IEEE Consumer Electronics Magazine - May/June 2023 - 70

Blockchain Technology to Combat COVID-19
(exercise induced angina (1 = yes; 0 = no)), " and
" oldpeak (ST depression induced by exercise
relative to rest) " .
Case II: In this case, we have taken the Open
Data, the " General Directorate of Epidemiology, " 14
which is related to COVID-19 dataset.
The dataset contains various important
attributes, like " sex " " patient type, " " entry date, "
" date symptoms, " " date died, " " pneumonia, "
" age, " " pregnancy, " " icu, " etc. This dataset was
also used to predict if a patient needs to be
shiftedtoICUbasedonthe patent attribute.
2) Discussion on Experimental Results
We have plotted the values in the graphs as shown
in Figures 5 and 6 for the Cases I and II datasets,
respectively. It is worth noticing that when the
noise level is increased by an attacker, the performance
degrades significantly in both the cases.
Performance of ML Model Without Data
Poisoning Attacks
It is noticed that if the data are stored in blockchain
system, they are by default tamper proof
and no one can tamper the data, but can access
the data without modifying it with proper credential
to decrypt the transactions into the blocks.
So, if the training data are present on a blockchain
system, the possibility of data poisoning attacks
by an attacker is reduced significantly.
Table 1 describes the performance of the ML
models without data poisoning attacks. It is
assumed that 0% noise insertion in the datasets
means no data poisoning attacks. Compared
with the results shown in Figures 5 and 6, it is
clear that if the data are put into private blockchains,
the performance of the ML models significantly
improved (see Table 1).
CONCLUSION
In this article, a private blockchain-enabled
security system has been suggested for homemonitoring
in the IoMT-enabled COVID-19 situation. The
proposed system makes use of both blockchain
technology and AI-based big data analytics. The
blockchain-based implementation has been performed
in computing computational time when the
number of blocks minedand the numberof transactions
in a block are varied. It is also shown that the
70
blockchain helps in achieving better security and
at the same time, AI also helps for efficient big data
analytics. In recent years, the lattice-based cryptographic
techniques have been applied inhealthcare
systems,15 because of its superior security and
computational efficiency as compared to the traditional
public-key cryptosystems. In future, we
would like to improve the proposed framework
using lattice-based cryptosystem.
ACKNOWLEDGMENTS
This work was supported by the Basic Science
Research Program through the National
Research Foundation of Korea (NRF) funded
by the Ministry of Education under Grant
2020R1I1A3058605.
&REFERENCES
1. R. Guo, G. Yang, H. Shi, Y. Zhang, and D. Zheng, " O3R-CP-ABE:
An efficient and revocable attribute-based
encryption scheme in the cloud-assisted IoMT system, "
IEEEInternetThings J., vol. 8, no. 11, pp. 8949-8963,
Jun. 2021, doi: 10.1109/JIOT.2021.3055541.
2. A. K. Das, M. Wazid, N. Kumar, M. K. Khan,
K. K. R. Choo, and Y. Park, " Design of secure and
lightweight authentication protocol for wearable
devices environment, " IEEEJ. Biomed. Health
Informat., vol. 22, no. 4, pp. 1310-1322, Jul. 2018,
doi: 10.1109/JBHI.2017.2753464.
3. N. Garg, M. Wazid, A. K. Das, D. P. Singh, J. J. P. C.
Rodrigues, and Y. Park, " BAKMP-IoMT: Design of
blockchain enabled authenticated key management
protocol for Internet of Medical Things deployment, "
IEEEAccess, vol. 8, pp. 95956-95977, 2020,
doi: 10.1109/ACCESS.2020.2995917.
4. M. Seliem and K. Elgazzar, " BIoMT: Blockchain for the
Internet of Medical Things, " in Proc. IEEEInt. Black
Sea Conf. Commun. Netw., 2019, pp. 1-4,
doi: 10.1109/BlackSeaCom.2019.8812784.
TABLE 1. Performance of ML models without data
poisoning attacks.
IEEE Consumer Electronics Magazine
http://dx.doi.org/10.1109/JIOT.2021.3055541 http://dx.doi.org/10.1109/JBHI.2017.2753464 http://dx.doi.org/10.1109/ACCESS.2020.2995917 http://dx.doi.org/10.1109/BlackSeaCom.2019.8812784
IEEE Consumer Electronics Magazine - May/June 2023

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - May/June 2023
