to the Internet, controllable and available from I. INTRODUCTION anywhere, anyhow and anytime. As such, the IoT brings numerous benefits in diverse application domains (Fig. 1). The right to healthcare is a fundamental right of every human being and includes anytime and anywhere accessible, Figure 1. An IoT ecosystem: architecture and applications [2] Copyright © 2017 held by the authors 14 The IoT devices are embedded with electronics, software, health-related data will be about 48 percent annually, and the sensors, and network connectivity, which enable sensing, volume of healthcare data will grow to 2,314 Exabytes (1018 collecting and exchanging information among each other, as bytes) by 2020. well as with the environment, with or without human intervention. The realization of the IoT vision, connecting people and things, with anything and anyone, at anyplace and using any path/network and any service, requires dramatic changes in systems, architectures, and communications which should be: flexible, adaptive, secure, and pervasive without being intrusive [3]. The coupling IoT and healthcare leads to the IoT-driven e- health solutions which have the power to completely revolutionize the healthcare industry. With the help of small, powerful and intelligent sensing devices, and the IoT concepts, availability and accessibility of healthcare are improved, more “personalized” systems are created alongside realized high- quality cost-effective healthcare delivery [3]. The increasing number of sensing devices used for Figure 2. IoT-based e-healthsystem [2] healthcare purposes will generate a large amount of data. These data have to be processed accurately and on time in order to Alongside a voluminous nature of data, variety, velocity, enable adequate diagnosis and care. Hence, it is essential to value and veracity, are also the foundational characteristics of analyze, capture, search, share, store, and visualize large- health-associated data. The IoT-based systems include medical volume, complex, growing health-related datasets [3]. Posting and healthcare information such as: personal information, large quantities of data to the Cloud for analysis and storage is radiology images, personal medical records, 3D imaging, not practical, and it takes some time what can induce a negative genomics, biometric sensor readings, etc. These data are influence in decision-making processes relating health. It is classified into structured information (e.g. clinical data) and believed that current Cloud computing systems will not be unstructured or semi-unstructured (e.g. office medical records, capable of managing the total burden of data generated by IoT, doctor notes, paper prescriptions, images, and radiograph and an adequate solution is seen in Fog computing. Fog films). The velocity of healthcare data increases with daily computing is sort of a middle layer between the Cloud and the measurements and readings from medical devices, while high- hardware and it reduces the quantities of data which needs to quality data and its value are essential in making a diagnosis, be sent to the Cloud by implementing more efficient data predicting outcomes at earlier stages, making real-time processing, analysis, and storage [4]. decisions, promoting patients’ health, enhancing medicine, This paper represents the analysis of computing issues in reducing costs, etc [2]. Hence, a voluminous, rapidly growing, IoT-driven e-health systems. Hence, the rest of the paper is and mostly unstructured medical data are the consequence of organized as follows. The second section presents the increased digitalization, the continuous optimization of fundamental characteristics of data produced by IoT-driven e- diagnostic laboratory and imaging sensors, increased health systems and challenges for their processing and monitoring with sensors of all kinds and so on, and represents analyzing. The principles of Fog computing and how it can one of the biggest challenges in healthcare systems nowadays. help in dealing with health-related data are shown in Section 3. These data are usually stored in the Cloud while a variety of The last section contains the concluding remarks. techniques and big data analytics are used to extract useful information, perform predictive modeling and make actionable II. IOT-DRIVEN E-HEALTH SYSTEMS: HOW TO DEAL WITH A decisions from the resulting massive volumes of high- LARGE AMOUNT OF VARIOUS HEALTH-RELATED DATA? dimensional observations [2]. To realize the vision of IoT-related healthcare systems, Healthcare organizations often use virtualization and Cloud the integration of IoT principles in e-health is essential. Hence, computing for manipulation, storage and use of such a complex a variety of sensors, embedded in a device, internally data structure. Ideally, this “real-time analytics” could only embedded, wearable by users or stationary devices, are utilized take minutes, but in the life or death situation, it is to gather diverse patient medical data. These data are further unacceptable [8]. The additional problem with Cloud processed, analyzed and transmitted wirelessly to medical computing is bandwidth. A growing number of smart devices professionals for further medical analysis, the remote control of today are generating too much data to be sent to the Cloud for certain medical treatments or parameters or real-time feedback processing. The bandwidth is not adequate and costs too much (Fig.2) [3, 5, 6]. [9]. Also, Cloud-based applications are typically widely There are several estimations of the total number of IoT distributed. The data are far away from the application logic devices anticipated to be in operation by 2019, ranging from 19 and may be far away from the consumer. This may lead to billion to 40 billion devices. Regardless of the correct expected latency and even reliability issues [10]. These challenges can increase in the total number of IoT devices, the large-volume, be overcome by operating at the edge of the Cloud. In other complex and constantly growing datasets represent the future words, the data are processed in smart devices where it is serious challenge. According to [7], an overall increase in generated instead of routing everything over Cloud channels. 15 In this manner data processing is faster, the response time is TABLE I. FOG NODES EXTEND THE CLOUD TO THE NETWORK EDGE [14] improved while the need for bandwidth is scaled down. Fog Consequently, costs are lowered and efficiency is enhanced [9, Fog nodes closest to IoT aggregation Cloud devices 11]. This approach is known as Fog computing or Fog nodes networking and holds the potential to revolutionize IoT-driven Response Seconds to Minutes, Milliseconds to subsecond e-health solutions and make them truly useful. time minutes days, weeks Machine to Machine Big data communication Haptics Visualization III. FOG COMPUTING AND ITS ROLE IN IOT-POWERED E- Application (controlling technology analytics HEALTH SOLUTIONS examples using the sense of touch), Simple Graphical Fog computing adds a middle layer of computing power including telemedicine analytics dashboards and training between the devices and the Cloud. In other words, it allows How long Short durations: individual devices to conduct critical analytics and thus Month or IoT data is Transient perhaps hours, years become processing nodes that can handle smaller, time- stored days, weeks sensitive computational decisions without having to send all Geographic Very local (e.g. one city Wider Global coverage block) their data up to the Cloud. In this way, time from request to answer is significantly reduced and the link with the Cloud is The IoT-driven e-health system consists of various sensors free for larger-scale analytics work [8]. The smart gateway, within or on the human body as well as those attached in shown in Fig. 3, is an example of Fog computing layer. By ambient surroundings. With the help of these devices, high- allowing real-time computing it minimizes the latency, dimensional, high-velocity and high-variety health-related data provides location awareness and facilitates handling of the is being generated on a daily base. Sending all that data to the mobility requirements of the nodes [12]. Cloud and transmitting response data back requires a larger It has to be highlighted that the Fog computing is not a bandwidth, a considerable amount of time and can suffer from replacement for Cloud computing. Fog computing vision latency issues. Fog computing, creating an additional retains the benefits of Cloud (e.g. agility, flexibility and computing layer between sensors and Cloud computing distributed computing) while allowing communication of the (consists of the gateways and distributed databases) can get data over the IoT devices much easier than Cloud [13]. Hence, around these barriers [8, 15, 16]. This middle layer acts as a Fog computing extends the Cloud computing paradigm at the miniature data processing center that exchange data without the edge of the network (Table 1) and it is developed to address need for the Cloud. The sensed data is being analyzed at this applications and services that do not fit the paradigm of the level using various data mining techniques and data analytics. Cloud, including [9, 13]: The found patterns are stored and unique patterns are  Applications that require very low and predictable transmitted to the Cloud alongside clinically relevant latency; information extracted (Fig. 3). Hence, computations are  Applications in which thousands or millions of things performed only where the data originates: at the hospital or across a large geographic area are generating data; physician office that holds the patient record, while patient  Fast mobile applications; and health data could be exposed to each device through a shared  Large-scale distributed control systems. interface, using predefined authorization and user protocols [15]. Figure 3. Fog computing in IoT-based e-health system [12] 16 Implementing the concept of Fog computing in IoT- REFERENCES powered e-health systems, the smart gateway as a middle layer between IoT-connected medical devices and sensors, and [1] Nesri, “What is the Human Right to Health and Health Care?,” [Online]: Cloud, enable applications of advanced data mining https://www.nesri.org/programs/what-is-the-human-right-to-health-and- techniques, distributed storage, and notification service at the health-care edge of a network [16]. Turning devices into their own mini- [2] Opentechdiary, “Internet of Things,” 2015. [Online]: https://opentechdiary.wordpress.com/tag/internet-of-things/ analytics centers, the Fog computing offers big benefits for [3] M. Maksimovic and V. Vujovic, Internet of Things based e-health healthcare: systems: ideas, expectations and concers, Chapter in the book Handbook  Fog layer easily deals with challenges such as of Large-Scale Distributed Computing in Smart Healthcare (in press), heterogeneity of devices and data sources, Springer, 2017. interoperability and bandwidth while connection of [4] Westbase Technology, “Fog Computing vs Cloud Computing: What’s the difference?,” 2016. [Online]: http://www.westbaseuk.com/news/fog- health data from disparate organizations is enabled computing-vs-cloud-computing-whats-the- through the IoT; difference/#sthash.5j0QkbxG.5HRRJSNc.dpuf  Splitting big data to sub data in the Fog layer leads to [5] D. Niewolny, “How the Internet of Things Is Revolutionizing Healthcare the easing data manage and process. In addition, it is -White Paper,” 2013. [Online]: simpler to extract useful key information when the https://cache.freescale.com/files/corporate/doc/white_paper/IOTREVHE data are processed in smart devices where it is ALCARWP.pdf generated. [6] D. Lake, R. Milito, M. Morrow, R. Vargheese, “Internet of Things: Architectural Framework for eHealth Security,” Journal of ITC  Fog layer enables real-time and online analytic even Standardization, Vol. 3 & 4, pp. 301–328, River Publishers, 2014. in event of loss of connectivity or poor connection [7] K. Corbin, “How CIOs Can Prepare for Healthcare ‘Data Tsunami’,” with the Cloud; 2014. [Online]: http://www.cio.com/article/2860072/healthcare/how-  Having in mind that the latency is highly associated cios-can-prepare-for-healthcare-data-tsunami.html with proximity, moving the applications and services [8] J. Bresnick, “How Fog Computing May Power the Healthcare Internet of Things,” Healthanalytics, [Online]: close to the end users contributes to significantly http://healthitanalytics.com/features/how-fog-computing-may-power- reduced latency. Hence, Fog computing implies less the-healthcare-internet-of-things congestion and faster real-time interaction what [9] N. Joshi, “Why is fog computing beneficial for IoT?,” 2016. [Online]: enables instantly alerting healthcare providers in a https://www.linkedin.com/pulse/why-fog-computing-beneficial-iot- case of emergency. naveen-joshi?articleId=8166335329880272527#comments- 8166335329880272527&trk=sushi_topic_posts_guest  Data privacy is easier to be provided since Fog [10] D. Linthicum, “3 ways to improve cloud performance, Infoworld,” 2012 computing separates the public and private data. [Online]: http://www.infoworld.com/article/2615188/cloud- computing/3-ways-to-improve-cloud-performance.html IV. CONCLUDING REMARKS [11] B. Marr, “What Is Fog Computing? And Why It Matters In Our Big Healthcare, as almost every other aspect of our lives, has Data And IoT World,” 2016. [Online]: not been immune to technology advancements. The evolution http://www.forbes.com/sites/bernardmarr/2016/10/14/what-is-fog- of the IoT has completely revolutionized healthcare industry, computing-and-why-it-matters-in-our-big-data-and-iot- world/#686925e34971 especially monitoring and delivering of healthcare. At the same [12] A.-M. Rahmani, N. K. Thanigaivelan, T. N. Gia, J. Granados, B. time, a great number of diverse IoT-connected medical devices Negash, P. Liljeberg, H. Tenhunen, “Smart e-Health Gateway: Bringing and sensors create an escalating volume of health-associated Intelligence to Internet-of-Things Based Ubiquitous Healthcare data. Instead of sending all these data to the Cloud, Systems,” in Proc. of Annual IEEE Consumer Communications and implementing a miniature data processing centers that Networking Conference (CCNC’15), pp. 826-834, 2015, USA. exchange data without the need for the Cloud has been shown [13] P. G. Vinueza Naranjo, M. Shojafar, L. Vaca-Cardenas, C. Canali, R. as a better approach. Problems with the bandwidth, a Lancellotti, E. Baccarelli, “Big Data Over SmartGrid – A Fog Computing Perspective,” SOFTCOM Workshop, pp. 1-6, 2016. considerable amount of time, and latency in a case of Cloud computing utilization justify the implementation of Fog [14] Cisco, “Fog Computing and the Internet of Things: Extend the Cloud to Where the Things Are,” 2015. [Online]: computing. The benefits that Fog computing offers (low https://www.cisco.com/c/dam/en_us/solutions/trends/iot/.../computing- latency, low bandwidth, heterogeneity, interoperability, overview.pdf scalability, security and privacy, real-time processing and [15] H. Dubey, “Fog Data: Enhancing Telehealth Big Data Through Fog actions) are of immense importance in health monitoring and Computing,” In Proceedings of the ASE BigData & SocialInformatics delivering healthcare. Moving powerful processing, currently 2015 (ASE BD&SI '15), New York, USA only available in the Cloud, to the edge of the network, Fog [16] T. N. Gia, M. Jiang, A.-M. Rahmani, T. Westerlund, T. Liljeberg, H. computing holds the potential to make IoT-driven e-health Tenhunen, “Fog Computing in Healthcare Internet-of-Things: A Case Study on ECG Feature Extraction,” IEEE International Conference on systems reliable, simpler, scalable, and exceptionally high Computer and Information Technology; Ubiquitous Computing and performance. However, Fog computing will not totally replace Communications; Dependable, Autonomic and Secure Computing; the Cloud computing. Complementing each other they will be a Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), powerful tool to achieve numerous benefits in various aspects 2015 of the healthcare domain. 17