Amalgamation of Fog Computing and Software Deﬁned Networking in

Healthcare 4.0: The Challenges, and a Way Forward

Khushi Shah

1 a

, Mohammad S. Obaidat

2,3,4,∗

, Preet Modi

1 b

, Jitendra Bhatia

1 c

, Sudeep Tanwar

5,∗∗

and Balqies Sadoun

Vishwakarma Government Engineering College, Gujarat Technological University, Ahmedabad, Gujarat, India

College of Computing and Informatics, University of Sharjah, U.A.E.

KAIST, University of Jordan, Jordan

University of Science and Technology Beijing, China

Department of CSE, Institute of Technology, Nirma University, Ahmedabad, Gujarat, India

College of Engineering, Al-Balqa’ Applied University, Al-Salt, Jordan

Keywords:

Healthcare, Cloud Computing, Fog Computing, Software Deﬁned Networking.

Abstract:

Rapid recent advances in automated data collection routines have led to a tsunami of health care oriented data

stored in the distributed, heterogeneous, and a large databases. Healthcare is one of the pioneering ﬁelds that

has started using Machine Learning (ML) and IoT (Internet of Things) for increasing life expectancies and

decreasing death risks. Since then, major improvements are being witnessed for achieving real-time results

and decreasing latency. This work attempts to provide an extensive and objective walkthrough in the direction

of adoption of fog computing and software deﬁned networking (SDN) framework for a huge data processing

in healthcare domain. Both of these technologies, holds a great promise for the healthcare industry. In this

paper, ﬁrst of all, we survey various communication technologies involved in heathcare and also discuss the

need of data processing and its security. Finally, we conclude with future research issues and challenges in

this domain.

1 INTRODUCTION

Health is a prominent aspect for concern to human.

Healthcare sector is growing on an expeditious scale.

With the increase in living expectancy of people, the

aging population is increasing by the day which is

the major reason to bring in advancements in health-

care that are effective, essential and most importantly-

quick (Vora et al., 2017). The main purpose of includ-

ing IoT in healthcare is to provide real-time results for

patients in critical conditions. The Summary of vari-

ous notations used in the paper is given in Table 1.

https://orcid.org/0000-0001-9157-5245

https://orcid.org/0000-0001-7172-125X

https://orcid.org/0000-0002-2375-5057

Fellow of IEEE and Fellow of SCS

Member, IEEE

Table 1: Summary of Notations.

Abbreviation Description

IoT Internet of Things

CC Cloud computing

FC Fog computing

SDN Software deﬁned network

RFID Radio-Frequency identiﬁcation

DL Deep Learning

DN Deep Network

ML Machine Learning

DT Decision Trees

NB Naive Bayes

KNN K-Nearest Neighbours

SVM Support Vector Machine

RF Random Forests

ANN Artiﬁcial Neural Network

BBN Bayesian Belief Network

1.1 IoT in Healthcare

IoT provides an end-to-end communication and proc-

essing. This archetype is an ecosystem of connected

Shah, K., Obaidat, M., Modi, P., Bhatia, J., Tanwar, S. and Sadoun, B.

Amalgamation of Fog Computing and Software Deﬁned Networking in Healthcare 4.0: The Challenges, and a Way Forward.

DOI: 10.5220/0009911300250032

In Proceedings of the 17th International Joint Conference on e-Business and Telecommunications (ICETE 2020) - Volume 3: ICE-B, pages 25-32

ISBN: 978-989-758-447-3

Figure 1: Organization of Paper.

devices that are accessible through the Internet. In-

ternet of Things (IoT)-enabled devices have made re-

mote monitoring in the healthcare sector possible and

results into superlative care by physicians. Besides,

remote checking of patient’s wellbeing helps in de-

creasing the length of hospital stay and preventing re-

admission. IoT also has a major impact on treatment

outcome and signiﬁcant reduction in healthcare costs.

However, monitoring all these objects in real time

is really difﬁcult. These devices inter-communicate

and generate an enormous amount of data. The man-

agement of this massive amount of data generated is

a hassle. Smart and efﬁcient utilization of this data

could proves to be beneﬁcial. We need to process and

analyze these data for various applications.

1.2 Data Processing and Analysis in

Healthcare

The data generated due to millions of interactions be-

tween these objects is usually unstructured and not

effectively employed. The expansion of healthcare-

speciﬁc IoT devices opens up large number opportu-

nities and the huge amount of data generated hold the

potential to transform the healthcare. Data Process-

ing helps in structuring of this raw data, whereas data

analysis plays a crucial role in handling this misman-

aged data. By performing proper segregation of data,

proﬁtable data sets can be obtained. The analysis of

these data sets can generate trends to track and mon-

itor the human health anatomy. These processes can

be performed on a high performance compute engine

like cloud.

1.3 Cloud Computing in Healthcare

Buying and maintaining expensive hardware devices

for computations can be quite expensive; computer

resources can be made available whenever and wher-

ever needed with the help of cloud computing. In

simple words, cloud computing(CC) is pay for what

you use. This term refers to allocation of com-

puter resources as per demands or requirements of

the user and charging for the same(Shah et al., 2019).

The data obtained from the IoT devices is sent to

the cloud for data processing and analysis to gener-

ate trends and perform calculations (Lakshmanachari

et al., 2017)(Bhatia et al., 2012). The vital informa-

tion of the patients can be sent to cloud compute en-

gine for data processing and trends are accordingly

generated and obtained as reports. The only draw-

backs with cloud computing are heavy load or trafﬁc

and delay in response time. The patient oriented IoT

is delay sensitive, so there is a need of a paradigm

which does the nearest computing or server ofﬂoad-

ing(Jaykrushna et al., ).

1.4 Fog Computing in Healthcare

Fog computing works as an intermediate layer be-

tween the cloud and the IoT devices. The data ob-

tained from the source, is ﬁrst sent to the fog devices

to perform critical computations that require imme-

diate processing. It increases the efﬁciency of the

network by providing real time results to the devices

nearer to the network (Verma and Sood, 2018) (Ku-

mari et al., 2019) (Guelzim et al., 2016) (Tanwar et al.,

2017). Fog computing or edge computing overcomes

the latency issues. This approach usually involves a

three layered architecture. The layers can be classi-

ﬁed as:

1. Data Source Layer

2. Fog Layer

3. Cloud Layer.

Fog Layer is also beneﬁcial with regard to security

aspects (Hathaliya and Tanwar, 2020).

1.5 Software Deﬁned Networking in

Healthcare

Healthcare organizations are under pressure to scale

and upgrade their network infrastructure to cope up

ICE-B 2020 - 17th International Conference on e-Business

Figure 2: Three Layered Architecture(Wadhwa and Aron, 2018) (Tanwar et al., 2020).

with latest medical technologies for patient care (Vora

et al., 2018) (Tanwar et al., 2018a) (Tanwar et al.,

2020a). While addressing these needs, upgraded net-

works can avail the advantage of SDN’s programma-

bility, speed, ﬂexibility and agility. SDN is a rising

paradigm that aims at providing the facility to pro-

gram the network. With SDN, creating new notions

in networking is possible (Bhatia et al., 2017)(Bhatia

et al., 2018).

SDN helps in innovation and evolution of the net-

works along with drastically simplifying the network

management. It does so, by decoupling the soft-

ware logic from the hardware to apply new protocols

with ease. An adoption of the SDN in the three lay-

ered architecture improves the efﬁciency of the sys-

tem by selecting the appropriate node of the fog layer

and provides real-time results with the minimum de-

lay(Bhatia et al., 2020).

1.6 Contributions

The primary objective of this paper is to give an in-

sight of the current ongoing technologies used and the

future directions and scopes in the area of healthcare

and smart health homes(Azibek et al., 2020). We have

also provided key apprehension of the ML algorithms

used in the past.

• We reviewed the existing survey of the past few

years by comparing and brieﬁng the various tech-

nologies used in the ﬁeld of healthcare.

• We categorised the review, on the basis of differ-

ent approaches used.

• We also projected the future scopes in the ﬁeld of

healthcare.

The organization of the paper is shown in the Fig. 1.

2 RELATED WORK

A lots of work has been done in healthcare us-

ing IoT, fog computing and cloud computing(Bhatia

and Kumhar, 2015)(Obaidat and Nicopolitidis, 2016).

Some of the relevant works have been included in this

survey. The review is done based on the communica-

tion and compute engine technologies. We also pro-

vide coverage of various emerging trendy technolo-

gies used in healthcare domain. The taxonomy of the

review work is shown in the Fig. 3.

2.1 Communication Technologies

RFID communicates via radio waves which can be

used in healthcare to keep a track of patients, staff and

equipments and hence, facilitating the monitoring of

in and out of the hospital. In 2017, Lakshmanachari

et al.(Lakshmanachari et al., 2017) used RFID, which

works on a frequency of 125 kHz. This was beneﬁcial

in terms of low power consumption, low complexity

and high portability, which are some of the impor-

tant aspects in area of healthcare. In 2018, Kumari

et al.(Kumari et al., 2018) have suggested, the use of

RFID, Wi-Fi, 5G and Zigbee in fog computing to de-

crease the latency and increase in network bandwidth.

While in 2019, Rahman et al.(Rahman et al., 2019)

have stated that, with the use of 5G D2D non-licensed

Amalgamation of Fog Computing and Software Deﬁned Networking in Healthcare 4.0: The Challenges, and a Way Forward

Figure 3: Taxonomy of the related work.

spectrum advancement, different critical IoT data can

be conﬁgured by keeping in consideration various pa-

rameters like latency and jitter. Pasquale et al.(Pace

et al., 2018) have proposed a system to support mo-

bile healthcare using Zigbee and Wi-Fi in 2018.

2.2 Compute Engine

Authors in (Lakshmanachari et al., 2017) (Singh and

Malhotra, 2019) (Maini et al., 2018) (Bhatia, 2015)

have used cloud as their compute engine which has

proven to be a very convenient option to carry out

massive computations in the recent years. One of the

biggest reasons behind the success of CC is its cost

efﬁciency. In the ﬁeld of healthcare, a little delay in

results, can put a life in critical situation for the pa-

tients. The delay incurred in cloud computing can-

not be accepted in healthcare as data is sent to a re-

mote server for data processing and analysis. As these

servers are highly employed at all times, heavy trafﬁc

is a major concern and the data transmission to these

far off servers take a lot of time. These factors cause

the users to experience a time delay in the results.

Authors in (Verma and Sood, 2018) (George et al.,

2018) (Kumari et al., 2018) (Guibert et al., 2017) used

fog computation method, which is more efﬁcient then

cloud. In FC, the critical decisions for the computa-

tions that are to be made from the data obtained, are

processed at the fog node itself. Only the data storage

and little bit data analysis is to be made at the cloud.

Nevertheless, on the otherside, ﬁnding a nearest fog

node to the source node is a major challenge. To re-

solve this, Software Deﬁned Network (SDN) can be

used due to its global view of network infrastructure

(Tanwar et al., 2018b). SDN controls the data ﬂow

and chooses the optimal node from the scattered net-

work of fog nodes to achieve fast results with a min-

imal latency. The three layered architecture is shown

in Fig. 3.

2.3 Emerging Technologies

There is a signiﬁcant demand of ML and DL in the

healthcare sector to train the continuously streaming

data using an efﬁcient algorithm. The concept of in-

tegrating ML and DL can be of great use to gener-

ate accurate trends. The data involved in healthcare

is extremely sensitive and it needs to be protected.

Blockchain technology can be used for security provi-

sioning to the data ﬂowing in the network(Vora et al.,

2018b)(Vora et al., 2018a).

Machine Learning. Data obtained from the hospi-

tal can be structured or unstructured. The unstruc-

tured data needs to be processed to perform data an-

alytics. ML algorithms have proven to be an opti-

mal choice for performing data analysis on a large

data sets. Authors in (Chen et al., 2018) (Singh

and Malhotra, 2019)(Maini et al., 2018)(Ara

ujo et al.,

2016)(Yahyaoui et al., 2019) have used the state of the

art ML algorithms and analysed the medical data to

generate trends and results. In 2017, Chen et al.(Chen

et al., 2018) used CNN algorithm to predict diseases

from structured and text data with an accuracy of

0.9420 and recall of 0.9808. Authors in (Chen et al.,

2018) used traditional ML algorithms for the struc-

ICE-B 2020 - 17th International Conference on e-Business

tured data with an accuracy roughly around 0.5. Ta-

ble 3 shows the ML algorithms used and the objec-

tives fulﬁlled in different articles by researchers.

Deep Learning. An ANN (Artiﬁcial Neural Net-

work) with a lot of hidden layers is known as a

Deep Network and the method to train this network

is known as Deep Learning. This technique in-

volves higher number of parameters which results in

obtaining better trends and precise decision bound-

aries. Authors in (Purushotham et al., 2017) (Rajko-

mar et al., 2018) have implemented Deep Networks

to achieve higher accuracy than traditional ML Algo-

rithms. Pham et al. (Pham et al., 2017) used DL algo-

rithm to predict trajectories in Patient Health Records

and achieve F-score as high as 80 with the Diabetes

data set (Hathaliya et al., 2019).

Blockchain. Security is an important aspect while

handling the medical data. Recent advancements in

blockchain technology ensures the security of this

data. Authors in (Mettler, 2016) (Yue et al., 2016)

(Liang et al., 2017) (Hathaliya et al., 2019) have used

this technology to ensure security of various Health-

care Systems using blockchain technology for secu-

rity and interoperablity of Electronic Health Record

(EHR) Systems (Tanwar et al., 2020b). Yue et al.(Yue

et al., 2016) implemented a system where blockchain

authorizes the control of medical records of the pa-

tients and also proposed Multi-Party Computing mon-

itored by blockchain technology to ensure safety of

the healthcare data.

3 CASE STUDY

Prabal et al.(Verma and Sood, 2018) has proposed a

Fog-assisted IoT enabled health monitoring systems

for patients in smart homes where health data of 67

patients was systematically generated for 30 days to

check the validity of their model. This model follows

the three layered architecture comprising of the fol-

lowing.

1. Data Acquisition Layer: Timely data retrieval

from the IoT devices is performed at this layer. The

environmental and physiological parameters are ob-

tained from these devices and sent to the fog layer.

2. Fog Layer: The parameters obtained from the

IoT devices are converted into adequate format be-

fore sending them to the cloud. The event classiﬁ-

cation also takes place at this layer where the data is

Figure 4: Decision making.

categorised as normal or abnormal. When parameters

have higher values than usual, like high blood pres-

sure or high glucose level, they are considered to be

abnormal states. The BBN classiﬁer is used to calcu-

late the probability of occurrence of any critical event.

3. Cloud Layer: This layer focuses on extracting

or mining useful data from the fog layer in real-time.

The training algorithms runs on this layer using the

continuous data generated from source.

The parameters of the data can be classiﬁed to be

in SS (Safe State) or US (Unsafe State) for the pa-

tients. If it is an US, emergency alert is sent from the

fog layer to the source of data generation, otherwise,

the data is sent to cloud and timely results are gener-

ated. The decision making of the model is explained

in Fig. 4.

4 EXPERIMENTAL RESULTS

We used the Pima Indians diabetes dataset(Pim, ) to

predict if a person has diabetes or not, which com-

prises of various attributes such as BMI (Body Mass

Index), Age, Blood pressure, Glucose Level, Insulin

Level, Skin Thickness, etc., generated from differ-

ent IoT devices. The ﬁrst step, that is supposed to

be taken in this process is data preprocessing. This

data consists of several entries, where some of the at-

tributes were erroneous or outlier. For example, blood

pressure of a living person cannot be 0. These en-

tries can mislead our classiﬁer to learn false trends.

On performing data preprocessing on our dataset, the

number of entries decreased from 768 to 722. For

Amalgamation of Fog Computing and Software Deﬁned Networking in Healthcare 4.0: The Challenges, and a Way Forward

Table 2: ML Algorithms.

Year Author ML Algorithms used Objectives

2016 Gupta et al. (Gupta et al., 2016) InfoGain, Adaboost Chronic Disease Prediction

2016 Ara

ujo et al. (Ara

ujo et al., 2016) RF, NB, SVM, KNN Preauthorization for Healthcare Insurance

Providers (HIPs)

2017 Chen et al.(Chen et al., 2018) CNN, NB, KNN, DT To predict diseases from Structured and text

data

2018 Maini et al. (Maini et al., 2018) DT, NB, ANN Cardiovascular Disease Prediction

2019 Singh et al.(Singh and Malhotra,

2019)

RF To detect epileptic seizure

2019 Yahyaoui et al. (Yahyaoui et al.,

2019)

SVM, RF, CNN To predict diabetes

2019 Jadhav et al.(Jadhav et al., 2019) SVM, NB mHealth disease prediction system

Table 3: ML Algorithms.

ML Algorithms used Accuracy Obtained

KNN 65%

LR 67%

RF 75%

data analytics, we used the state-of-the-art ML algo-

rithms such as KNN, RF and LR. For the KNN al-

gorithm, we achieved an accuracy of 65% with F1

score as high as 0.72. F1 score is the metric com-

monly used for evaluation of a model. Only recall or

precision is not enough, so F1 score, a combination

of recall and precision is used. It is deﬁned as F1 =

2((recall * precision)/(recall + precision)). On using

the LR model, we achieved an accuracy of 67% with

a learning rate of 0.3 and 800 epochs. On the other

hand, with RF algorithm, the accuracy was boosted

up to 75.32% when applied with 100 estimators. This

data suggests that better results can be obtained from

the large unutilized data generated by the current IoT

network(s).

5 CONCLUSION

In this paper, we have provided insights about the evo-

lution in the ﬁeld of healthcare. It can be concluded

from the above literature review that CC limits the

infrastructure in terms of real-time results for criti-

cal data. This issue can be resolved with the help of

three layered architecture of FC along with SDN and

Cloud. Using ML and DL algorithms in the health-

care infrastructure for data analytics, generation of

precise and accurate trends is possible. The amal-

gamation of various communication technologies and

infrastructures will bring in an efﬁcient and effec-

tive development in the ﬁeld of healthcare and smart

health homes.

REFERENCES

Pima Indians Diabetes Database predict the on-

set of diabetes based on diagnostic measures.

http://https://www.kaggle.com /uciml/pima-indians-

diabetes- database. Accessed: 2019-12-28.

Ara

ujo, F. H., Santana, A. M., and Neto, P. d. A. S. (2016).

Using machine learning to support healthcare profes-

sionals in making preauthorisation decisions. Interna-

tional journal of medical informatics, 94:1–7.

Azibek, B., Zhigerova, S., and Obaidat, M. S. (2020). Smart

and efﬁcient health home system. In Emerging Re-

search in Data Engineering Systems and Computer

Communications, pages 677–691. Springer.

Bhatia, J., Dave, R., Bhayani, H., Tanwar, S., and Nayyar,

A. (2020). Sdn-based real-time urban trafﬁc analy-

sis in vanet environment. Computer Communications,

149:162–175.

Bhatia, J., Govani, R., and Bhavsar, M. (2018). Soft-

ware deﬁned networking: From theory to practice.

In 2018 Fifth International Conference on Parallel,

Distributed and Grid Computing (PDGC), pages 789–

794.

Bhatia, J. and Kumhar, M. (2015). Perspective study on

load balancing paradigms in cloud computing. IJCSC,

6(1):112–120.

Bhatia, J., Mehta, R., and Bhavsar, M. (2017). Variants

of software deﬁned network (sdn) based load balanc-

ing in cloud computing: A quick review. In Inter-

national Conference on Future Internet Technologies

and Trends, pages 164–173. Springer.

Bhatia, J., Patel, T., Trivedi, H., and Majmudar, V. (2012).

Htv dynamic load balancing algorithm for virtual ma-

chine instances in cloud. In 2012 International Sym-

posium on Cloud and Services Computing, pages 15–

20. IEEE.

Bhatia, J. B. (2015). A dynamic model for load balancing

in cloud infrastructure. Nirma University Journal of

Engineering and Technology (NUJET), 4(1):15.

Chen, M., Li, W., Hao, Y., Qian, Y., and Humar, I. (2018).

Edge cognitive computing based smart healthcare sys-

tem. Future Generation Computer Systems, 86:403–

411.

ICE-B 2020 - 17th International Conference on e-Business

George, A., Dhanasekaran, H., Chittiappa, J. P., Challa-

gundla, L. A., Nikkam, S. S., and Abuzaghleh, O.

(2018). Internet of things in health care using fog

computing. In 2018 IEEE Long Island Systems, Ap-

plications and Technology Conference (LISAT), pages

1–6. IEEE.

Guelzim, T., Obaidat, M., and Sadoun, B. (2016). Intro-

duction and overview of key enabling technologies for

smart cities and homes. In Smart cities and homes,

pages 1–16. Elsevier.

Guibert, D., Wu, J., He, S., Wang, M., and Li, J. (2017).

Cc-fog: Toward content-centric fog networks for e-

health. In 2017 IEEE 19th International Conference

on e-Health Networking, Applications and Services

(Healthcom), pages 1–5. IEEE.

Gupta, D., Khare, S., and Aggarwal, A. (2016). A method

to predict diagnostic codes for chronic diseases using

machine learning techniques. In 2016 International

Conference on Computing, Communication and Au-

tomation (ICCCA), pages 281–287. IEEE.

Hathaliya, J., Sharma, P., Tanwar, S., and Gupta, R.

(2019). Blockchain-based remote patient monitoring

in healthcare 4.0. In 2019 IEEE 9th International

Conference on Advanced Computing (IACC), pages

87–91.

Hathaliya, J. J. and Tanwar, S. (2020). An exhaustive sur-

vey on security and privacy issues in healthcare 4.0.

Computer Communications, 153:311 – 335.

Hathaliya, J. J., Tanwar, S., Tyagi, S., and Kumar, N.

(2019). Securing electronics healthcare records in

healthcare 4.0 : A biometric-based approach. Com-

puters & Electrical Engineering, 76:398 – 410.

Jadhav, S., Kasar, R., Lade, N., Patil, M., and Kolte, S.

(2019). Disease prediction by machine learning from

healthcare communities.

Jaykrushna, A., Patel, P., Trivedi, H., and Bhatia, J. Linear

regression assisted prediction based load balancer for

cloud computing. In 2018 IEEE Punecon, pages 1–3.

IEEE.

Kumari, A., Tanwar, S., Tyagi, S., and Kumar, N. (2018).

Fog computing for healthcare 4.0 environment: Op-

portunities and challenges. Computers & Electrical

Engineering, 72:1–13.

Kumari, A., Tanwar, S., Tyagi, S., Kumar, N., Obaidat,

M. S., and Rodrigues, J. J. P. C. (2019). Fog com-

puting for smart grid systems in the 5g environment:

Challenges and solutions. IEEE Wireless Communi-

cations, 26(3):47–53.

Lakshmanachari, S., Srihari, C., Sudhakar, A., and Nala-

jala, P. (2017). Design and implementation of cloud

based patient health care monitoring systems using

iot. In 2017 International Conference on Energy,

Communication, Data Analytics and Soft Computing

(ICECDS), pages 3713–3717. IEEE.

Liang, X., Zhao, J., Shetty, S., Liu, J., and Li, D. (2017).

Integrating blockchain for data sharing and collabora-

tion in mobile healthcare applications. In 2017 IEEE

28th Annual International Symposium on Personal,

Indoor, and Mobile Radio Communications (PIMRC),

pages 1–5. IEEE.

Maini, E., Venkateswarlu, B., and Gupta, A. (2018). Apply-

ing machine learning algorithms to develop a univer-

sal cardiovascular disease prediction system. In In-

ternational Conference on Intelligent Data Commu-

nication Technologies and Internet of Things, pages

627–632. Springer.

Mettler, M. (2016). Blockchain technology in healthcare:

The revolution starts here. In 2016 IEEE 18th Inter-

national Conference on e-Health Networking, Appli-

cations and Services (Healthcom), pages 1–3. IEEE.

Obaidat, M. S. and Nicopolitidis, P. (2016). Smart cities

and homes: Key enabling technologies. Morgan Kauf-

mann.

Pace, P., Aloi, G., Gravina, R., Caliciuri, G., Fortino, G.,

and Liotta, A. (2018). An edge-based architecture

to support efﬁcient applications for healthcare indus-

try 4.0. IEEE Transactions on Industrial Informatics,

15(1):481–489.

Pham, T., Tran, T., Phung, D., and Venkatesh, S.

(2017). Predicting healthcare trajectories from med-

ical records: A deep learning approach. Journal of

biomedical informatics, 69:218–229.

Purushotham, S., Meng, C., Che, Z., and Liu, Y.

(2017). Benchmark of deep learning models on

large healthcare mimic datasets. arXiv preprint

arXiv:1710.08531.

Rahman, M. A., Rashid, M., Barnes, S., Hossain, M. S.,

Hassanain, E., and Guizani, M. (2019). An iot

and blockchain-based multi-sensory in-home qual-

ity of life framework for cancer patients. In 2019

15th International Wireless Communications & Mo-

bile Computing Conference (IWCMC), pages 2116–

2121. IEEE.

Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N.,

Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al.

(2018). Scalable and accurate deep learning with elec-

tronic health records. NPJ Digital Medicine, 1(1):18.

Shah, N. B., Shah, N. D., Bhatia, J., Trivedi, Harshal”, e. S.,

Akashe, S., and Mahalle, P. N. (2019). Proﬁling-

based effective resource utilization in cloud environ-

ment using divide and conquer method. In Informa-

tion and Communication Technology for Competitive

Strategies, pages 495–508, Singapore. Springer Sin-

gapore.

Singh, K. and Malhotra, J. (2019). Iot and cloud computing

based automatic epileptic seizure detection using hos

features based random forest classiﬁcation. Journal

of Ambient Intelligence and Humanized Computing,

pages 1–16.

Tanwar, S., Parekh, K., and Evans, R. (2020a). Blockchain-

based electronic healthcare record system for health-

care 4.0 applications. Journal of Information Security

and Applications, 50:102407.

Tanwar, S., Parekh, K., and Evans, R. (2020b). Blockchain-

based electronic healthcare record system for health-

care 4.0 applications. Journal of Information Security

and Applications, 50:102407.

Tanwar, S., Trivedi, H., and Priyank, T. (2018a). Soft-

ware deﬁned network-based vehicular adhoc net-

works for intelligent transportation system: Recent

Amalgamation of Fog Computing and Software Deﬁned Networking in Healthcare 4.0: The Challenges, and a Way Forward

advances and future challenges. Futuristic Trends in

Network and Communication Technologies (FTNCT),

858:325–337.

Tanwar, S., Vora, J., Kaneriya, S., and Tyagi, S. (2017).

Fog-based enhanced safety management system for

miners. In 2017 3rd International Conference on

Advances in Computing,Communication Automation

(ICACCA) (Fall), pages 1–6.

Tanwar, S., Vora, J., Kaneriya, S., Tyagi, S., Kumar, N.,

Sharma, V., and You, I. (2020). Human arthritis analy-

sis in fog computing environment using bayesian net-

work classiﬁer and thread protocol. IEEE Consumer

Electronics Magazine, 9(1):88–94.

Tanwar, S., Vora, J., Tyagi, S., Kumar, N., and Obaidat,

M. S. (2018b). A systematic review on security issues

in vehicular ad hoc network. Security and Privacy,

1(5):1–23.

Verma, P. and Sood, S. K. (2018). Fog assisted-iot enabled

patient health monitoring in smart homes. IEEE Inter-

net of Things Journal, 5(3):1789–1796.

Vora, J., DevMurari, P., Tanwar, S., Tyagi, S., Kumar, N.,

and Obaidat, M. S. (2018a). Blind signatures based

secured e-healthcare system. In 2018 International

Conference on Computer, Information and Telecom-

munication Systems (CITS), pages 1–5. IEEE.

Vora, J., Italiya, P., Tanwar, S., Tyagi, S., Kumar, N., Obai-

dat, M. S., and Hsiao, K.-F. (2018b). Ensuring privacy

and security in e-health records. In 2018 International

Conference on Computer, Information and Telecom-

munication Systems (CITS), pages 1–5. IEEE.

Vora, J., Kaneriya, S., Tanwar, S., and Tyagi, S. (2018).

Performance evaluation of sdn based virtualization for

data center networks. In 2018 3rd International Con-

ference On Internet of Things: Smart Innovation and

Usages (IoT-SIU), pages 1–5.

Vora, J., Tanwar, S., Tyagi, S., Kumar, N., and Rodrigues,

J. J. (2017). Faal: Fog computing-based patient

monitoring system for ambient assisted living. In

2017 IEEE 19th international conference on e-health

networking, applications and services (Healthcom),

pages 1–6. IEEE.

Wadhwa, H. and Aron, R. (2018). Fog computing with the

integration of internet of things: Architecture, appli-

cations and future directions. In International Con-

ference on Parallel and Distributed Processing with

Applications, Ubiquitous Computing & Communica-

tions, Big Data & Cloud Computing, Social Comput-

ing & Networking, Sustainable Computing & Commu-

nications, pages 987–994. IEEE.

Yahyaoui, A., Rasheed, J., Jamil, A., and Yesiltepe, M.

(2019). A decision support system for diabetes predic-

tion using machine learning and deep learning tech-

niques.

Yue, X., Wang, H., Jin, D., Li, M., and Jiang, W. (2016).

Healthcare data gateways: found healthcare intelli-

gence on blockchain with novel privacy risk control.

Journal of medical systems, 40(10):218.

ICE-B 2020 - 17th International Conference on e-Business