Professional Documents
Culture Documents
net/publication/328859092
CITATIONS READS
0 145
5 authors, including:
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Syed Tauhid Ullah Shah on 04 December 2018.
Syed Tauhid Ullah Shah, Faizan Badshah, Faheem Dad, Nouman Amin,
and Mian Ahmad Jan
1 Introduction
Network
providers
Research
Emergency aid
institution
services
Analysis Storage
Processing servers
HealthCare Family,friends
advisor and social media
result in access to better healthcare, minimized cost, and direct interaction between
healthcare professionals and the patient (Fig. 1).
Asthma is a prolonged lung disease of wheezing and breathlessness that occurs
several times a day or in a week in individuals. This disease is common among
children, and the number of deaths in children is greater than those in the elders.
According to WHO, more than 235 million people are suffering from asthma [5].
This disease occurs in both low-income and high-income countries, while more than
80% of deaths occur in low-income countries. According to estimates released in
2016 by WHO, over 383,000 deaths occur because of asthma in 2015. Air pollution
and smoking are the core causes for the problem. Due to the absence of instant
help, elder people suffer most and may experience stress. Still, no widespread work
has been done about cloud-assisted HealthcareIoT-driven framework for asthma
patients.
In this paper, we proposed a cloud-assisted IoT-driven healthcare monitoring
framework for asthma patients. First of all, using different devices and sensor,
patient respiration rate can be recorded at home or outdoors. On the client side,
using a desktop based or mobile application will take out the undesirable noise
from the collected signal. As patient data safety is very important in HealthcareIoT.
Therefore, data must be protected from unauthorized access. A gap in the patient
data security may cause mental disorder, social embarrassment, heart attack, or any
other physical damage. Therefore the signal is embedded with watermarking for
Cloud-Assisted IoT-Based Smart Respiratory Monitoring System for Asthma Patients 79
authentication and security. Respiration rate is calculated with the help of a simple
algorithm. After that the encrypted signal is transmitted to the cloud, where features
are extracted and classified with the help of a classifier. Then the classified data
with watermarked signal is transmitted to the specific healthcare professional. The
healthcare professional analyzes the signal and classified data and sends a decision
to the cloud server. At the end, the patient is notified with the healthcare professional
decision.
2 Literature Review
To get rid of common glitches and noise from the recorded signal, it must be
enhanced before any kind of processing and feature extraction. In the enhancement
phase, low-pass filter is applied to the recorded signal to overwhelm high frequency
modules caused by noise. After that, the median filter was applied to eliminate
minute glitches. Figure 3 shows the effect of passing the signal through the low-pass
and median filters. The figure illustrates that the quality of the signal is improving
and looks clear after applying the low-pass and median filters.
82 S. T. U. Shah et al.
Fig. 3 The effect of low-pass and median filter on record signal: (a) recorded signal, (b) low-pass
filtered, and (c) median filter signal
4.2 Watermarking
This technique is used to protect signals from forgery. Through this technique, we
embed some specific information in the signal so that its credibility can be protected
and the signal will no longer intermix with other signals. This technique consists of
two parts which are watermark embedding and watermark extraction. Watermark
embedding adds some information to the respiration signal and guarantees the
authenticity. We used discrete wavelet transform (DWT) for this purpose. This
technique decomposes the respiration signal to four different frequencies of sub-
bands: horizontal details (HLi ), low-frequency details (Li), high-frequency details
(HHi ), and vertical details (LHi ). We apply the watermark embedding into those
coefficients having low frequencies [20]. We used IDWT technique to extract the
original details of the signal [21]. Watermark embedding to the signal is applied on
the client, while extraction is applied at cloud side.
Cloud-Assisted IoT-Based Smart Respiratory Monitoring System for Asthma Patients 83
At the cloud server side, different features are extracted from the respiration signal.
That includes calculating the breath rate/minute (bpm). Breath rate may vary
between 12 and 37 bpm, while the normal breath rate of an adult in resting position
is 12–20 bpm. The breath rate for a 1-year-old baby can vary between 30 and 40,
while in elders, it may vary between 12 and 30. To calculate the breath rate, we used
the algorithm in Fig. 4.
Algorithm_1 – CalculateRespiratoryRate
In the algorithm described in Fig. 4, first of all, we will take data of 20 s from
the graph. In the next step, the data will be placed in an array. Next, using a sliding
window technique with having a size of 5 for each window, we identify the total
number of peak points. Through this we will compute each set of five elements; if
the central element is greater than the central point, then it will be considered as
peak point, and the numofpeak variable will be incremented. After computing all
the data in the array, the breath per minute is obtained by multiplying the resultant
numofpeak by 3.
Figure 5 shows the workload of the transmission services used by the proposed
system. The figure focuses on the transmission of respiration signal. The runtime
measurement of this service is collected using a Java-based simulator program. To
achieve this, we used a virtual machine with Intel core i3 1.7 GHZ processor, 3GB
DDR ECC RAM, 8MBPS bandwidth, and running windows server 2012.
6 Conclusion
References
1. https://www.forbes.com/sites/tjmccue/2015/04/22/117-billion-market-for-internet-of-things-
in-healthcare-by-2020/#5a6eba4069d9
2. https://www.psmarketresearch.com/market-analysis/smart-home-healthcare-market
3. http://healthitanalytics.com/news/healthcare-internet-of-things-driving-global-market-growth
4. http://blog.iiconsortium.org/2015/01/how-toindustrial-internet-of-things-can-save-50000-
lives-a-year.html
5. http://www.who.int/mediacentre/factsheets/fs307/en/
6. Hassanalieragh, M., et al. Health monitoring and management using Internet-of-Things (IoT)
sensing with cloud-based processing: Opportunities and challenges, Services Computing
(SCC), 2015 IEEE international conference on. IEEE, 2015.
7. Mohammed, J., et al. Internet of Things: Remote patient monitoring using web services and
cloud computing. Internet of Things (iThings), 2014 IEEE international conference on, and
green computing and communications (GreenCom), IEEE and cyber, physical and social
computing (CPSCom), IEEE. IEEE, 2014.
8. Hu, L., et al. (2015). Software defined healthcare networks. IEEE Wireless Communications,
22(6), 67–75.
9. Riazul Islam, S. M., et al. (2015). The internet of things for health care: A comprehensive
survey. IEEE Access, 3, 678–708.
86 S. T. U. Shah et al.
10. Jara, A. J., Zamora-Izquierdo, M. A., & Skarmeta, A. F. (2013). Interconnection framework
for mHealth and remote monitoring based on the internet of things. IEEE Journal on Selected
Areas in Communications, 31(9), 47–65.
11. Xu, B., et al. (2014). Ubiquitous data accessing method in IoT-based information system for
emergency medical services. IEEE Transactions on Industrial Informatics, 10(2), 1578–1586.
12. Li, Y., Guo, L., & Guo, Y. Enabling health monitoring as a service in the cloud. Utility and
cloud computing (UCC), 2014 IEEE/ACM 7th international conference on. IEEE, 2014.
13. Hossain, M. S. (2015). Cloud-supported cyber–physical localization framework for patients
monitoring. IEEE Systems Journal, 11(1), 118–127.
14. Zhang, K., et al. (2015). Security and privacy for mobile healthcare networks: From a quality
of protection perspective. IEEE Wireless Communications, 22(4), 104–112.
15. Hossain, M. S., & Muhammad, G. (2014). Cloud-based collaborative media service framework
for healthcare. International Journal of Distributed Sensor Networks, 10(3), 858712.
16. Granados, J., et al. (2015). Web-enabled intelligent gateways for eHealth internet-of-things. In
Internet of Things. User-Centric IoT (pp. 248–254). Cham: Springer International Publishing.
17. Amendola, S., et al. (2014). RFID technology for IoT-based personal healthcare in smart
spaces. IEEE Internet of Things Journal, 1(2), 144–152.
18. Catarinucci, L., et al. (2015). An IoT-aware architecture for smart healthcare systems. IEEE
Internet of Things Journal, 2(6), 515–526.
19. Raji, A., et al. Respiratory monitoring system for asthma patients based on IoT. Green
engineering and technologies (IC-GET), 2016 online international conference on. IEEE, 2016.
20. Tiwari, N, Ramaiya, M. K., & Sharma, M. Digital watermarking using DWT and DES.
Advance computing conference (IACC), 2013 IEEE 3rd international. IEEE, 2013.
21. Gonge, S. S., & Bakal, J. W. (2013). Robust digital watermarking techniques by using DCT and
spread spectrum. International Journal of Electrical, Electronics and Data Communication,
1(2), 111–124.
22. Goldberger, A. L., et al. (2000). Physiobank, physiotoolkit, and physionet. Circulation,
101(23), e215–e220.