International Journal of Engineering &Technology, 7 (1.

7) (2018) 175-178

International Journal of Engineering & Technology

Website: www.sciencepubco.com/index.php/IJET

Research paper

Internet of things (IoT) based health monitoring

system and challenges
M. Sathya *1, S. Madhan 2, K. Jayanthi 3
1, 3
Assistant Professor, Department of Information Technology, School of Computing,Vel Tech Rangarajan
Dr. Sagunthala R&D Institute of Science and Technology,Avadi, Chennai-62, TamilNadu, India.
2
Assistant Professor,
Department of Computer Science and Engineering,University College of Engineering, Thirukkuvalai.

*Email: [email protected]

Abstract

Among the applications that Internet of Things (IoT) facilitated to the world, Healthcare applications are most important. In
general, IoT has been widely used to interconnect the advanced medical resources and to offer smart and effective healthcare
services to the people. The advanced sensors can be either worn or be embedded into the body of the patients, so as to
continously monitor their health. The information collected in such manner, can be analzed, aggregated and mined to do the early
prediction of diseases. The processing algorithms assist the physicians for the personalization of treatment and it helps to make
the health care economical, at the same time, with improved outcomes. Also, in this paper, we highlight the challenges in the
implementation of IoT health monitoring system in real world.

Keywords: Internet of Things (IoT), health monitoring, Medical Devices, Sensors

1. Introduction embedded with the patients, so that to enable seamless

networking between the patients, medical devices and
physicians. The sensors will record signals in a continuous
The world population is increasing tremendously. The cities
manner, they are then correlated with the essential
accommodating more population face astounding pressure of
physiological parameters and communicated over the wireless
urban living. Even though the medical resources and facilities
network. The resulting data is stored, processed and analzed
in cities are expanded daily, still the suffice level is not
with the existing health records [1]. Using the available data
attained. The massive pressure towards the management of
records and decision support systems, the physician can do a
healthcare in cities has triggered the advancement in
better prognosis so that to suggest early treatment. Even when
technologies to come out with the proper solutions to the
the doctor is not available, this analysis enables the today’s
booming problems.
machines to predict the health issues. Not only prediction,
With the increased rate of medically challenged people,
machines can also be able to come out with the medicines
remote healthcare has become a part of our life. In recent
from the systematic study of the medicinal databases.
years, we observe the increased interest in wearable sensors
The progressive technology will have a transformative impact
and such devices are available in market for cheaper rate for
in every human’s life and health monitoring; it will
personal healthcare and activity awareness. Researchers
remarkably cut down the healthcare expenses and a step ahead
considered implementation of such advanced devices for the
in the accuracy of disease predictions. In this paper, we
medical applications for data recording, management and also
present a idea of a service model in technological and
to continuosly monitor the patient’s health.
economic views for the comfort of patients and also the open
The Intenet of Things offers a rising technology to attain the
challenges in implementing IoT in real world medical field.
next level of health services [2]. It assures for the affordable,
low-cost, reliable and handy devices to be carried or

Copyright © 2018 Authors. This is an open access article distributed under the Creative Commons Attribution License, which permits
unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
176 International Journal of Engineering & Technology

2. Background This system consists of four-protocol layers such as the

physical layer, network layer, middleware layer and
application layer. First, the physical layer consists of devices
In recent days, various IoT systems were developed for health
embedded with sensors and transmitters. The network layer is
monitoring systems. Wang et al [6] designed a compatible IoT
responsible of transmitting signals from sensors to the
system for medical devices which was having multiple
Cloudlets whereas the Middleware layer do the work of
communication standard. A resource-based data retrieving
storing the data into the cloud and make it available to the
method (UDA-IoT) was proposed by Xu et al [7] for
people who are concerned. Finally, in the application layer,
information-intensive health applications.
analytics and diagnosis process are performed.
Peer-to-Peer (P2P) and IoT technologies were combined in a
medical system called as a smart box to keep the patients in
Data collection and Transmission:
control. Kolici et al [8] implemented that compared the
experimental results for different scenarios. Web Real-Time
Patients will be given with the necessary wearable sensors
Communication (WebRTC) was given by Sundholm et al [9]
capable of measuring Electrocardiography (ECG),
which focused mostly on the secured transmission of data
Temperature, Electromyography (EMG) muscle activity,
multiple concurrent streams in an efficient manner.
respiratory rate, sweating and blood glucose level. Using these
By enabling the electronic sphygmomanometer to
devices, diseases such as arrhythmia, fever, neuromuscular
communicate via Bluetooth, an Android application [10] was
abnormality, blood pressure, obesity and diabetes. The sensors
developed to record the data such as SBP-Systolic Blood
used nowadays can be easily placed in contact with the skin in
Pressure, DBP - Diastolic Blood Pressure and Heart Rate. That
mulitiple body parts are highly preferable so that to obtain
application made it easy to transmit the recorded data using
accurate measures.
any mobile device and such data is then be recorded,
From the compact sensors embedded within the patients body,
abnormality is found out and message is conveyed to the
physiological data is collected consisting of various necessary
people.
physiological parameters. Then a small hardware capable of
A real-time application [11] was presented with distributed
preprocessing the acquired data and a communication software
flow environment for the IoT healthcare. When the person
to transmit that data. The sensors must be small, light-weight
under observation moves beyond range, data will be recorded
and not troubling the patient’s mobility and movements. Those
in the local server and communicated later. A Galileo board
sensors must operate on small, energy efficient batteries. The
[12] is a IoT-based device with embedded medical platform
batteries are expected to be working continuosly without
for the designed for electrocardiogram (ECG) signal analysis
charging and replcacement.
and based on an algorithm, heart function is monitored.
In market, few IoT Portable Medical Devices [13] were
introduced which upgraded the patient’s mobility. But the
security threats and few drawbacks were also there while
using Portable Medical Devices. When we started to consider
light-weight IoT devices, using the existing databases,
diseases were predicted. But while such predictions, issues
were in storage of databases and analysis using those
databases. A new cloud-based fine-grained health information
access control framework [14] was introduced which
addressed the security challenges and the cloud reciprocity
issues.
A proxy-based approach for end-to-end communication
between the IoT-enabled living systems [15] was proposed to
challenge the real world applications. A portable electric aid
device[16] was designed specifically for the blind people in
which ultrasonic range finders are mounted on the belt to find
the obstacles present in the users way and to direct the blind
people through Bluetooth headphone. Another depth sensor
based den avigation system [17] for the blind people with high
accuracy and to alert user via vibrio tactile feedback in the
hand gloves.
When the previous works are addressed, there is a limitation
of database connectivity between the different cloud The system components responsible for data transmission
environment in monitoring the data in constant time intervals must be able to convert recordings of the patient from any of
and to analyze data. Considering this limitation, in this paper, their location to the health centre with accuracy and security.
we present a cloud-based Internet of Things system that can be For transmission, short range low-power digital radio Zigbee
implemented in different health monitoring systems. or Bluetooth can be used. Further, the acquired data can be
relayed to health center through Internet for storage. The
sensors involved in the IoT system can be operated through
the Internet via the concentrator which can even be a smart
3. System Architecture phone.
International Journal of Engineering & Technology 3

In the health monitoring system, the existing Wireless Sensor analyzing this for longer duration, accuracy in the medical
Networks(WSN) must be customized so as to remodify the diagnostics can be better improved.
sensing nodes based on relative distance between sensors and Data from the wearable sensors will undergo the process of
health center, also to acquire more physical information for pattern recognition and machine learning techniques [22]. In
long time by avoiding redundant tasks. [18]. When we focus order to handle with more heterogenous and constantly
on low energy consumption, threshold levels should be set so changing sensor data, machine learning must be developed
as to handle the emergency situations. At the same time, the further. Also, those algorithms must be capable of dealing
other sensors can be powered off to save batter lifetime. with inevitably missing data values, streaming data and
When energy consumption is limited, there increases the need information of varying dimensionality and semantics as the
of low power protocols for communication. When compared design of sensors often change.
with IEEE 802.15.4, Zigbee is a low rate Wireless Personal There are three main challenges while we do the analytics
Area Network (LR-WPAN) which operates even in the process in the implementation of IoT in medical fields. Firstly,
distance of 10m. Zigbee is implemented in mesh networking in the field of medicine, almost every day new measuring
with reliability and extended battery life. devices and equipment’s will be introduced. And so, they
Another wireless communication preferred is Bluetooth low need periodic updating of the IoT devices and the sensor data
energy (BLE) which is for short range communication with will also be different.
low power consumption. It suits for particular requirements of Obviously, it will make a huge impact in the database design
applications such as health monitoring, home entertainment and the IoT devices must be capable of managing all those.
and also sports. Using BLE, the components can be put in The machine learning algorithms are expected to be developed
sleep for long intervals and so the energy consumption will be further to handle the constantly changing sensory information.
highly reduced in terms of number of bytes sent per Joule of Secondly, everytime depending upon the condition of the
energy [19]. Further the protocol Low Power Wireless patient, the data to be collected will differ as directed by the
Personal Area Networks (6LoWPAN) can also be utilized in physician. Hence it is somewhat infeasible to additional input
case of connecting energy constrained WPAN devices to the changing over time. It is possible to match the prior sensor
Internet [20]. data with the clinical records, still it is challenging because of
the rare patient conditions. The concept of classification and
Cloudlet Processing: regression methods can be helpful to prepare the common
training data for providing machine learning algorithms, but
Nowadays, the smart phones are coming with much and more again it will be the additional burden to the physicians.
advanced facilities so that it can be used as both LTE and Finally, as we take input from different sources, the sensory
WiFi. Such smart phones can act as concentrators in this data will produce heterogenous modalities. This heterogeneity
system. Data collected by the concentrator will be transmitted remains as a challenge for the machine learning approaches as
to the cloud to storage. Such data, if stored, it will be much it handles homogenous data. Graphical models may be helpful
helpful to access on demand by the physicians or for analytics. to combine different input data in a centered framework with
A small processing unit called cloudlet which is used for both significant customization.
storing and processing locally when the local resources are not Even though the sensor data are numerical; the medical data
suffice to fulfill the requirements. It also helpts to run time- are plotted graphically to continuously monitor the patient’s
critical tasks on the patients medical data. When data is stored health. The concept of visualization plays a vital in health
in cloudlet, it enables all time access for data analytics to monitoring. The data from IoT warble sensors are spanned
produce better diagnostic details. using different visualization methodologies for the effective
Cloudlet Computing has been proposed as a better solution for prediction. The visualization tools must be always ready to
the health applications through PAN as they often deal with interact with the heterogenous data to quick and accurate
offline data. The concenter and cloudlet are allowed to prediction in emergency cases. The visualization must be
communicate through WiFi interface in order to reduce the capable of handling the static images for comparing the
data transfer latency for critical tasks on the collected data. At medical reports of patients.
last, the data in the cloudlet will be saved in the cloud for
reliable storage and distributed access of data. The data 4. Conclusion & Future Work
aggregation performed between cloud and cloudlet can be
differentiated by context aware concentration where context is
nothing but the current and expected status of the patient. In this paper, we found the importance and fruitful benefits of
It has become highly essential to keep the patient’s electronic implementation of IoT in remote health monitoring systems.
medical records secure while storing in cloud. In order to The compact sensors with IoT will make a huge impact on
prevent unauthorized access, appropriate privacy preserving every patient’s life, that even though they are away from home
measures should be taken when we transfer offline data to the and physician, this helps them to reduce the fear of danger.
cloud. Therefore, secure cloud storage frameworks were The sensory data can be acquired in home or work
introduced to deal with the sensitive medical information [21], environments. Also, the challenges in sensing, analytics and
but it is still a challenge. prediction of the disease are also highlighted and those can be
addressed to provide a seamless integraton into the medical
Analytics and Prediction: field.
As the medical datasets are rich in quantity, the data analytics
is also big task. The machine learning algorithms do this work References
of correlating sensor parameters and clinical data. By
178 International Journal of Engineering & Technology

[1] Sullivan, H.T., Sahasrabudhe, S.: Envisioning inclusive In: IEEE Midwest Symposium on Circuits and Systems
futures: technology-based assistive sensory and action (2014)
substitution. Futur. J. 87, 140–148 (2017) [18] C. T. Chou, R. Rana, and W. Hu, “Energy efficient
[2] Yin, Y., Zeng, Y., Chen, X., Fan, Y.: The Internet of Things information collection in wireless sensor networks using
in healthcare: an overview. J. Ind. Inf. Integr. 1, 3–13 (2016) adaptive compressive sensing,” in IEEE 34th Conf.on Local
[3] Himadri Nath Saha, Supratim Auddy, Subrata Pal: Health Computer Networks, LCN 2009., Oct 2009, pp. 443–450.
Monitoring using Internet of Things (IoT), IEEE Journal [19] M. Siekkinen, M. Hiienkari, J. Nurminen, and J. Nieminen,
pp.69–73, 2017 “How low energy is bluetooth low energy? comparative
[4] Sarfraz Fayaz Khan, “Health Care Monitoring System in measurements with zigbee/802.15.4,” in Wireless
Internet of Things (loT) by Using RFID”, IEEE International Communications and Networking Conference Workshops
Conference on Industrial Technology and Management pp (WCNCW), 2012 IEEE, April 2012, pp. 232–237.
198-204, 2017 [20] N. Bui and M. Zorzi, “Health care applications: A solution
[5] MoeenHassanalieragh; Alex Page ; TolgaSoyata; Gaurav based on the internet of things,” in Proc. of the 4th Int.
Sharma,”Health Monitoring and Management Using Symposium on Applied Sciences in Biomed. and Com.
Internet-of-Things (IoT)Sensing with Cloud-Based Tech., ser. ISABEL ’11. New York, NY, USA: ACM, 2011,
Processing: Opportunities and Challenges”, 2015 pp. 131:1–131:5.
[6] Wang, X., Wang, J.T., Zhang, X., Song, J.: A multiple [21] M. Li, S. Yu, Y. Zheng, K. Ren, and W. Lou, “Scalable and
communication standards compatible IoT system for secure sharing of personal health records in cloud computing
medical usage. In: IEEE Faible Tension Faible using attributebased encryption,” IEEE Trans. Parallel
Consommation (FTFC), Paris, pp. 1–4 (2013) Distrib. Syst., vol. 24, no. 1,pp. 131–143, Jan. 2013.
[7] Xu, B., Xu, L.D., Cai, H., Xie, C., Hu, J., Bu, F.: Ubiquitous [22] C. Bishop, Pattern recognition and machine learning. New
data accessing method in IoT-based information system for York, NY:Springer, 2006.
emergency medical services. IEEE Trans. Ind. Inf.10(2),
1578–1586 (2014)
[8] Kolici, V., Spaho, E., Matsuo, K., Caballe, S., Barolli, L.,
Xhafa, F.: Implementation of a medical support system
considering P2P and IoT technologies. In: Eighth
International Conference on Complex, Intelligent and
Software Intensive Systems, Birmingham, pp. 101–106
(2014)
[9] Sandholm, T., Magnusson, B., Johnsson, B.A.: An on-
demand WebRTC and IoT device tunneling service for
hospitals. In: International Conference on Future Internet of
Things and Cloud, Barcelona, pp. 53–60 (2014)
[10] Antonovici, D.A., Chiuchisan, I., Geman, O., Tomegea, A.:
Acquisition and management of biomedical data using
Internet of Things concepts. In: International Symposium on
Fundamentals of Electrical Engineering, Bucharest, pp. 1–4
(2014)
[11] Krishnan, B., Sai, S.S., Mohanthy, S.B.: Real time internet
application with distributed flow environment for medical
IoT. In: International Conference on Green Computing and
Internet of Things, Noida, pp. 832–837 (2015)
[12] Azariadi, D., Tsoutsouras, V., Xydis, S., Soudris, D.: ECG
signal analysis and arrhythmia detection on IoT wearable
medical devices. In: 5th International Conference on Modern
Circuits and Systems Technologies, Thessaloniki, pp. 1–4
(2016)
[13] Mohan, A.: Cyber security for personal medical devices
Internet of Things. In: IEEE International Conference on
Distributed Computing in Sensor Systems, Marina Del Rey,
CA, pp. 372–374 (2014)
[14] Yeh, L.Y., Chiang, P.Y., Tsai, Y.L., Huang, J.L.: Cloud-
based fine-grained health information access control
framework for lightweight IoT devices with dynamic
auditing and attribute revocation. IEEE Trans. Cloud
Comput. PP(99), 1–13 (2015) IoT-Based Health Monitoring
System for Active and Assisted Living 19
[15] Porambage, P., Braeken, A., Gurtov, A., Ylianttila, M.,
Spinsante, S.: Secure end-to-end communication for
constrained devices in IoT-enabled ambient assisted living
systems. In: IEEE 2nd World Forum on Internet of Things,
Milan, pp. 711–714 (2015)
[16] Laubhan, K., Trent, M., Root, B., Abdelgawad, A.,
Yelamarthi, K.: A wearable portable electronic travel aid for
the blind. In: IEEE International Conference on Electrical,
Electronics, and Optimization Techniques (2016)
[17] Yelamarthi, K., DeJong, B.P., Laubhan, K.: A kinect-based
vibrotactile feedback system to assist the visually impaired.