A Survey on COVID-19 Disease Detection using Advanced

Techniques

Sunil Dalal

, Arvind Kumar Tiwari

, Jyoti Prakash Singh

Computer Science Department, Kamla Nehru Institute of Technology, Sultanpur, UP, India

Computer Science Department, National Institute of Technology, Patna, Bihar, India

Keywords: Machine Learning, Deep Learning,COVID-19

Abstract: Coronavirus disease (COVID-19) has become the most dangerous pandemic in worldwide. The World Health

Organization (WHO) has declared COVID-19 as an outbreak that has placed a heavy burden on all nations.

Health sector has included the help of emerging technology including Machine Learning, Artificial

intelligence, Deep Learning, Internet of Things, Block chain and etc. to battle and look ahead against the new

diseases. In recognizing and recommending the production of a vaccine for COVID-19, various advanced

technologies may play a vital role. In this paper, we provide a brief survey on COVID-19 detection of disease

based on 75 collected papers. Furthermore, a study on recently used techniques, their limitations and

applications is also included in this survey.

INTRODUCTION

The advent of the second decade of the 21st cen-tury

is marked by the outbreak of extremely contagious

and equally dangerous Severe Acute Respiratory

Syndrome-Corona virus (SARS-CoV). The epicenter

of the COVID-19 is found to be Wuhan, Hubei

Province, China, in the sea food market and traces its

origin in Bats. With time, for the last few months this

epicenter has shifted it’s allocation toItaly and now is

reaching America and other continents. This has led

to declare COVID-19 as pandemic and a situation of

Global Health emergency. To combat this new threat

India has already taken various steps and has gone

under complete lockdown. This move is seen as a step

to flatten the curve of this pandemic to release

pressure on the medical infrastructure and to allow for

its containment. The demand for medicines and

medical types of equipment such as Ventilators has

been skyrocketing and India is trying its level best to

match the need. Intensive care units are being built to

ensure the safety of the people. According to WHO,

this pandemic will have huge repercussions shortly

and can come down heavily on the health

infrastructure and economy of various nations. It is

expected that it will grow in the recent future but in a

controlledmanner.

In this paper, our aim is to provide the answer of

following questions:

•

What are the recent techniques used in the

COVID-19 disease detection in computer science

domain?

•

What are the limitations of techniques in the

COVID-19 diseasedetection?

•

What are the applications in COVID-19 disease

detection?

For this, we have collected 75 published papers

based on COVID-19 disease detection. After that,

based on the keyword and abstract, we categorize all

papers into various category. Figure 1 elaborates the

total numbers of papers in different category. Here,

ML, DL, and AI denote machine learning, deep

learning, and artificial intelligence (AI) respectively.

IoT and BC identify the internet of things and block

chain respectively. Remaining part of the paper is

elaborated as: section 2 highlights the related work on

COVID 19. Furthermore, related work includes the

comparative study of recent works on COVID-19. In

section 3, we provide the brief information about

techniques used in COVID-19 diseas prediction.

After that, limitations of various techniques are

discussed in section4. In section5, we provide the

various applications of AI. At the end, section 6

concludes the paper.

Dalal, S., Tiwari, A. and Singh, J.

A Survey on COVID-19 Disease Detection using Advanced Techniques.

DOI: 10.5220/0010564500003161

In Proceedings of the 3rd International Conference on Advanced Computing and Software Engineering (ICACSE 2021), pages 159-164

ISBN: 978-989-758-544-9

159

Figure 1: Distribution of selected papers.

RELATED WORK

(Wu et al., 2020), December 2019 saw an out break

of severe acute respiratory syndrome(SARS) coro In

this paper (Zhangetal.,2020), the rationale behind

SARS-CoV using ACE2-receptor as a point of entry

into cells is observed and studied. Benvenuto et al.

have proposed to study the evolution and spread of

COVID-19 (Benvenuto et al., 2020). The Johns

Hopkins epidemiological data isused in ARIMA

model to predict the pattern of growth of COVID-

19.The work of Liao et al. (Liao et al., 2020) is to

prepare Intensive Care Units (ICU) in such a way that

they can be used to isolate and treat extreme cases of

COVID-19. The extreme cases pose serious threat to

other people and hence need to be handled properly.

Shanmugaraj et al. (Shanmugaraj et al., 2020) have

provided a constructive discussion on the outbreak of

COVID- 19. (Al-Qaness et al., 2020) have introduced

a modified form of the flower pollination algorithm

(FPA) is used along with the salp swarm algorithm

(SSA). It is called FPASSA and improves the

performance of the adaptive neuro-fuzzy inference

system (ANFIS) by determining optimal values of the

parameters. Xu et al. (Xu et al., 2020) have published

a systemati-cally review on COVID-19 and then

compare between SARS-CoV and SARS-CoV-2 in

the matter of their originations, incubations, treatment

methods and di-agnosis, pathogenic mechanisms, and

proteomic and genomic sequences is the goal of this

paper. Gralinski and Menachery (Gralinski and

Menachery, 2020) have given stress to use historical

pandemics data with latest tools to handle group 2B

coronavirus.

In paper corona virus in the Wuhan, Hubei

province, China. The ability of the virus to spread

from animals to humans highlights its threat to global

health. Looking at the gravity of corona virus crisis, it

is the moral responsibility of all academic journals,

websites to share the data related to COVID-19 for

research and prevention measures (Wu and Poo,

2020). This is a technical guidance created for

instructing centres to controll disease at all possible

level sand describe the procedure for conducting

laboratory testing of the unexplained pathogens

causing viral pneumoniain Wuhan, China (National et

al., 2020). Andersen et al. have reviewed and studied

the discovery and development of broad-spectrum

antiviral agents (BSAAs) and identify different drug

combinations for the treatment of various viral

infections (Andersen et al., 2020). With the death of

Dr. Li Wenliang, the doctor who first found SARS-

Cov-2 in Wuhan, China; the threat posed by SARS-

Cov-2 to the clinicians treating people and to the

frontline workers has become evident and needs to be

handled very efficiently (Petersen et al., 2020). Wang

et al. (Wang et al., 2020) have mentioned that The

outbreak of COVID-19 in Wuhan should

continuously be monitored and necessary and strict

public health measures should be implemented in

phased manner till the infection reaches to an ideal

level. Liu et al. (Liu et al., 2020) have reviewed that

the average basic reproduction number (R0) of

COVID- 19 is 3.28 which over whelmingly exceeds

WHO estimates of 1.4 to 2.5. Abbad et al. (Abbad et

al., 2019) have provided the trend of an emerging

Middle East respiratory syndrome corona virus

(MERS- CoV). The first case of Coronavirus was

observed in Nov, 2019 in Wohan, China. In this

research paper the author (Schwartz and Graham,

2020) have mentioned about the effect of on infection

of SARS-CoV and MERS-CoV on women during

their pregnancy.It is mentioned how pneumonia is

dangerous for pragnent women. According to this

research paper the major couse of indirect metarnel

death is pneumonia. Out of all the pragnent women

who are suffering from pneumonia there are 25%

pregnant women who need to be hospitalized and

their care to be taken. The observation of this research

is that pregnant women need extra care during the ir

pregnancy so that the risk of infection in pregnant

women can be reduced. For identifying the cases of

COVID-19,the idea of using the algorithms of

machine learning has been proposed (Rao and

Vazquez, 2020); In order to decrease the chances of

spread, the population with high risk can be

quarantined earlier as compared to population with

mid-risk or low-risk. The population with high-risk,

mid- risk and low-risk can be identified using AI by

collecting the details of previously affected cases. As

of February 20, 212 cases has been tested, out of

which only one case was positive and 211 cases

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

160

showed negative result in Nepal (Shrestha et al.,

2020). The confirmed case in Nepal is a 32 year old

male student studying in China, who returned to

Nepal for winter holidays on January 9. The Nepal

Government has taken several steps to take care and

many centres have been constructed. Several satellite

hospitals and network of five hubs has been

constructed in Kathmandu, at hub hospitals 55

isolation beds has been provided. In paper (Al Kahlout

et al., 2019), it is hard to identify from where the virus

has arrived. It is hard to identify its original source.

According to the analysis of phy-logenetic, the corona

virus is categorized as: alpha-, beta-, gamma-, and

delta-corona viruses.

In 2012, in the kingdome of Saudi Arabia, the

human beta-coronavirus (HcoV) which is a Middle

East respiratory syndrome coronavirus (MERS-CoV)

was identified. Until 2017, 21 cases have been

identified, in the state of Qatar. Out of these 21 cases

33.33% (7cases) results to death. Among all 21 cases

20 were male and only one female case was reported,

in Qatar. Isolation was initially done in Qatar. In this

research paper (Reusken et al., 2020), the idea for

molecular test of 2019-nCoV has been discussed. It is

mentioned that out of 30 EU/EEA countries 24

countries has already implemented the above test. In

this research paper (Nishiuraetal., 2020),there

analysis of spreading of coronavius is done.

Epidemiological Analysis isdone by analyzing

epidemic curve in three steps. As a result it has been

observed that epidemic curve is consistent. It is hard

to say that there is any zoonotic transmission occurred

because there is no proof that the virus in animal sold

on the market. According to this research paper (Ji et

al., 2020), there are 70641 cases of corona virus are

confirmed by February 16, 2020, out of these 70641

cases 1772 are deaths.2.5% is the average mortality,

while the mortality rate of Wohan is greater than 3%.

New local medical facilities are built by China

Government. Kock et al. (Rahimi and Abadi, 2020)

have mentioned that the humans affected by corona

virus may suffer from cold. The genome of 2019-

nCoV are related to the bat corona viruses and SARS-

CoV. The main reason of spreading 2019-nCoV is

considered the seafood abdanimal market in Wohan,

China. In spite of this, Table 1 shows the comparative

study of some recent papers that use various

algorithms/techniques (Bhattacharya et al., 2021; Suri

et al.,2021).

From literature review, we observe various

techniques used in the COVID-19 disease prediction.

ADVANCED TECHNIQUES

•

Machine learning: The aim of machine learning is

to develop algorithms that can learn and create

mathematical models for data processing and

prediction. On the basis of the data presented, the

ML algorithms should be able to learn by

themselves and make specific predictions without

having been specifically trained for a given task. In

recent years, not only computer scientists and AI

algorithm manufacturing specialists have seen rapid

development beyond theoretical developments in

the application of machine learning, but also other

researchers in different fields who are applying

these techniques for their own purposes. Chemical

and material sciences have been affected by the

usage of machine learning to speed certain

analytical activities or to solve problems for which

traditional simulation methods are ineffective,

among many other fields of research. A subset of

machine learning based on artificial neural

networks (ANNs), deep learning is targeted at

further escalating AI developments.

•

Deep learning: Deep learning is an AI function

that emulates the functions of the human mind in

the analysis of image classification data, voice

recognition, translation of expression, and

strategic thinking. Deep learning AI is capable of

learning without proper supervision, trying to on

both unstructured and unlabeled data. A deep

neural network is an ANN with several layers

between the input and output layers (DNN). Each

architecture has found success in specific domains.

Unless they have been tested on the same data set,

the performance of different architectures cannot

always be correlated.

•

Artificial Intelligent: AI refers to any human

thought exhibited in computer science by a

computer, robot, or another machine. AI refers to

a computer or machine’s ability to imitate the

human mind’s commonly used abilities, to learn

from illustrations and knowledge, to recognize

objects, to interpret and respond to language, to

make decisions, to solve problems, and to

integrate these and other abilities to perform tasks

that a person might perform.

•

Blockchain: Blockchain’s implementation seems

to be complex, which it can undoubtedly be, but the

core principle is indeed very clear. A blockchain is

a form of a ledger. In order to be able to grasp the

blockchain, you first need to understand what a

network actually is. Blockchain systems

compensate

for the difficulties of security and

A Survey on COVID-19 Disease Detection using Advanced Techniques

161

Table 1: Table for covid cases

and confidence in many respects. First, there is

still linear and chronological storage of fresh

blocks usable. That is, the ’end’ of the blockchain

is still attached to them. ”You can find that each

block has a ”height” location on the chain when

you look at the Bitcoin network.

•

The Internet of Things (IoT): It comprises a

system of interconnected, internet-connected

devices that can capture and transmit data across a

wifi connection without human interference.

Endless individual or company possibilities exist.

A ’device’ can apply to a connected medical

system, a biochip transponder (think livestock), a

solar panel, a connected car with sensors that warn

the driver to a number of potential problems (fuel,

tyre pressure, maintenance needed, and more) or

any object fitted with sensors that can collect and

relay information through a network.

Figure 2: Mutation stages of COVID-19

CHALLENGES AND ISSUES

The problems and problems related to DL integration

for computational biology for COVID19 disease

outbreak management in green infrastructure are

described below:

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

162

Table 2: Applications

•

Privacy Availability of large data and greater

collections from COVID-19 is a significant

obstacle given medical customer privacy.

•

Pattern The spread and outbreak of the disease

does not have a simple pattern. This has got a very

complex and different behavior from country to

country and time to time as covid-19 virus mutates

itself.

APPLICATIONS

Applications of the latest Techniques has been given

in the table 2.

CONCLUSION

This paper provides a brief survey on COVID-19

disease detection. For this, we have collected

various papers from different domains. Filtering

has been done based on the keywords well as abstract

of the collected papers and then selected the papers

from computer science background. We have

discussed the different works done using various

techniques and algorithm from machine learning,

deep learning, artificial intelligence, internet of things

and blockchain. Inspite of this, we have also

discussed bottleneck for these techniques and

algorithms. Applications of these techniques in

detecting COVID-19 have been analyzed. The

advantage of our survey is that it covers various

parameters and research directions for beginners.

REFERENCES

Abbad, A., Perera, R. A., Anga, L., Faouzi, A., Minh, N.

N. T., Malik, S. M. M. R., Iounes, N., Maaroufi, A., Van

Kerkhove, M. D., Peiris, M., et al. (2019). Middle east

respiratory syndrome coronavirus (mers-cov)

neutralising antibodies in a high-risk human population,

morocco, november 2017 to january 2018.

Eurosurveillance, 24(48):1900244.

Al Kahlout, R. A., Nasrallah, G. K., Farag, E. A., Wang,

L.,Lattwein,E.,Mu¨ller,M.A.,ElZowalaty,M.E.,

Romaihi, H. E., Graham, B. S., Al Thani, A. A., et al.

(2019). Comparative serological study for the

prevalence of anti-mers coronavirus antibodies in high-

A Survey on COVID-19 Disease Detection using Advanced Techniques

163

and low-risk groups in qatar. Journal of immunology

research,2019.

Al-Qaness, M. A., Ewees, A. A., Fan, H., and Abd El Aziz,

M. (2020). Optimization method for forecasting confirmed

cases of covid-19 in china. Journal of Clinical

Medicine,9(3):674.

Andersen, P. I., Ianevski, A., Lysv and, H., Vitkauskiene,

A.,Oksenych,V.,Bjøra˚s,M.,Telling,K.,Lutsar, I.,

Dumpis, U., Irie, Y., et al. (2020). Discovery and

development of safe-in-man broad-spectrum antiviral

agents. International Journal of Infectious Diseases,

93:268–276.

Benvenuto, D., Giovanetti, M., Vassallo, L., Angeletti, S.,

and Ciccozzi, M. (2020). Application of the arima

model on the covid-2019 epidemic dataset. Data in

brief, 29:105340.

Bhattacharya, S., Maddikunta, P. K. R., Pham, Q.-V.,

Gadekallu, T. R., Chowdhary, C. L., Alazab, M., Piran,

M. J., et al. (2021). Deep learning and medical image

processing for coronavirus (covid-19) pandemic: A

survey. Sustainable cities and society, 65:102589.

Gralinski, L.E. and Menachery, V. D. (2020). Returnofthe

coronavirus: 2019-ncov. Viruses,12(2):135.

Ji, Y., Ma, Z., Peppelenbosch, M. P., and Pan, Q. (2020).

Potential association between covid-19 mortality and

health-care resource availability. The Lancet Global

Health, 8(4):e480.

Liao,X.,Wang, B.,and Kang, Y. (2020).Novelcoronavirus

infection during the 2019–2020 epidemic: prepar ing

intensive care units—the experience in sichuan

province, china. Intensive care medicine, 46(2):357–

360.

Liu, Y., Gayle, A. A., Wilder-Smith, A., and Rocklo¨v,

J. (2020). The reproductive number of covid-19 is higher

compared to sars coronavirus. Journal of travel

medicine.

National, H. C. O.T.P.,Republic,O.C.,et al.

(2020).Technical guidance for laboratory testing of

2019-ncov infection.

Nishiura, H., Linton, N. M., and Akhmetzhanov, A. R.

(2020). Initial cluster of novel coronavirus (2019- ncov)

infections in wuhan, china is consistent with substantial

human-to-human transmission.

Petersen, E., Hui, D., Hamer, D. H., Blumberg, L.,Madoff,

L. C., Pollack, M., Lee, S. S., McLellan,

S.,Memish,Z.,Praharaj,I.,etal.(2020).Liwenliang,afacet

othe frontline healthcare worker. the first doctor to

notify the emergence of the sars-cov-2,(covid-

19),outbreak. International Journal of Infectious

Diseases,93:205– 207.

Rahimi, F. and Abadi, A. T. B. (2020). The uncertainties

underlying herd immunity against covid-19.

Rao, A. S. S. and Vazquez, J. A. (2020). Identification of

covid-19 can be quicker through artificial intelligence

framework using a mobile phone–based survey when

cities and towns are under quarantine. Infection Control

& Hospital Epidemiology, 41(7):826–830.

Reusken, C. B., Broberg, E. K., Haagmans, B., Meijer, A.,

Corman, V. M., Papa, A., Charrel, R., Drosten, C.,

Koopmans, M., Leitmeyer, K., et al. (2020). Laboratory

readiness and response for novel coronavirus (2019-

ncov) in expert laboratories in 30 eu/eea

countries,january2020.Eurosurveillance,25(6):200008

Schwartz, D. A. and Graham, A. L. (2020). Potential

maternal and infant outcomes from (wuhan)

coronavirus 2019-ncov infecting pregnant women:

lessons from sars, mers, and other human coronavirus

infections. Viruses, 12(2):194.

Shanmugaraj, B., Malla, A., and Phoolcharoen, W. (2020).

Emergence of novel coronavirus 2019-ncov: need for

rapid vaccine and biologics development. Pathogens,

9(2):148.

Shrestha, R., Shrestha, S., Khanal, P., and Kc, B. (2020).

Nepal’s first case of covid-19 and public health

response. Journal of travel medicine,27(3):taaa024.

Suri, J. S., Agarwal, S., Gupta, S. K., Puvvula, A., Biswas,

M., Saba, L., Bit, A., Tandel, G. S., Agarwal, M.,

Patrick, A., et al. (2021). A narrative review on

characterization of acute respiratory distress syndrome

in covid-19-infected lungs using artificial intelligence.

Computers in Biology and Medicine, page104210.

Wang, H., Wang, Z., Dong, Y., Chang, R., Xu, C., Yu, X.,

Zhang, S., Tsamlag, L., Shang, M., Huang, J., et al.

(2020). Phase-adjusted estimation of the number of

coronavirus disease 2019 cases in wuhan, china. Cell

discovery, 6(1):1–8.

Wu, C.-I. and Poo, M.-m. (2020). Moral imperative for

immediate release of 2019-ncov sequence data.Wu,

F.,Zhao, S., Yu,B., Chen, Y.-M.,Wang,W., Song,Z.-G.,

Hu, Y., Tao, Z.-W., Tian, J.-H., Pei, Y.-Y., etal. (2020).A

new corona virus associated with human respiratory

disease in china.Nature,579(7798):265–269.

Xu, J., Zhao, S., Teng, T., Abdalla, A. E., Zhu, W.,

Xie,L.,Wang,Y.,andGuo,X.(2020).Systematic

comparison of two animal-to-human transmitted human

coronaviruses:Sars-cov-2andsars-

cov.Viruses,12(2):244.

Zhang,H.,Penninger,J.M.,Li,Y.,Zhong,N.,andSlutsky,

A.S.(2020).Angiotensin-converting enzyme2(ace2) as a

sars-cov-2 receptor: molecular mechanisms and

potential therapeutic target. Intensive care me.

ICACSE 2021 - International Conference on Advanced Computing and Software Engineering

164