3. Books Publications
Book(1) published Big Data Analytics and Artificial Intelligence Against
COVID-19: Innovation Vision and Approach by Hassanien,
Aboul-Ella, Dey, Nilanjan, Elghamrawy, Sally M.
https://www.springer.com/gp/book/9783030552572
Book (2) published Aboul Ella Hassanien, and Ashraf Darwsih, Digital
Transformation and Emerging Technologies for Fighting
COVID-19 Pandemic: Innovative Approaches, Studies in
Systems, Decision and Control, Springer 2020.
Book (3) published Muhammad Alshurideh, Aboul-Ella Hassanien, Ra’ed
Masa’deh,The effect of Coronavirus Disease (COVID-19)
on Business Intelligent Systems, Studies in Systems,
Decision and Control Springer series, 2020
Book(4) Running Aboul Ella Hassanien, Ashraf Darwish ,
Benjamin A. Gyampoh , Alaa tharwat, Ahmed M. Anter,
The Global Environmental Effects during and beyond
COVID-19: Intelligent Computing Solutions, Studies in
Systems, Decision and Control Springer series, 2020
Book(5) Running Sally Elghamrawy, Ivan Zilank and Aboul Ella Hassanien,
Advances in Data Science and Intelligent Data
Communication Technologies for COVID-19 Pandemic”
Studies in Systems, Decision and Control, 2021
Book(6) Running Ahmed Taher, and Aboul Ella Hassanien, Modeling,
Control and Drug Development for COVID-19 Outbreak
Prevention, Studies in Systems, Decision and Control, 2021
4. Journal Publication
Paper Abstracts
Dalia Ezzat, Aboul Ella Hassanien,
Hassan Aboul Ella "An optimized
deep learning architecture for the
diagnosis of COVID-19 disease
based on gravitational search
optimization," Applied Soft
Computing,
Impact Factor = 5.472
In this paper, a novel approach called GSA-DenseNet121-COVID-19 based on a hybrid
convolutional neural network (CNN) architecture is proposed using an optimization
algorithm. The CNN architecture used is called DenseNet121, and the optimization
algorithm used is called the gravitational search algorithm (GSA). The GSA is used to
determine the best values for the hyperparameters of the DenseNet121 architecture. To
help this architecture to achieve a high level of accuracy in diagnosing COVID-19 through
chest x-ray images. The obtained results showed that the proposed approach could
classify 98.38% of the test set correctly. To test the efficacy of the GSA in setting the
optimum values for the hyperparameters of DenseNet121. The GSA was compared to
another approach called SSD-DenseNet121, which depends on the DenseNet121 and the
optimization algorithm called social ski driver (SSD). The comparison results
demonstrated the efficacy of the proposed GSA-DenseNet121-COVID-19. As it was able to
diagnose COVID-19 better than SSD-DenseNet121 as the second was able to diagnose
only 94% of the test set. The proposed approach was also compared to another method
based on a CNN architecture called Inception-v3 and manual search to quantify
hyperparameter values. The comparison results showed that the GSA-DenseNet121-
COVID-19 was able to beat the comparison method, as the second was able to classify
only 95% of the test set samples. The proposed GSA-DenseNet121-COVID-19 was also
compared with some related work. The comparison results showed that GSA-
DenseNet121-COVID-19 is very competitive.
https://www.sciencedirect.com/science/article/pii/S1568494620306803
Zohair Malki, El-Sayed Atlam,
Aboul-Ella Hassanien, Guesh
Dagnew, Mostafa A.Elhosseini and
Ibrahim Gad "Association between
weather data and COVID-19
pandemic predicting mortality rate:
Machine learning approaches"
Chaos, Solitons & Fractals, Vol
138, September 2020, 110137,
Impact Factor = 3.764
Nowadays, a significant number of infectious diseases such as human coronavirus disease
(COVID-19) are threatening the world by spreading at an alarming rate. Some of the
literatures pointed out that the pandemic is exhibiting seasonal patterns in its spread,
incidence and nature of the distribution. In connection to the spread and distribution of the
infection, scientific analysis that answers the questions whether the next summer can save
people from COVID-19 is required. Many researchers have been exclusively asked
whether high temperature during summer can slow down the spread of the COVID-19 as it
has with other seasonal flues. Since there are a lot of questions that are unanswered right
now, and many mysteries aspects about the COVID-19 that is still unknown to us, in-depth
study and analysis of associated weather features are required. Moreover, understanding
the nature of COVID-19 and forecasting the spread of COVID-19 request more
investigation of the real effect of weather variables on the transmission of the COVID-19
among people. In this work, various regressor machine learning models are proposed to
extract the relationship between different factors and the spreading rate of COVID-19. The
machine learning algorithms employed in this work estimate the impact of weather
variables such as temperature and humidity on the transmission of COVID-19 by
extracting the relationship between the number of confirmed cases and the weather
variables on certain regions. We have collected the required datasets related to weather and
census features and necessary prepossessing to validate the proposed method. The
experimental results show that the weather variables are more relevant in predicting the
mortality rate compared to the other census variables such as population, age, and
urbanization. Thus, from this result, we can conclude that temperature and humidity are
important features for predicting COVID-19 mortality rate. Moreover, it is indicated that
the higher the value of temperature the lower number of infection cases
https://www.sciencedirect.com/science/article/pii/S096007792030
5336.
Arpaci, Ibrahim; Alshehabi,
Shadi; Al-
Emran,Mostafa; Khasawneh,
Mahmoud; Mahariq,
People started posting textual tweets on Twitter as soon as the novel coronavirus (COVID-
19) emerged. Analyzing these tweets can assist institutions in better decision-making and
prioritizing their tasks. Therefore, this study aimed to analyze 43 million tweets collected
between March 22 and March 30, 2020 and describe the trend of public attention given to
the topics related to the COVID-19 epidemic using evolutionary clustering analysis. The
5. Ibrahim; Abdeljawad,
Thabet; Hassanien, Aboul Ella.,
Analysis of Twitter data using
evolutionary clustering during the
COVID-19 pandemic" Computers,
Materials & Continua, vol.65, no.1,
pp.193-204, 2020,
Impact Factor = 4.89
results indicated that unigram terms were trended more frequently than bigram and trigram
terms. A large number of tweets about the COVID-19 were disseminated and received
widespread public attention during the epidemic. The high-frequency words such as
“death”, “test”, “spread”, and “lockdown” suggest that people fear of being infected, and
those who got infection are afraid of death. The results also showed that people agreed to
stay at home due to the fear of the spread, and they were calling for social distancing since
they become aware of the COVID-19. It can be suggested that social media posts may
affect human psychology and behavior. These results may help governments and health
organizations better understand the psychology of the public, thereby better
communicating with them to prevent and manage the panic.
https://www.techscience.com/cmc/v65n1/39561
Gitanjali R Shinde, Asmita B
Kalamkar, Parikshit N Mahalle,
Nilanjan Dey, Jyotismita Chaki,
Aboul Ella Hassanien
Shinde, G.R., Kalamkar, A.B.,
Mahalle, P.N. et al. Forecasting
Models for Coronavirus Disease
(COVID-19): A Survey of the State-
of-the-Art. SN COMPUT.
SCI. 1, 197 (2020).
COVID-19 is a pandemic that has affected over 170 countries around the world. The
number of infected and deceased patients has been increasing at an alarming rate in almost
all the affected nations. Forecasting techniques can be inculcated thereby assisting in
designing better strategies and in taking productive decisions. These techniques assess the
past situations, thereby enabling better predictions about the situation to occur in the
future. These predictions might help to prepare against possible threats and consequences.
Forecasting techniques play a very important role in yielding accurate predictions. This
study categorizes forecasting techniques into two types, namely, stochastic theory
mathematical models and data science/machine learning techniques. Data collected from
various platforms also play a vital role in forecasting. In this study, two categories of
datasets have been discussed, i.e., big data accessed from World Health
Organization/National databases and data from a social media communication. Forecasting
of a pandemic can be done based on various parameters such as the impact of
environmental factors, incubation period, the impact of quarantine, age, gender and many
more. These techniques and parameters used for forecasting are extensively studied in this
work. However, forecasting techniques come with their own set of challenges (technical
and generic). This study discusses these challenges and provides recommendations for the
people who are currently fighting the global COVID-19 pandemic.
https://link.springer.com/article/10.1007/s42979-020-00209-9
Ashraf Ewis, Guesh Dagnew, Ahmad
Reda, Ghada Elmarhomy, Mostafa A
Elhosseini, Aboul Ella Hassanien,
Ibrahim Gad, "ARIMA Models for
Predicting the End of COVID-19
Pandemic and the Risk of a Second
Rebound" Neural computing and
Application, Neural Comput &
Applic (2020).
Impact Factor = 4.774
Globally, many research works are going on to study the infectious nature of COVID-19
and every day. We learn something new about it by flooding the huge data that are
accumulating hourly rather than daily, which instantly opens hot research topics for
artificial intelligence researchers. However, the public’s concern by now is to find answers
to two questions; 1) when this COVID-19 pandemic will be over? and 2) After coming to
its end, will COVID-19 return again in what is known as a second rebound of the
pandemic?. This research developed a predictive model that can estimate the expected
period that the virus can be stopped and the risk of the second rebound of the COVID-19
pandemic. Therefore, this study considered the SARIMA model to predict the virus's
spread in several selected countries and is used for pandemic life cycle and end date
predictions. The study can predict the same for other countries as the virus's nature is the
same everywhere. This study's advantages are that it helps the governments make decisions
and planning now for the future, reduces anxiety, and prepares people's mentality for the
next phases of the pandemic. The most striking finding to emerge from this experimental
and simulation study is that the proposed algorithm shows that the expected COVID-19
infections for the top countries with the highest number of the confirmed case will
slowdown in October 2020. Moreover, our study forecasts that there may be a second
rebound of the pandemic in a year if the current precautions taken are eased completely.
We have to consider the uncertain nature of the current COVID-19 pandemic, and the
growing inter-connected and complex world; what are ultimately required are the
flexibility, robustness, and resilience to cope with the unexpected future events and
scenarios.
https://link.springer.com/article/10.1007/s00521-020-05434-0
7. E. El-shafeiy, A. E. Hassanien, K.
M. Sallam and A. A. Abohany,
"Approach for training a quantum
neural network to predict severity
of covid-19 in
patients," Computers, Materials &
Continua, vol. 66, no.2, pp. 1745–
1755, 2021.
Impact Factor = 4.89
Currently, COVID-19 is spreading all over the world and profoundly
impacting people’s lives and economic activities. In this paper, a novel
approach called the COVID-19 Quantum Neural Network (CQNN) for
predicting the severity of COVID-19 in patients is proposed. It consists of
two phases: In the first, the most distinct subset of features in a dataset is
identified using a Quick Reduct Feature Selection (QRFS) method to
improve its classification performance; and, in the second, machine
learning is used to train the quantum neural network to classify the risk. It
is found that patients’ serial blood counts (their numbers of lymphocytes
from days 1 to 15 after hospital admission) are associated with relapse
rates and evaluations of COVID-19 infections. Accordingly, the severity of
COVID-19 is classified into two categories, serious and non-serious. The
experimental results indicate that the proposed CQNN’s prediction
approach outperforms those of other classification algorithms, and its high
accuracy confirms its effectiveness.
https://www.techscience.com/cmc/v66n2/40661
Ismail Elansary, Walid Hamdy,
Ashraf Darwish and Aboul Ella
Hassanien, "Bat-inspired
Optimizer for Prediction of Anti-
Viral Cure Drug of SARS-CoV-2
based on Recurrent Neural
Network, Journal of System and
Management Sciences Vol. 10
(2020) No. 3, pp. 20-34
COVID-19 is a large family of viruses that causes diseases ranging from
the common cold to more severe SARS-CoV diseases. There are currently
several attempts to create an anti-viral drug to combat the virus. The
antiviral medicines could be promising treatment choices for COVID-19.
Therefore, a fast strategy for drug application that can be utilized to the
patient immediately is necessary. In this context, deep learning-based
architectures can be considered for predicting drug-target interactions
accurately. This is due to much complicated knowledge, such as
hydrophobic interactions, ionic interactions, and hydrogen bonding. In
this paper, the Recurrent Neural Network (RNN) is used to build a drug-
target interaction prediction model to predict drug-target interactions.
Bat Algorithm (BA) is used in this paper to optimize the model
parameters of RNN (RNN-BA) and then to use the Coronavirus as a
target. The drug with the best binding affinity will be a potential cure for
the virus. The proposed model consists of four phases; a data
preparation phase, hyper-parameters optimizing phase, learning phase,
and fine-tuning for specific ligand subsets. This paper's used dataset to
train and evaluate the proposed model is selected from a total of
677,044 SMILES. The experimental results of the proposed model
showed a high level of performance compared to the related approaches.
http://www.aasmr.org/jsms/Vol10/Vol.10.3.2.pdf
Sally M. Elghamrawy , Aboul Ella
Hassnien2,* and Vaclav Snasel
An Optimized Deep Learning-
Inspired Model for Diagnosis and
Prediction of COVID-19" CMC-
Computers, Materials & Continua
Impact Factor = 4.89
Abstract: This study aimed to develop a COVID-19 diagnosis and
prediction (AIMDP) model that could identify patients with COVID-19 and
distinguish it from other viral pneumonia signs detected in chest
computed tomography (CT) scans. The proposed system uses
convolutional neural networks (CNNs) as a deep learning technology to
process hundreds of CT images and speed up COVID-19 case prediction
to facilitate its containment. We employed the whale optimization
algorithm (WOA) to select the most relevant patient signs. A set of
experiments validated the AIMDP performance. It demonstrated the
superiority of AIMDP in terms of the area under curve - receiver
operating characteristic (AUC - ROC) curve, positive predictive value
(PPV), negative predictive rate (NPR) and negative predictive value (NPV).
AIMDP was applied to a dataset of hundreds of real data and CT images,
and it was found to achieve 96% AUC for diagnosing COVID-19 and 98%
for overall accuracy. The results showed the promising performance of
AIMDP for diagnosing COVID-19 when compared to other recent
diagnosing and predicting models.
O. M. Elzeki, Mahmoud. Y. Shams,
Shahenda Sarhan, Mohamed Abd
Chest X-ray (CXR) image is one of the most feasible diagnosis
modalities to early detect the infection of COVID-19 viruses,
8. Elfattah, Aboul
Ella Hassanien, COVID-19: A New
deep learning computer-aided
model for classification, PeerJ
Computer Science
Impact factor = 3.091
which is classified as a pandemic, according to the World Health
Organization (WHO) report in December 2019. COVID-19 is a
rapid natural mutual virus that belongs to the coronavirus
family. CXR scans are one of the vital tools to early detect
COVID-19 to monitor further and control its virus spread.
Classification of COVID-19 aims to detect whether a subject is
infected or not. In this paper, a model is proposed for analyzing
and evaluating grayscale Chest X-Ray images called Chest X-
Ray COVID Network (CXRVN) based three different COVID-
19 X-Ray datasets. The proposed CXRVN model is a
lightweight architecture that depends on a single fully connected
layer representing the essential features and thus reducing the
total memory usage and processing time verse pre-trained
models and others. The CXRVN adopts two optimizers; mini-
batch gradient descent and Adam optimizer, are applied, and the
model has almost the same performance. Besides, CXRVN
accepts CXR image in grayscale that is a perfect image
representation for CXR and consumes less memory storage and
processing time. Hence, CXRVN can analyze the CXR image
with high accuracy in a few milliseconds. The consequences of
the learning process focus on decision making using a scoring
function called SoftMax that leads to high rate true-positive
classification. The CXRVN model is trained using two different
datasets and compared to the pre-trained models: GoogleNet,
ResNet, and AlexNet, using the fine-tuning and transfer learning
technologies for the evaluation process. To verify the
effectiveness of the CXRVN model is evaluated in terms of the
well-known performance measures such as precision,
sensitivity, F1-score, and accuracy. The evaluation results based
on sensitivity, precision, recall, accuracy, and F1 score
demonstrated that, after GAN augmentation, the accuracy
reached 96.7% in experiment 2 (dataset-2) for two classes and
93.07% in experiment-3 (dataset-3) for three classes. While, the
average accuracy of the proposed CXRVN model is 94.5%.
Mohamed A. El-dosuk,
Mona Soliman, and Aboul
Ella Hassanien, Deep
neural network with
Cockroach hyperparameter
optimization for COVID-19
Viral Gene Sequences
Classi_cation between
COVID-19 and Inuenza
Viruses. International
Journal of Imaging Systems
and Technology.
Impact factor =1.925
It is also evident that distantly related viral proteins could
interact with a conserved cellular protein target and thus
increase their pathogenic potential. Among coronaviruses as
with many other viruses, receptor interactions are an important
determinant of species speciicity, virulence, and pathogenesis.
The pathogenesis of the COVID-19 depends on the ability of the
virus to attach to and enter into a suitable human host cell. This
paper presents a deep learning approach based on viral genome
virus sequencing to signi_cantly detects and di_erentiates
between COVID-19 and inuenza types (A, B, and C). The
architecture of the deep network is inspired by using a
cockroach optimization algorithm to optimize the deep neural
network hyperparasite. COVID-19 sequences are obtained from
repository 2019 Novel Coronavirus Resource, and inuenza A, B,
and C sub-datasets are obtained from other repositories. Five
hundred ninety-four unique sequences are used in the training
and testing process with 99% overall accuracy for the
classification model.
Mohamed Torky, Essam The fight against the COVID-19 pandemic still witnesses a lot of
9. Goda, Vaclav Snasel,
Aboul Ella Hassanein
Blockchain Mobil
Application System for
Detecting and Tracking the
Infected Cases of COVID-
19 Pandemic in Egypt,
Scintific Report, Nature.
2021
Impact factor = 3.998
struggles and challenges. The greatest challenge that most
governments are currently suffering from is the lack of a precise,
accurate, and automated mechanism for detecting and tracking the
new infected COVID-19 coronavirus cases. In response to this
challenge, this study proposes the first blockchain-based system
called COVID-19 Contact Tracing System (CCTS) to verify, track,
and detect the newly infected cases of COVID-19 coronavirus. The
proposed system consists of four coherent components: The
infection verifier subsystem, Mass Surveillance System, P2P mobile
application, and a blockchain platform for manage all transactions
between the three subsystem models. The proposed system has been
simulated and tested against a created dataset consists of 300
confirmed cases and 2539 contact persons. The evaluation results
proved that the proposed blockchain-based system achieved 75.79%
accuracy in recognizing the contact persons for COVID-19 patients.
The simulation results also clarified the proposed system's success
in performing self-estimation of Infection probability and
sending/receiving infection alerts in P2P communications within
crowds of people. The new system is forecasted to support the
governments, health authorities, and citizens in Egypt to take
critical decisions regarding the infection detection, infection
prediction, infection tracking, and infection avoidance regarding
COVID-19 outbreak or other coming pandemics.
Doaa Mohey El-Din, Aboul
Ella Hassanein, Ehab E.
Hassanien and Walaa M.E.
Hussei, E-Quarantine: A
Smart Health System for
Monitoring Coronavirus
Patients for Remote
Quarantine. Journal of
System and Management
Sciences, Vol. 10 (2020)
No. 4, pp. 102-124
Coronavirus becomes a global pandemic officially due to the speed of
spreading off in various countries. An increasing number of infected
with this disease causes the Inability problem to fully care in hospitals
and afflict many doctors and nurses inside the hospitals. This paper
proposes a smart health system that monitors the patients holding
the Coronavirus remotely. It observes the people with this disease
based on putting many sensors to record their patients' many
features every second. These parameters include measuring the
patient's temperature, respiratory rate, pulse rate, blood pressure,
and time. The proposed system saves lives and improves making
decisions in difficult cases. It proposes using artificial intelligence and
Internet-of-things to make remotely quarantine and develop
decisions in various situations. It provides monitoring patients
remotely and guarantees giving patients medicines and getting
complete health care without anyone getting sick with this disease. It
targets two people's slides, the most serious medical conditions and
infection, and the lowest serious medical conditions in their houses.
They are observing hospitals for the most serious medical cases that
cause infection in thousands of healthcare members, so there is a
significant need to use it. Other less serious patients slide, this system
enables physicians to monitor patients and get the healthcare from
patient's houses to save places for the critical cases in hospitals.
http://www.aasmr.org/jsms/Vol10/Vol.10.4.7.pdf
Chapters and Conferences Publications
M. Y. Shams, O. M. Elzeki, Mohamed
AbdElfattah, Lobna M. Abouelmagd,
Ashraf Darwish] and Aboul Ella
Hassanien Impact of COVID-19
Recently, the COVID-19 pandemic has an efficient impact on all things around the world.
Food estimation or diet has been grown great attention in the recent pandemic. This paper
utilizes the Support Vector Machine (SVM) to predict the effect of the COVID-19
pandemic on a diet and further forecast the number of persons subject to death due to this
10. Pandemic on Diet Prediction and Patient
Health based on Support Vector Machine.
AMLTA2021
pandemic. This work is based on the available dataset that contains fat quantity, energy
intake (kcal), food supply quantity (kg), and protein for different categories of food.
Furthermore, we are concerned the animal products, cereals excluding beer, obesity,
including vegetal products that affect humans' general health during the pandemic.
Furthermore, the dataset includes confirmed deaths, recovered, and active cases in the
percentage of each country's current population. The results depend on Root Mean Square
Error (RMSE), which indicates that SVM's use with the Radial Basis Function (RBF)
kernel produces0.27. Further, SVM with linear Kernel achieves 0.18 RMSE, and finally,
deep regression model achieves 0.29 RMSE.
Mohamed Elsersy , Ahmed Sherif ,
Ashraf Darwsih3, Aboul Ella
Hassanien, Digital Transformation
and Emerging Technologies for
Tackling COVID-19 Pandemic,
Studies in Systems, Decision and
Control, Springer 2020.
Several emerging technologies were introduced to tackle the unprecedented crisis of the
new COVID-19. Remarkable emerging technologies are outlined, such as machine and
deep learning, Internet of things, cloud and fog computing, and blockchain technology.
Those emerging technologies have been explored to support the solution proposed to
ensure the integration of these technologies to fight the pandemic. Also, numerous
emerging technologies used for the COVID-19 fight have been highlighted. Finally, the
impact of COVID-19 is discussed, and applications showing how to mitigate this impact
using the emerging technologies are outlined.
Atrab A. Abd El-Aziz, Nour Eldeen
M. Khalifa, Ashraf Darwsih , and
Aboul Ella Hassanien
The Role of Emerging Technologies
for Combating COVID-19 Pandemic,
Digital Transformation and Emerging
Technologies for Fighting COVID-19
Pandemic: Innovative Approaches,
Studies in Systems, Decision and
Control, Springer 2020.
The outbreak of the new coronavirus disease (COVID-19) in 2019 resulted in more than
100,000 infections and thousands of deaths. The number of deaths and infections continues
to rise rapidly since the virus date of appearance. COVID-19 threatens not only human
health but also many aspects of life such as manufacturing, social performance, and
international relations. Emerging technologies can help in the fight against COVID-19.
Emerging technologies include blockchain, Internet of Things (IoT), artificial intelligence
(AI), and big data technologies, and they proved its efficiency in practical fields. These
fields include the fast aggregation of multi-source big data, fast visualization of epidemic
information, diagnosing, remote treatment, and spatial tracking of confirmed cases. Every
country in the world is still seeking realistic and cost-effective solutions to stand against
COVID-19 under current epidemiological conditions. This chapter discusses the concepts
of emerging technologies, applications, and contributions to combating COVID-19.
Moreover, the challenges and future research directions are reviewed in detail. Also, a list
of publicly available open-source COVID-19 datasets will be presented. Finally, this
chapter concludes that cooperation among government, medical institutions, and the
scientific community is significant and critical. Also, there is an urgent demand for
improvement in the analytical algorithms and electronic devices to combat the COVID-19
pandemic.
Nour Eldeen M. Khalifa, Mohamed
Hamed N. Taha, Aboul Ella
Hassanien, Sarah Hamed N. Taha
"The Detection of COVID-19 in CT
Medical Images: A Deep Learning
Approach" Big Data Analytics and
Artificial Intelligence Against COVID-
19: Innovation Vision and Approach,
Springer, Big Data series, 2020.
The COVID-19 Coronavirus is one of the latest viruses that hit the earth in the new
century. It was declared as a pandemic by the World Health Organization in 2020. In this
chapter, a model for the detection of COVID-19 virus from CT chest medical images will
be presented. The proposed model is based on Generative Adversarial Networks (GAN),
and a fine-tuned deep transfer learning model. GAN is used to generate more images from
the available dataset. While deep transfer models are used to classify the COVID-19 virus
from the normal class. The original dataset consists of 746 images. The is divided into two
parts; 90% for the training and validation phase, while 10% for the testing phase. The 90%
then is divided into 80% percent for the training and 20% percent for the validation after
using GAN as image augmenter. The proposed GAN architecture raises the number of
images in the training and validation phase to be 10 times larger than the original dataset.
11. The deep transfer models which are selected for experimental trials are Resnet50,
Shufflenet, and Mobilenet. They were selected as they include a medium number of layers
on their architectures if they are com-pared with large deep transfer models such as
DenseNet, and Inception-ResNet. This will reflect on the performance of the proposed
model in terms of reducing training time, memory and CPU usage. The experimental trials
show that Shufflenet is selected to be the optimal deep transfer learning in the proposed
model as it achieves the highest possible for testing accuracy and performance metrics.
Shufflenet achieves an overall testing accuracy with 84.9%, and 85.33% in all performance
metrics which include recall, precision, and F1 score.
M. Y. Shams, O. M. Elzeki,
Mohamed Abd Elfattah, T. Medhat,
and Aboul Ella Hassanien"
Why are Generative Adversarial
Networks Vital for Deep Neural
Networks? A Case Study on COVID-
19 Chest X-Ray Image"
Big Data Analytics and Artificial
Intelligence Against COVID-19:
Innovation Vision and Approach,
Springer , Big Data series, 2020.
Abstract. The need to generate large scale datasets from a limited number of determined
data is highly required. Deep neural networks (DNN) is one of the most important and
effective tools in machine learning (ML) that required large scale datasets. Recently,
generative adversarial networks (GAN) is considered as the most potent and effective
method for data augmentation. In this chapter, we investigated the importance of using
GAN as a preprocessing stage to applied DNN for image data augmentation. Moreover, we
present a case study of using GAN networks for a limited COVID-19 X-Ray Chest images.
The results indicate that the proposed system based on using GAN-DNN is powerful with
minimum loss function for detecting COVID-19 X-Ray Chest images. Stochastic gradient
descent (SGD) and Improved Adam (IAdam) optimizers are used during the training
process of the COVID-19 X-Ray images, and the evaluation results depend on loss
function are determined to ensure the reliability of the proposed GAN architecture
Ahmed A. Hammam, Haytham H.
Elmousalami, Aboul Ella Hassanien
Stacking Deep Learning for Early
COVID-19 Vision Diagnosis, Big
Data Analytics and Artificial
Intelligence Against COVID-19:
Innovation Vision and Approach,
Springer , Big Data series, 2020.
Abstract— early and accurate COVID-19 diagnosis prediction plays a crucial role for
helping radiologists and health care workers to take reliable corrective actions for classify
patients and detecting the COVID 19 confirmed cases. Prediction and classification
accuracy are critical for COVID-19 diagnosis application. Current practices for COVID-19
images classification are mostly built upon convolutional neural network (CNNs) where
CNN is a single algorithm. On the other hand, ensemble machine learning models produce
higher accuracy than a single machine leaning. Therefore, this study conducts stacking
deep learning methodology to produce the highest results of COVID-19 classification. The
stacked ensemble deep learning model accuracy has produced 98.6% test accuracy.
Accordingly, the stacked ensemble deep learning model produced superior performance
than any single model. Accordingly, ensemble machine learning evolves as a future trend
due to its high scalability, stability, and prediction accuracy.
Doaa Mohey El-Din, Aboul Ella
Hassanein, and Ehab E. Hassanien
The effect Coronavirus Pendamic on
Education into Electronic Multi-
Modal Smart Education, Big Data
Analytics and Artificial Intelligence
Against COVID-19: Innovation
Vision and Approach, Springer , Big
Data series, 2020.
Abstract. this paper presents how Coronavirus drives education to smart education in
interpreting multi-modals. It uses to improve the electronic learning in multiple data types.
This paper is a survey paper about the importance of smart education and the effect of
Coronavirus on drives education into smart online education. It also presents many
changes in the education vision around the world to utilize multi-modal for enhancing E-
learning. The combination of artificial intelligence and data fusion plays a vital role in
improving decision making and monitoring students remotely. It also presents benefits and
open research challenges of a multi-modal smart education. This main objective of this
paper is to highlight the deepening digital inequality in smart education in emergencies due
to Coronavirus, the concept of digital equality has been defined as equal opportunities in
accessing technology as hardware and software as well as equal opportunities in obtaining
equal digital education through Ease of access to high-quality and interactive digital
content based on the interaction
12. Walid Hamdy, Ismail Elansary,
Ashraf Darwish and Aboul Ella
Hassanien" An Optimized
Classification Model for COVID-19
Pandemic based on Convolutional
Neural Networks and Particle Swarm
Optimization Algorithm" Studies in
Systems, Decision and Control,
Springer 2020.
With the daily rapid growth in the number of newly confirmed and suspected COVID-19
cases, COVID-19 extremely threatens public health, countries' economic, social life, and
international relations around the world. There are different medical methods to detect and
diagnose this disease such as viral nucleic acid screening by using specimens of the lower
respiratory tract. However, the availability of sufficient laboratory screening in the infested
counties represents a critical challenge especially with the fast-spreading of COVID-19.
Therefore, alternative diagnostic procedures that depend on Artificial Intelligence (AI)
techniques are required in the meantime to fight against this epidemic. This paper focuses
on using chest CT for diagnosis of COVID-19, as an alternative or assistive method to the
reverse-transcription polymerase chain reaction (RT-PCR) tests. Motivated by this, this
paper introduces a new model based on deep learning for detecting patients infected with
COVID-19 using chest CT. In this paper, a new proposed model for diagnosis of COVID-
19 based on using Convolutional Neural Networks (CNN) and Particle Swarm
Optimization (PSO) algorithm to classify the CT chest images of patients into infected or
not infected. In this paper, the network hyper-parameters in the CNN are optimized by
using the PSO algorithm to eliminate the requirement of manual search and enhance the
network performance. The used chest radiography dataset in this paper is described which
leveraged to train COVID-Net and includes include more 16,500 chest radiography images
across more 13,500 patient cases from two open access data repositories. The experimental
results of this work exhibited that the suggested system accuracy ratio of 98.04% is
competitive to the other models.
Kamel. K. Mohammed, Heba M.
Afify, Ashraf Darwish, Aboul Ella
Hassanien"Automatic Scoring and
Grading of COVID-19 Lung Infection
Approach" Studies in Systems,
Decision and Control, Springer
2020.
Abstract: Although the successful detection of COVID-19 from lung computed
tomography (CT) image mainly depends on radiologist's experience, specialists
occasionally disagree with their judgments. The performance of COVID-19 detection
models needs to be improved. According to COVID-19 symptoms and human immune
approach response, there are four types of its contagion such as asymptomatic, mild,
severe, and recovered. In this chapter, an automatic scoring of COVID-19 lung infection
grading approach is presented. The proposed approach is based on a combination of image
segmentation techniques and the Particle Swarm Optimization (PSO) algorithm to access
accurate evaluation for infection rate. Fuzzy c-means, K-means and thresholding-based
segmentation algorithms are used for isolating the chest lung from the CT images. Then,
PSO is used with the three segmentation algorithms for clustering the region of interest
(ROI) that consists of COVID-19 infected regions in lung CT. Then, scoring the infection
rate for each case. Finally, four infection classes related to the obtained infection COVID-
19 is determined and classified.
Walid Hamdy, Ashraf Darwish and
Aboul Ella Hassanien "Artificial
Intelligence Strategy in the Age of
Covid-19: Opportunities and
Challenges" Studies in Systems,
Decision and Control, Springer
2020.
With the frequent speedily rise in the number of recently reported and suspected cases of
COVID-19, COVID-19 is a significant threat to public health, cultural, social and foreign
relations around the world. Accurate diagnosis has to turn into a critical issue affecting the
containment of this disease, especially at the countries which outbreak the virus. In the
fight against COVID-19, Artificial Intelligence (AI) techniques have played a significant
role in many aspects. In this chapter, a systematics review of the recent work related to
COVID-19 containment using AI and big data techniques is introduced, showing their
main findings and limitations to make it easy for researchers to investigate new techniques
that will help the healthcare sector worker and reduce the spread of COVID-19 pandemic.
13. The chapter also presents the problems and challenges and present to the researchers and
academics some future research points from the AI point of view that can help healthcare
sectors and curbing the COVID-19 spread.
Jaideep Singh Sachdev, Arti Kamath,
Nitu Bhatnagar, Roheet Bhatnagar,
Arpana Rawal, Ashraf Darwish,
Aboul Ella Hassenian "SAKHA: An
Artificial Intelligence Enabled
VisualBOT for Health and Mental
Wellbeing during COVID’19
Pandemic" Studies in Systems,
Decision and Control, Springer
2020.
Abstract: COVID19 pandemic is playing havoc all around the world. Though the world is
fighting this invisible enemy it has succumbed to the devastating potential of the
Coronavirus. Largest of world economies and developed nations have been exposed and
their health infrastructure has collapsed during this testing time. It is assessed and
predicted that the novel coronavirus which is responsible for COVID19 pandemic, may
turn into an endemic (just like HIV) and will never go away. It will become part and parcel
of our life and humans have to learn to live with it even if the vaccine is developed. The
government’s world over is concerned with containment & eradication of this virus at the
earliest and massive efforts are on at all front to contain it's spread. As of now (3rd week
of May 2020), more than 4.4 million cases of the disease have been recorded worldwide
and more than 300,000 have died. The world has also seen technological innovation during
this time and mechanisms to tackle COVID19 patients. Innovations in carrying out quick
testing using Rapid testing kits, Artificial Intelligence (AI) powered thermal scanning for
temperature monitoring in the crowd, AI-enabled contact tracing, Mobile Apps, low-cost
ventilators, and many other such similar solutions. All these pertain to checking for
COVID19 symptoms and taking actions thereafter, but what about the stress, pain, and
shock of a person who has been put under quarantine in a facility meant for the purpose or
the person who is Corona positive? In this chapter, the authors have discussed briefly the
pandemic and tried to provide a solution for the mental wellbeing of such people who are
under quarantine and are isolated but heavily stressed or showing stress symptoms, by
creating a VisualBOT which could understand the facial expression of the person and
judge his mood, for providing suitable counseling and help.
Hassan Amin, Ashraf Darwish and
Aboul Ella Hassanien "Classification
of COVID19 x-ray images based on
Transfer Learning InceptionV3 Deep
Learning Model" Studies in Systems,
Decision and Control, Springer
2020.
The World Health Organization (WHO) has recently announced the novel Coronavirus
2019 as a pandemic. Many preventative plans and non-pharmaceutical efforts have
emerged and been in use to manage and control the spread of the disease which includes
infection control, proper isolation of patients, and social distancing. The main test used to
confirm a COVID-19 case is the RT-PCR test. However, this approach needs analysis time
and specimen collection. Therefore, the importance of medical imaging is increased to
screen COVID-19 cases. Hence radiology has a pivotal role in managing COVID-19
infection using CT scans and chest x-ray (CXR) throughout the screening, diagnosis, and
prognostication processes of the disease. In this paper, a new model using the transfer
learning method and InceptionV3 algorithm has been presented to classify the x-ray
images into COVID-19, Normal, and Pneumonia classes. The experimental results show
that the proposed model achieved 98% Accuracy on the test set for classifying the images
from the 3 different classes.
Aya Salama, Ashraf Darwsih, and
Aboul Ella Hassanien "Artificial
Intelligence Approach to Predict the
COVID-19 Patient's Recovery"
Studies in Systems, Decision and
Control, Springer 2020.
Abstract: Coronavirus is the new pandemic hitting all over the world. Patients all over the
world are facing different symptoms. Most of the patients with severe symptoms die
especially the elderly. In this chapter, three machine learning techniques have been chosen
and tested to predict the patient’s recovery of Coronavirus disease. The support vector
machine has been tested on the given data with a mean absolute error of 0.2155. The
Epidemiological data set is prepared by researchers from many health reports of real-time
14. cases to represent the different attributes that contribute as the main factors for recovery
prediction. Deep analysis with other machine learning algorithms including artificial neural
networks and regression models has been tested and compared with the SVM results. The
experimental results show that most of the patients who could not recover had a fever,
cough, general fatigue, and most probably malaise.
Mona Soliman, Asahraf Daerwish,
Aboul Ella Hassanien" Deep Learning
Technology for Tackling COVID-19
Pandemic" Studies in Systems,
Decision and Control, Springer
2020.
Abstract. Although the COVID-19 pandemic continues to expand, researchers
around the world are working to understand, diminish, and
curtail its spread. The primary _elds of research include investigating
transmission of COVID-19, promoting its identi_cation, designing potential
vaccines and therapies, and recognizing the pandemic's socioeconomic
impacts. Deep Learning (DL), which uses either deep learning
architectures or hierarchical approaches to learning, is developed a machine
learning class since 2006. The exponential growth and availability
of data and groundbreaking developments in hardware technology
have led to the rise of new distributed and learning studies. Throughout
this chapter, we discuss how deep learning can contribute to these goals
by stepping up ongoing research activities, improving the e_ciency and
speed of existing methods, and proposing original lines of research
Adarsh Kumar, Mohamed Elsersy,
Ashraf Darwsih, Aboul Ella
Hassanien"Drones combat COVID-
19 Epidemic: Innovating and
Monitoring Approach" Studies in
Systems, Decision and Control,
Springer 2020.
With the daily rapid growth in the number of newly confirmed and suspected Coronavirus
cases, Coronavirus extremely threatens public health, countries' economic, social life, and
international relations around the world. In the fight against Coronavirus, Unmanned
Aerial Vehicles (UAV) or drones can play a significant role in many aspects to limit the
spread of this pandemic. Also, the strategic planning of many governments such as in
China for controlling this crisis is supported by the use of drones for the Coronavirus
outbreak. This chapter explores the possibilities and opportunities of UAV, also called
drones in fighting Coronavirus. Drones are introduced, showing their main findings to
make it easy for researchers to investigate new techniques that will help the healthcare
sector worker and reduce the spread of Coronavirus pandemic. The chapter also presents
some problems and challenges that can help healthcare sectors and curbing the
Coronavirus spread.
Mourad R Mouhamed, Ashraf
Darwish, Aboul Ella Hassanien" 3D
Printing Supports COVID-19
Pandemic Control" Studies in
Systems, Decision and Control,
Springer 2020.
At the end of December last year a new type of Coronavirus has appeared in Wuhan,
China, with new properties the researchers named it COVID-19. In February, the world
health organization considers it a world pandemic; it had spread in most world countries.
This virus attacks the respiratory system, which makes failure in the system's function.
The effect of this crisis touched all the fielfieldslife, where all countries applied quarantine
and roadblock that makes a real shortage in most of the ple needs. BesiBesides biological
scientists’ efforts, the computer scientists proposed many ideas to fight this epidemic
using emergent technologies. This chapter is covering 3D printing principals the latest
efforts against COVID-19 as one of the emergent technologies. 3D printing technology
helps to flatten the curve of the outbreak of the virus by reducing the effect of shortage in
the supply chain of medical parts and all personal protective equipment (PPE) (i.e. face
masks and goggles), where it provides the extensive customization capability.
Lamia Nabil Mahdy, Kadry Ali Ezzat, As the COVID-19 pandemic grows, the shortening of clinical hardware is expanding. A
15. Ashraf Darwish and Aboul Ella
Hassanien "The Role of Social
Robotics to combat COVID-19
Pandemic" Studies in Systems,
Decision and Control, Springer
2020.
key bit of hardware getting out of sight has been ventilators. The contrast among the
organic market is significant to be dealt with ordinary creation strategies, particularly
under social removing measures set up. The examination investigates the method of
reasoning of human-robot groups to increase creation utilizing preferences of both the
simplicity of coordination and keeping up social removing. This chapter highlights the role
of social robotic in fighting COVID-19. Also, it presents the requirements of social
robotics.
Haytham H. Elmousalami, Ashraf
Darwish and Aboul Ella Hassanien
"The Truth about 5G and COVID-19:
Basics, analysis, and opportunities"
Studies in Systems, Decision and
Control, Springer 2020.
5G is a paradigm shift for data transfer and wireless communication technology where 5G
involves massive bandwidths based on high carrier frequencies. Unlike 4G, 5G is highly
integrative to produce a seamless user experience and universal high-rate coverage. The
key role of 5G is increasing data capacity, improving data rate transfer, providing better
service quality, and decreasing latency. Recently, COVID-19 is declared as an
international epidemic. More than 4.5 million confirmed cases and + 308000 death cases
have been recorded around more than 209 countries on May 16 2020. There are several
insane theories about 5G technology and human health. Therefore, people are burning
valuable 5G infrastructure down out of fear for their health. People think that 5G towers
are weakening the immune system and causing the global COVID-19 pandemic. This
chapter reviews the data transmission revolution from 1G to 5G technology and discusses
the impact of 5G technology on human health, pandemic, and business perspectives.
Mohamed Torky, Ashraf Darwish and
Aboul Ella Hassanien "Blockchain
Use Cases for COVID-19:
Management, Surveillance, Tracking
and Security" Studies in Systems,
Decision and Control, Springer
2020.
Blockchain has become a key technology in building and managing healthcare systems. the
distinguished attributes of the blockchain (e.g. security, decentralization, time stamping,
and transparency) make it the best technology for managing COVID-19 pandemic in real-
time. This chapter investigates five blockchain use cases for fighting against the COVID-
19 virus spread. Finally, this chapter is ended with discussing the recent blockchain
platforms that can be utilized for Managing epidemic diseases, HashLog, and XMED
Chain.
Mohamed Nagy, Hagar M. Abbad,,
Ashraf Darwish, Aboul Ella
Hassanien "The 4th Industrial
Revolution in Coronavirus Pandemic
Era" Studies in Systems, Decision
and Control, Springer 2020.
The global prevalence of coronavirus disease 2019 (COVID-19) requires a remarkable
avenue to endure and restrain it; Although the most advanced and sophisticated healthcare
systems around the world could not stand against this pandemic, the synthesis of the fourth
industrial revolution manifests its potential to eradicate this virus. This chapter discusses
how multiple advanced technologies involve diverse perspectives of fighting the
catastrophe, starting from reduction of the spreading of the virus,
automated surveillance for infected cases, contribution to retaining the communication as
well as social safety during the lockdown, and evolving healthcare medical equipment to
the process of developing a vaccine. It also has a vital role in keeping most nations'
institutions run remotely, such as education systems, besides the declination of the
expected economic losses by running businesses online. Moreover, introducing the
essential role of these technologies to monitor the propagation of COVID-19
globally that permits taking precautionary measures earlier and evaluating the current
situation of each country individually. Eventually, the inuence of these privileges of this
revolution and how it has convinced other nations the importance of accelerating and
16. boosting those advanced technologies to defeat the current situation by considering China
as a realistic illustration of the efficiency.
Arome J. Gabriel1, Ashraf
Darwsih and Aboul Ella
Hassanien"Cyber Security in the Age
of COVID-19" Studies in Systems,
Decision and Control, Springer
2020.
As a containment strategy for the dreaded Corona Virus Disease 19 (COVID 19) which is
spreading rapidly and causing severe damage to life and economy of nations, places of
public gathering like schools, places of religious worship, open physical markets, offices as
well as venues for social meetings (such as clubs) are been closed down, to promote social
distancing in most nations across the globe. Therefore, most public/private organizations,
and even individuals have resorted to the use of diverse Information Technologies (IT) for
connecting themselves and other life essentials. Educational, agricultural, religious and
even health institutions now deliver their services to users/clients and receive payments via
online platforms, students study from home, even employees of most organizations now
work remotely (maybe from their homes). Moreover, there is a sharp growth in demand for
food deliveries and online grocery. The massive adoption of IT by almost all aspects of
human life especially during this epidemic has also led to increased cyber security
concerns. Cybercriminals and other individuals with malicious intent now take COVID-19
as an opportunity to perpetrate cybercrimes, especially for monetary gains. Domestic
violence seems to be on the rise perhaps due to the lockdown, contact tracing approaches
are massively been developed and used, healthcare systems are being attacked with ransom
ware and resources such as patient records confidentiality, and integrity is being
compromised. Individuals are falling victim to phishing attacks through COVID-19 related
content. This paper presents an extensive study of major cybersecurity concerns that are
and could take place during the COVID 19 pandemic as well as strategies for mitigating
them.
Khaled Ahmed, Sara Abdelghafar,
Aya Salama, Nour Eldeen
M.Khalifa, Ashraf Darwish, and
Aboul Ella Hassanien "Tracking of
COVID-19 Geographical Infections
on Real-Time Tweets" Studies in
Systems, Decision and Control,
Springer 2020.
Abstract. Coronavirus COVID-19 is a global pandemic stated by the World Health
Organization (WHO) in 2020. The COVID-19 devasting impact was not only affect human
life but also many aspects of it such as social interaction, transportation options, personal
saving and expenses, and more. The power of social media data in such world pandemic
outbreaks provides an efficient source of tracking, raising awareness, and alerts with
potentials infection location. Social networks can fight the pandemic by sharing helpful
content and statistics based on demographics features of users around the world. There is
an urgent need for such frameworks for tracking helpful content, detecting misleading
content, ranking the trusted user content, presenting accurate demographics statistics of the
outbreak. In this paper, the real-time tweets of Coronavirus pandemic (COVID-19)
analysis will be presented. The proposed framework will be used to track the geographical
infections, trends of the content, and the user's categorization. The framework will include
analysis, demographics features, statistical charts, classifying the content of tweets related
to its usefulness. The performance of the proposed framework is evaluated based on
different measures such as classification accuracy, sensitivity, and specificity. Finally, a set
of recommendations will be presented to benefit from the proposed framework with its full
potentials as a tool to stand against the COVID-19 spreading.
Ismail Elansary, Ashraf Darwish and
Aboul Ella Hassanien "The Future
Scope of Internet of Things for
Monitoring and Prediction of COVID-
19 Patients" Studies in Systems,
The new outbreak of pneumonia triggered by a novel coronavirus (COVID-19) poses a
major threat and has been declared a global public health emergency. This outbreak had
first been discovered in December 2019 in Wuhan, China and until now has spread to the
world. Emerging technology such as the Internet of Things (IoT) and sensor networks (SN)
have been utilized widely in our everyday lives in a diversity of ways. IoT has also been an
17. Decision and Control, Springer
2020.
instrumental role in fighting against the COVID-19 pandemic currently out breaking across
the globe, where it plays a significant role in tracking COVID-19 patients and infected
people in hospitals and hotspots. This paper exhibited a survey of IoT technologies used in
the fight against the deadly COVID-19 outbreak in different applications and discusses the
key roles of IoT science in this unparalleled war. Research directions on discovering IoT's
potentials, improving its capabilities and power in the battle, and IoT's issues and problems
in healthcare systems are explored in detail. This study is intended to provide an overview
of the current status of IoT applications to IoT researchers and the broader community and
to inspire researchers to leverage IoT potentials in the battle against COVID-19.
Pre-prints publications
Nour Eldeen Mahmoud
Khalifa, Mohamed Hamed N.
Taha, Aboul Ella Hassanien, Sally M.
Elghamrawy:
Detection of Coronavirus (COVID-
19) Associated Pneumonia based on
Generative Adversarial Networks and
a Fine-Tuned Deep Transfer
Learning Model using Chest X-ray
dataset. CoRR abs/2004.01184 (20
20)
The COVID-19 Coronavirus is one of the devastating viruses according to the world health
organization. This novel virus leads to pneumonia, which is an infection that inflames the
lungs' air sacs of a human. One of the methods to detect those inflames is by using x-rays
for the chest. In this paper, a pneumonia chest x-ray detection based on generative
adversarial networks (GAN) with a fine-tuned deep transfer learning for a limited dataset
will be presented. The use of GAN positively affects the proposed model robustness and
made it immune to the overfitting problem and helps in generating more images from the
dataset. The dataset used in this research consists of 5863 X-ray images with two
categories: Normal and Pneumonia. This research uses only 10% of the dataset for training
data and generates 90% of images using GAN to prove the efficiency of the proposed
model. Through the paper, AlexNet, GoogLeNet, Squeeznet, and Resnet18 are selected as
deep transfer learning models to detect the pneumonia from chest x-rays. Those models are
selected based on their small number of layers on their architectures, which will reflect in
reducing the complexity of the models and the consumed memory and time. Using a
combination of GAN and deep transfer models proved it is efficiency according to testing
accuracy measurement. The research concludes that the Resnet18 is the most appropriate
deep transfer model according to testing accuracy measurement and achieved 99% with the
other performance metrics such as precision, recall, and F1 score while using GAN as an
image augmenter. Finally, a comparison result was carried out at the end of the research
with related work which used the same dataset except that this research used only 10% of
original dataset. The presented work achieved a superior result than the related work in
terms of testing accuracy.
https://arxiv.org/abs/2004.01184
V. Rajinikanth, Nilanjan Dey, Alex
Noel Joseph Raj, Aboul Ella
Hassanien, K. C.
Santosh, Nadaradjane Sri Madhava
Raja:
Harmony-Search and Otsu based
System for Coronavirus Disease
(COVID-19) Detection using Lung
CT Scan
Images. CoRR abs/2004.03431 (20
20)
The COVID-19 Coronavirus is one of the devastating viruses according to the world health
organization. This novel virus leads to pneumonia, which is an infection that inflames the
lungs' air sacs of a human. One of the methods to detect those inflames is by using x-rays
for the chest. In this paper, a pneumonia chest x-ray detection based on generative
adversarial networks (GAN) with a fine-tuned deep transfer learning for a limited dataset
will be presented. The use of GAN positively affects the proposed model robustness and
made it immune to the overfitting problem and helps in generating more images from the
dataset. The dataset used in this research consists of 5863 X-ray images with two
categories: Normal and Pneumonia. This research uses only 10% of the dataset for training
data and generates 90% of images using GAN to prove the efficiency of the proposed
model. Through the paper, AlexNet, GoogLeNet, Squeeznet, and Resnet18 are selected as
deep transfer learning models to detect the pneumonia from chest x-rays. Those models are
selected based on their small number of layers on their architectures, which will reflect in
reducing the complexity of the models and the consumed memory and time. Using a
combination of GAN and deep transfer models proved it is efficiency according to testing
accuracy measurement. The research concludes that the Resnet18 is the most appropriate
deep transfer model according to testing accuracy measurement and achieved 99% with the
other performance metrics such as precision, recall, and F1 score while using GAN as an
image augmenter. Finally, a comparison result was carried out at the end of the research
18. with related work which used the same dataset except that this research used only 10% of
original dataset. The presented work achieved a superior result than the related work in
terms of testing accuracy.
https://arxiv.org/abs/2004.01184
Dalia Ezzat, Aboul Ella
Hassanien, Hassan Aboul Ella:
GSA-DenseNet121-COVID-19: a
Hybrid Deep Learning Architecture
for the Diagnosis of COVID-19
Disease based on Gravitational
Search Optimization
Algorithm. CoRR abs/2004.05084 (2
020)
In this paper, a novel approach called GSA-DenseNet121-COVID-19 based on a hybrid
convolutional neural network (CNN) architecture is proposed using an optimization
algorithm. The CNN architecture that was used is called DenseNet121 and the
optimization algorithm that was used is called the gravitational search algorithm (GSA).
The GSA is adapted to determine the best values for the hyperparameters of the
DenseNet121 architecture, and to achieve a high level of accuracy in diagnosing COVID-
19 disease through chest x-ray image analysis. The obtained results showed that the
proposed approach was able to correctly classify 98% of the test set. To test the efficacy of
the GSA in setting the optimum values for the hyperparameters of DenseNet121, it was
compared to another optimization algorithm called social ski driver (SSD). The
comparison results demonstrated the efficacy of the proposed GSA-DenseNet121-COVID-
19 and its ability to better diagnose COVID-19 disease than the SSD-DenseNet121 as the
second was able to diagnose only 94% of the test set. As well as, the proposed approach
was compared to an approach based on a CNN architecture called Inception-v3 and the
manual search method for determining the values of the hyperparameters. The results of
the comparison showed that the GSA-DenseNet121 was able to beat the other approach, as
the second was able to classify only 95% of the test set samples.
https://arxiv.org/abs/2004.05084
Rizk M. Rizk-Allah, Aboul Ella
Hassanien:
COVID-19 forecasting based on an
improved interior search algorithm
and multi-layer feed forward neural
network. CoRR abs/2004.05960 (20
20)
COVID-19 is a novel coronavirus that was emerged in December 2019 within Wuhan,
China. As the crisis of its serious increasing dynamic outbreak in all parts of the globe, the
forecast maps and analysis of confirmed cases (CS) becomes a vital great changeling task.
In this study, a new forecasting model is presented to analyze and forecast the CS of
COVID-19 for the coming days based on the reported data since January 22 2020. The
proposed forecasting model, named ISACL-MFNN, integrates an improved interior search
algorithm (ISA) based on chaotic learning (CL) strategy into a multi-layer feed-forward
neural network (MFNN). The ISACL incorporates the CL strategy to enhance the
performance of ISA and avoid the trapping in the local optima. By this methodology, it is
intended to train the neural network by tuning its parameters to optimal values and thus
achieving high-accuracy level regarding forecasted results. The ISACL-MFNN model is
investigated on the official data of the COVID-19 reported by the World Health
Organization (WHO) to analyze the confirmed cases for the upcoming days. The
performance regarding the proposed forecasting model is validated and assessed by
introducing some indices including the mean absolute error (MAE), root mean square error
(RMSE) and mean absolute percentage error (MAPE) and the comparisons with other
optimization algorithms are presented. The proposed model is investigated in the most
affected countries (i.e., USA, Italy, and Spain). The experimental simulations illustrate that
the proposed ISACL-MFNN provides promising performance rather than the other
algorithms while forecasting task for the candidate countries.
https://arxiv.org/abs/2004.05960
Mohamed Torky, Aboul Ella
Hassanien:
COVID-19 Blockchain Framework:
Innovative
Approach. CoRR abs/2004.06081 (
2020)
The world is currently witnessing dangerous shifts in the epidemic of emerging SARS-
CoV-2, the causative agent of (COVID-19) Coronavirus. The infection, and death numbers
reported by World Health Organization (WHO) about this epidemic forecasts an increasing
threats to the lives of people and the economics of countries. The greatest challenge that
most governments are currently suffering from is the lack of a precise mechanism to detect
unknown infected cases and predict the infection risk of COVID-19 virus. In response to
mitigate this challenge, this study proposes a novel innovative approach for mitigating big
challenges of (COVID-19) coronavirus propagation and contagion. This study propose a
blockchain-based framework which investigate the possibility of utilizing peer-to peer,
time stamping, and decentralized storage advantages of blockchain to build a new system
19. for verifying and detecting the unknown infected cases of COVID-19 virus. Moreover, the
proposed framework will enable the citizens to predict the infection risk of COVID-19
virus within conglomerates of people or within public places through a novel design of
P2P-Mobile Application. The proposed approach is forecasted to produce an effective
system able to support governments, health authorities, and citizens to take critical
decision regarding the infection detection, infection prediction, and infection avoidance.
The framework is currently being developed and implemented as a new system consists of
four components, Infection Verifier Subsystem, Blockchain platform, P2P-Mobile
Application, and Mass-Surveillance System. This four components work together for
detecting the unknown infected cases and predicting and estimating the infection Risk of
Corona Virus (COVID-19).
https://arxiv.org/abs/2004.06081
Aboul Ella Hassanien, Aya Salama,
Ashraf Darwsih
Artificial Intelligence Approach to
Predict the COVID-19 Patient's
Recovery, No. 3223. EasyChair,
2020
Coronaviruse is the new pandemic hitting all over the world. Patients all over the world are
facing different symptoms. Most of the patients with severe symptoms die specially the
elderly. In this paper, we test three machine learning techniques to predict the patient’s
recovery. Support vector machine was tested on the given data with mean absolute error
of 0.2155. The Epidemiological data set was prepared by researchers from many health
reports of real time cases to represent the different attributes that contribute as the main
factors for recovery prediction. A deep analysis with other machine learning algorithms
including artificial neural networks and regression model were test and compared with the
SVM results. We conclude that most of the patients who couldn't recover had fever,
cough, general fatigue and most probably malaise. Besides, most of the patients who died
live in Wuhan in china or visited Wuhan, France, Italy or Iran.
https://easychair.org/publications/preprint/4bf1
Day Level Forecasting for
Coronavirus Disease (COVID-19)
Spread: Analysis, Modeling and
Recommendations
Haytham H. Elmousalami, Aboul Ella
Hassanien
arXiv:2003.07778
In mid of March 2020, Coronaviruses such as COVID-19 is declared as an international
epidemic. More than 125000 confirmed cases and 4,607 death cases have been recorded
around more than 118 countries. Unfortunately, a coronavirus vaccine is expected to take
at least 18 months if it works at all. Moreover, COVID -19 epidemics can mutate into a
more aggressive form. Day level information about the COVID -19 spread is crucial to
measure the behavior of this new virus globally. Therefore, this study presents a
comparison of day level forecasting models on COVID-19 affected cases using time series
models and mathematical formulation. The forecasting models and data strongly suggest
that the number of coronavirus cases grows exponentially in countries that do not mandate
quarantines, restrictions on travel and public gatherings, and closing of schools,
universities, and workplaces (Social Distancing).
https://arxiv.org/abs/2003.07778
Papers in Reviews
Applied Soft Computing Manash Sarkar, Aboul Ella Hassanien, Saptarshi Gupta, Bhavya Gaur, "
Exploring an IoT Enabled Smart Monitoring System to Combat with COVID-19
pandemic empowered with Hybrid Intelligence Techniques"
Journal of Digital imaging Nour Eldeen M. Khalifa, Mohamed Hamed N. Taha, Aboul Ella Hassanien,
Sally Elghamrawy Detection of SARS-CoV-2 Associated Pneumonia based on
Generative Adversarial Networks
World neural network Lamia Nabil Mahdy, Kadry Ali Ezzat, Haytham H. Elmousalami, Hassan Aboul
Ella, Aboul Ella Hassanien Automatic X-ray COVID-19 Lung Image
Classification System based on Support Vector Machine
Ismail Elansary, Walid Hamdy, Ashraf Darwish and Aboul Ella Hassanien Bat-
inspired Optimizer for Prediction of Anti-Viral Cure
Drug of SARS-CoV-2 based on Recurrent Neural Network
20. Annals of Global health Aboul Ella Hassanien, Reham Gharbia , Atrab A. Abd El-Aziz,The Mutual
Influence between COVID-19 Pandemic and Nitrogen Dioxide Air Pollution with
Python
Health Policy and technology Aboul Ella Hassanein, Doaa Mohey El-Din, Ehab E. Hassanien, and Walaa
M.E. Hussein, Remotely Quarantine Smart Health System for
Monitoring Coronavirus Patients