The First International Conference on Emerging

The First International Conference on Emerging

Smart Technologies and Applications

(eSmarTA2021)

10th– 12th August 2021

Lebanese International University (LIU),

Sana'a, Yemen.

“Smart Technologies for Digital Transformation”

Editors:

Abdulaziz Al-hetar

Fathey Mohammed

Redhwan Shaddad

Murad Rassam

Organizing Committee

iii

Honorary Chair

Rida Hazimi, LIU Yemen President

Conferences Co-Chairs

Abdulaziz Al-hetar (General Chair)

Fathey Mohammed (General Vice-Chair)

Program Committee

Redhwan Shaddad (Committee Chair)

Ammar Zahari

Saeed Bamashmos

Sami Abdulaziz

Technical Committee

Murad Rassam (Committee Chair)

Ahmed Mohammed Al-Saman

Abdulaziz Al-Nahari

Hefdhallah Sakran

Publication Committee

Fathey Mohammed (Committee Chair)

Zaid Ahmed Shamsan

Abdulqader M. Mohsen

Publicity & Public Relations Committee

Mohammed Hadwan (Committee Chair)

Nabil Yousef

Abdullah Omar Aldhaibani

Abdulrahman Al-ezzi Mohsen Al-fadhli

Yahya Algurbani

Technical Support Committee

Abdulfattah Esmail Ba Alawi (Committee Chair)

Ahmed Najeeb Hassan

Dhiaa Faisal Alshamy

Osama Al-Sharabi

Organizing Committee

iv

Finance Chair

Qais Ali Alnuzaili

Registration Committee

Gamil Sultan (Committee Chair)

Ahmed Alnagar

Methaq Salam

Sponsorship Committee

Wail Alhakimi

Ammar Zahari

Local Arrangements and Logistic Committee

Khaled Alameer

Qais Ali Alnuzaili

Technical Committee

v

Abdulbasit Darem, Mysore University, India

Abdulghani Ali Ahmed, Universiti Malaysia Pahang, Malaysia

Abdulrahman Alsewari, Universiti Malaysia Pahang, Malaysia

Abdulrazak Alhababi, UNIMAS, Malaysia

Ahmed Al-Saman,

Ahmed Hamza, King Abdulaziz University, KSA

Ali Al-Awadhi, Lincoln University College, Malaysia

Ameer Tawfik, KMIT University, Australia

Ashraf Osman, Alzaiem Alazhari University, Sudan

Asma Ahmed Alhashmi, Mysore University, India

Ghahida Mutasher, University of Technology, Iraq

Hussein Abu Al-Rejal, University Utara Malaysia, Malaysia

Nasrin Makbol, Universiti Science Malaysia, Malaysia

Osamah Ibrahim Khalaf, Al-Nahrain University, Iraq

Qais Alnuzaili, Amran University, Amran, Yemen

Taha Hussein, Universiti Malaysia Pahang, Malaysia

Thabit Sabbah, Al-Quds Open University, Palestine

Yahya M. Al-dheleai, Universiti Teknologi Malaysia, Malaysia

Mohammed Sarhan Al-Duais, Faculty of Informatics and Computing, Malaysia

Khaled Abdullah Al-Soufy, Ibb University, Yemen

Hatem Abdo Ali Al-Dois, Ibb University, Yemen

Samir Ahmed Al-Gailani, Universiti Sains Malaysia, Malaysia

Waleed Ali Ahmed, King Abdulaziz University, KSA

Fahd Ahmed Alqasemi, University of Science and Technology, Yemen

Abdulqawi Saif, Taiz university, Yemen

Fuad Abdulgaleel Ghaleb, Universiti Teknologi Malaysia, Malaysia

Sami AL-MAQTARI, Sanaa University, Yemen

Amin Mohamed Ahsan, International University of Technology Twintech,Sanaa,

Yemen

Arwa Aleryani, Independent Researcher, Canada

Bander Ali, Universiti Teknologi Malaysia, Malaysia

Abdulrazak Yahya, UniMAS, Malaysia

Abdulgaleel Radman, Taiz University, Yemen

Technical Committee

vi

CONFERENCE HONORARY CHAIR MESSAGE

The fist International conference of emerging smart

technologies and applications (eSmarTA2021) provides

an opportunity for master's and doctoral students in

engineering and information technology to present their

research and present it to specialized technical committees

from various countries for evaluation, arbitration, and

knowledge of its quality, and the accepted ones are

published and archived on a global significance site as IEEE proceeding.

This conference is the first of its kind in Sana'a, and the Lebanese International University

is honored to host it. One of the goals of the Lebanese International University (LIU) is

to spread knowledge and improve the academic process. In order to contribute to

providing high-quality and valuable outputs to the national and regional markets, the

hosting and supporting events from such a conference is one way to do so. Through this

event, the Lebanese International University provides an opportunity for researchers,

including master's and doctoral students, as well as academic researchers, to communicate

and interact with the global research community.

Dr. Rida Hazimi

LIU Yemen President

Technical Committee

vii

YEMEN RESEARCH PRESEDENT MESSAGE

It is a source of pleasure that the first international

conference on emerging smart technologies and

applications (eSmarTA2021) is held in Sana'a, Yemen.

eSmarTA2021 is organized by the Yemeni Organization

for Science and Technology Research (YOSTR - Yemen

Research). We are proud that it is the first international

event organized by Yemen Research with a team of

Yemeni experts and specialized scientists present around

the world to raise Yemen's name high in the field of

scientific research and its achievements.

Thanks are to the Lebanese International University, Yemen Branch, which harnessed all

its kind efforts and initiated cooperation without delay, and also thanks to the Institute of

Electrical and Electronics Engineers IEEE Yemen Subsection for its technical sponsorship

of the conference so that conference's literature is published on the world famous research

site IEEEXplor, which provides archived documentation service on the Internet and

trusted within the SCOPUS website. We also thank the Yemeni Company for

International Telecommunications, TeleYemen, Sana'a, Yemen for its continuous

support.

Greetings and appreciation to those who are the stars of this eSmarTA2021 conference:

the main speakers, and participants with their research papers in which they presented a

summary of their scientific and applied experiences, the core of their ideas and the harvest

of their creativity to serve the various future disciplines in emerging smart technologies

and their applications. Thanks also is directed to researchers who mentioned Yemen in

their research, as many of the research papers presented in this conference did not

overlook the Yemeni reality and its needs in this aspect, in a way that serves the Yemeni

society in the present and the future.

Yemen Research hopes that this international conference will be a precursor to specialized

scientific conferences that will be held on an annual or semi-annual basis at Yemen,

undoubtedly with the cooperation and co-organization of Yemeni higher education and

scientific research institutions from governmental and private universities, centers,

institutes, and higher colleges.

In conclusion, we welcome all the guests, attendees and participants to our first

conference, and thank you for their wonderful interaction.

Asso. Prof. Dr. Redhwan Qasem Shaddad

YOSTR President

Technical Committee

viii

CONFERENCE GENERAL CHAIR MESSAGE

The Conference Committees warmly welcomes all our

distinguished guests and participates for attending of

2021 IEEE 1st International Conference of emerging

smart technologies and applications(eSmarTA2021),

which be held on-site at Lebanese International

University (LIU), Sana’a, Yemen, and virtually via

ZOOM online meeting from 10 – 12 August 2021.

eSmarTA will be an annual event focusing on state of

the art the various aspects of advances in smart technologies and applications, providing

a discussion platform for researchers, practitioners, educators and industry to present and

discuss some of the most recent innovations, trends, experiences and concerns in the areas

of Artificial Intelligence (AI), machine learning, big data analysis, and applications such

as health informatics, signal processing, Internet of Things, cloud computing, cyber

security, information systems, communications network, and social media.

The eSmarTA2021 conference received more than 80 submissions from more than 20

countries via Electronic Submission System, which were reviewed by the reviewers and

experts, and 42 papers have been selected for presentation and included in the

eSmarTA2021 proceedings after rigorous double-blind peer-review. 5 Keynote Speakers

and 3 Technical Sessions will be hosted during the conference. It will be a fantastic

opportunity for students, researchers, and engineers to speak with professionals and

specialists and receive advice.

On behalf of the eSmarTA2021 Committees, we would like to express our gratitude to all

of the resource persons, including keynote speakers and session chairpersons, for

volunteering their time to support the conference. We'd also like to thank the Honorary

Chair, General Chair, General Co-chair, Program Chair, Technical Chair, Technical Co-

Chair, Technical Committee, Publicity Chair, Publication Chair, and all other members of

the Program Committee for their constant support and countless hours spent ensuring that

the conference worked perfectly. We also want to express our gratitude to all of the

conference organizers, who made a significant contribution to the conference's success.

Special thanks go out to the authors who contributed to this event. Furthermore, all

funding institutions have been really helpful and supportive.

We strongly hope and believe that everyone who attends this conference will have a

scientifically immediate benefit. I wish everyone here pleasure and good health!.

Assoc. Prof. Dr. Abdulaziz Al-hetar

eSmarTA2021 General Chair

Technical Committee

ix

CONFERENCE VICE CHAIR MESSAGE

It is our great pleasure to welcome you to the first

International Conference of emerging smart technologies

and applications(eSmarTA2021). This conference is

organized by Yemeni Organization for Science and

Technology Research (YOSTR - Yemen Research) in

collaboration with Lebanese International University

(LIU), Sana’a, Yemen. eSmarTA2021 is technically

supported by IEEE Yemen Sub-Section and sponsored by

Yemeni Company for International Telecommunications, TeleYemen, Sana'a, Yemen.

I would like to take this opportunity to express my utmost gratitude and sincere thanks

and appreciation to the organizing committee members for their countless efforts and to

the technical committee chair and members for managing the submissions’ review

process. Many thanks go to our keynote speakers, Prof. Dr. Tharek Abd. Rahman, Prof.

Dr. Nuno M. Garcia, Dr. Mohamad Abou Ali, Dr. Ali Nagi Nosary and Dr. Ibrahim Mohd

Alsofyani for sharing their knowledge and experience with us in eSmarTA2021. I would

also like to thank all authors for submitting papers to eSmarTA2021 and for presenting

and discussing their papers during the conference.

Also, I would like to extend my thanks and appreciations to all who participated, attended,

and supported this conference and make it a reality.

Finally, we hope that all guests, participants, and attendees have a great time at

eSmarTA2021. The success of this conference will inspire us more in future.

Dr. Fathey Mohammed,

eSmarTA2021 Vice Chair

Technical Committee

x

TECHNICAL COMMITTEE CHAIR MESSAGE

A warm welcome to the IEEE International Conference on

Emerging Smart Technologies and its Applications

(eSmarTA2021).

We are very excited to introduce you to the technical

program of our conference that this year includes 46 papers

representing high-quality research conducted over the

broad spectrum of topics related to Smart Technologies

and their different applications. There are 12 tracks that

constitute different areas of applying smart and emerging

technologies in various aspects of life.

This year, eSmarTA2021 received 81 submissions coming from 22 different countries.

The acceptance rate was about 55% which reflects a strict review process by more than

81 external reviewers who contributed around 155 reviews in addition to the reviews made

by eSmarTA2021 committee members. The task of providing a timely and fair review

outcome was challenging due to the current situation of the COVID-19 pandemic that

makes most of the referees unavailable and very hard to reach.

Great thanks should go to the professional team who were responsible for chairing the 12

tracks of the conference. Each paper was assigned to, at least, three reviewers and received

two to four reviews, either from the technical committee members or external reviewers

carefully selected by track chairs. A period of one month was given for the whole review

process from the beginning of submissions by authors until they got notified by the

conference chair. A strict policy was practiced for papers that require corrections as

suggested by reviewers and to conform with IEEE templates and styles

By the end, we wish great success for the eSmarTA2021 program which will be held on

10-12 August 2021.

Murad A. Rassam, PhD

eSmarTA2021 Technical Committee Chair

Keynote Speakers

xi

Keynote Speaker I:

Prof. Dr. Tharek Abd. Rahman

Professor of Electrical Engineering, Faculty of

Electrical Engineering, Universiti Teknologi

Malaysia (UTM).

Keynote title:

“5G Standardization and Evolution”

Brief Profile

Prof. Dr. Tharek Abd Rahman is a Professor at Faculty of Electrical Engineering,

Universiti Teknologi Malaysia (UTM). He obtained his BSc. in Electrical & Electronic

Engineering from University of Strathclyde UK in 1979, MSc in Communication

Engineering from UMIST Manchester UK and PhD in Mobile Radio Communication

Engineering from University of Bristol, UK in 1988. He is the Director of Wireless

Communication Centre (WCC), UTM. His research interests are radio propagation,

antenna and RF design and indoors and outdoors wireless communication. He has also

conducted various short courses related to mobile and satellite communication to the

Telecommunication Industry and Government body since 1990. He has published more

than 120 papers related to wireless communication in national/international journal and

conference.

Keynote Speakers

xii

Keynote Speaker II:

Prof. Dr. Nuno M. Garcia

Computer Science Engineering University of Beira

Interior, Covilhã, Portugal

Keynote title:

“5P Medicine and Smart IoT and applications: the

development of predictive algorithms”

Brief Profile

Prof. Dr. Nuno M. Garcia holds a PhD in Computer Science Engineering from the Universidade da Beira Interior (UBI, Covilhã, Portugal) (2008) and is a 5-year BSc in Mathematics/Informatics (Hons.) also from UBI (1999-2004). He was an entrepreneur (1988-2004), member of the Research Team at Siemens SA (2004-2007) and Nokia Siemens SA (2007-2008), and Head of Re-search at PLUX SA (2008-2010). Currently serving as Vice Dean of the Faculty of Engi-neering at UBI (2018-), he is an Associate Professor with Habilitation at the Computer Science Department at UBI (2010) and Invited Associate Professor at the Universidade Lusófona de Humanidades e Tecnologias (Lisbon, Portugal, 2010-). He was the founder and is a researcher of the Assisted Living Computing and Telecommu-nications Laboratory (ALLab, 2010), a research group within the Instituto de Telecomuni-cações at UBI. He was also co-founder and is Chair of the Executive Council of the BSAFE LAB – Law enforcement, Justice and Public Safety Research and Technology Transfer Laboratory, a multidisciplinar research laboratory in UBI (2015). Since 2010, he has par-ticipated as Principal Investigator, Coordinator, Local Coordinator or Researcher of sever-al European or national Research projects. The funds he directly managed for these pro-jects surpass the 4.8 M€. For the two research groups, a total of 19 projects have been or are managed, of them, 8 as Principal Investigator, and 11 as Coordinator of the research team at UBI. He was the founder and coordinator of the Cisco Academy at UBI (2010-2020) and was Chair of the COST Action IC1303 AAPELE – Architectures, Algorithms and Platforms for Enhanced Living Environments (Brussels, Belgium, 2013-2017). He is currently a member of COST Actions SHELD-ON (CA16226) and GDHRnet (CA19143).In 2020, he was identified as one of the world top 2% most influencing researchers. He is member of ISOC and of the Non-Commercial Users Constituency, a group within GNSO in ICANN. His main interests include Next-Generation Networks, predictive algorithms for healthcare and well-being, distributed and cooperative algorithms, and the battle for a Free and Open Internet.

Keynote Speakers

xiii

Keynote Speaker III:

Dr. Mohamad Abou Ali

Biomedical/Medical Engineering, Lebanese

International University, Lebanon

Keynote title:

Brief Profile

Dr. Mohamad Abou Ali is a Professor of Biomedical/Medical Engineering, Lebanon

International University. He is an Experienced Director Clinical Engineering with a

demonstrated history of working in the hospital & health care industry. Skilled in Medical

Devices, Healthcare Information Technology (HIT), Biotechnology, Management, and

Capital Equipment. Strong business development professional with a Master and PhD of

Engineering Science focused in Biomedical/Medical Engineering from University of New

South Wales.

“Medical Equipment Purchasing Informed Decision"

Keynote Speakers

xiv

Keynote Speaker V:

Dr. Ali Nagi Nosary

Chief Executive Officer at TeleYemen, Faculty of

Engineering, Sana'a University, Yemen

Keynote title:

“Artificial Intelligence in Telecom Industry”

Brief Profile:

Dr. Ali Nagi Nosary is an Assistant Professor, Faculty of Engineering, Sana'a University.

His research interests are in signal processing pattern recognition, artificial intelligence

and coding. He has been working as an ICT consultant at the ministry of

telecommunications and other ministries. He was nominated as Director General of

Yemen Telecom (PTC) from august 2007 to March 2012. Through this position, was the

Chairman of Yemen Mobile, vice chairman of TeleYemen, board member of the Post

Authority during that period.

Keynote Speakers

xv

Keynote Speaker VI:

Dr. Ibrahim Mohd Alsofyani

Ajou University, Suwon, South Korea

Keynote title:

“Future Electric Vehicles: Construction and Operation”

Brief Profile:

Ibrahim Mohd Alsofyani received M.Eng. degree in electrical mechatronics and

automatic control and the Ph.D. degree in electrical engineering both from the Universiti

Teknologi Malaysia, Johor Bahru, Malaysia, in 2011 and 2014, respectively. From 2014

to 2016, he was a research associate and then postdoctoral fellow at the UTMPROTON

Future Drive Laboratory, Universiti Teknologi Malaysia. From 2016 to 2017, he worked

as a lecturer in the Faculty of Engineering, Lincoln University College, Selangor,

Malaysia. In 2017, he joined the School of Electrical and Computer Engineering, Ajou

University, Suwon, South Korea, as a Research Professor, where he became an Assistant

Professor in 2018. His current research interests include electric machine drives,

renewable power generations, and power electronic converters.

Dr. Alsofyani was a recipient of the Brain Korea 21 Fellowship in 2017 and Ajou

University Research Excellence Award in 2019.

Conference Program

xvi

The table below shows an overview of the eSmarTA2021 Program.

Day 1: Tuesday 10th August, 2021

8:00 am – 8:50 am Registration

8:50 am - 9:00 am Arrival of guests

9:00 am - 9:05am National Anthem

9:05 am - 9:10 am Quran Kareem

9:10 am - 9:20 am Welcoming speech by Dr. Abdulaziz Al-hetar, the

eSmarTA2021 General Chair

9:20 am - 9:30 am Welcoming speech by Dr. Rida azimi, eSmarTA2021 Hon-

orary Chair

9:30 am - 9:40 am Speech of IEEE Yemen subsection by Dr. Ammar Zahary,

Director of IEEE Yemen subsection

9:40 am - 9:50 am Speech and officially opening eSmarTA2021 by Mr. Hussen

Haazeb, Minister of High Education

10:00 am–10:40 am Keynote Speech 1 by:

Prof. Dr. Tharek Abd Rahman, UTM, Malaysia

Title: “5G Standardization and Evolution”

10:40 am-10:50 am Refreshment

10:50 am–11:30 am Keynote Speech 2 by:

Dr. Ibrahim Mohd Alsofyani, Ajou University, Suwon, South

Korea

Title: “Future Electric Vehicles: Construction and Operation”

11:30 am–12:10 pm Keynote Speech 3 by:

Dr. Ali Nagi Nosary, Chief Executive Officer at TeleYemen,

Faculty of Engineering, Sana'a University, Yemen

Title: “Artificial Intelligence in Telecom Industry”

12:10 pm - 01:00 pm Break

1:00 pm – 1:40 pm Keynote Speech 4 by:

Prof. Dr. Nuno M. Garcia, Computer Science Engineering

University of Beira Interior, Covilhã, Portugal

Title: “5P Medicine and Smart IoT and applications: the

development of predictive algorithms”

1:40 pm-1:50 pm Refreshment

1:50 pm – 3:35pm Parallel Session 1

Auditorium MBA Suite (1)

6 papers 6 papers

Conference Program

xvii

Day 2: Wednesday 11th August, 2021

8:30 am – 9:00 am Registration

9:00 am – 9:40 am Keynote Speech5 by:

Dr. Mohamad Abou Ali, Lebanese International University,

Lebanon

9:40 am – 10:00 am Refreshment

10:00 am –12:15 pm Parallel Session 1


9 papers 9 papers

12:15 pm - 1:15 am Break

1:15 pm – 2:45 pm Parallel Session 2


6 papers 6 papers

2:45 pm – 3:00pm Close and Certificate

Day 3: Thursday 12th August, 2021

8:00 am - 1:00 pm Conference Trip to Wadi Daher, Sana'a (for Presenters only)

Title: “Medical Equipment Purchasing Informed Decision”

Paper Presentation Schedule

xix

Parallel Session I

Day1: Tuesday August 10th, 2021 (13:50 – 15:35), Location: Auditorium

Time ID Chaired by: Dr. Wail Sultan

Co-chaired by: Dr. Omer Alabsi

13:50 – 14:05 23 P300-based Speller Brain-Computer Interface

Tahany Alswoidy, Shaima Sharaf Adeen and Reham Alasbahi

14:05 – 14:20 49

Deep Attentional Bidirectional LSTM for Arabic Senti-

ment Analysis in Twitter

Hanane Elfaik and El Habib Nfaoui

14:20 – 14:35 46

The Role of Pre-trained Models in Covid-19 Diagnosis

using Chest X-Ray Images

Abdulfattah Ba Alawi, Ahmed Y. A. Saeed and Murad Rassam

14:50 – 15:05 64

Review of Internet Things(IoT) of Security Threats and

Challenges

Ahmed O. Ali and Qazwan Tarbosh

15:05 – 15:20 50

BLOCKCHAIN TECHNOLOGY IN HEALTHCARE BIG DATA

MANAGEMENT: Benefits, Applications and Challenges

Mahmmod A. Bazel, Fathey Mohammed and Mazida Ahmad

15:20 – 15:35 26

Smart Attendance System Based on Face Recognition

Techniques

Amr Al-Sabaeei, Amer Al-Basser, Hesham Al-Khateeb, Habeb

Al-Sameai, Mohammed Derhem and Mohammed Alshameri


xx

Parallel Session I

Day1: Tuesday August 10th, 2021 (13:50 – 15:35), Location: MBA Suite (1)

Time ID Chaired by: Dr. Radhwan Shadad

Co-chaired by: Dr. Sami Abdulaziz

13:50 – 14:05 36

PCM melting process in a quadruple tube heat exchanger

using Ansys

Abduljalil Alabidi

14:05 – 14:20 13

MATLAB/Simulink Medical CO2 Insufflator Model with

PID-PQT & MPC-PQT Controllers

Kinana Rashwani, Hussein Mohamad Wehby, Mariam Khay-

reldeen, Abdulhalim Mohamad, Mohamad I.C. Hajjhassan, Mo-

hamed Wadaane, Ahmad Elsayed, Ahmad Al-Naggar, Saeed

Bamashmos, Hassan Wehbi, Mohamad Hajj-Hassan, Mo-

hamad Abou Ali and Abdallah Kassem

14:20 – 14:35 70

Trajectory Generation and Optimization Algorithm for

Autonomous Aerial Robots

Yunes Al-Qadasi, Ayman Kassem and Gamal El-Bayoumi

14:50 – 15:05 40

Performance of Hrad Handover in 5G Heterogeneous

Networks

Jamil Sultan, Mubarak Mohsen, Nashwan Al-Thobhani and

Waheb Abduljabbar

15:05 – 15:20 65

Proposed Path Loss Model in Outdoor Environment at

28-GHz for 5G System in tropical region

Abdusalama Massoud Daho, Yamada Yoshihde and Ahmed Al-

Samman

15:20 – 15:35 51

Improved Performance in Compact Antenna by Using E-

slotted and DGS for V and E band 5G Applications

Hamdi Saif, Ehab A. G. Abdo and Akram H. M. Qahtan


xxi

Parallel Session II

Day2: Wednesday August 11th, 2021 (10:00 – 12:15), Location: Auditorium

Time ID Chaired by: Dr. Ibrahim Mohd Alsofyani

Co-chaired by: Dr. Jamil Sultan

10:00 – 10:15 60

DENGUE PREDICTION USING DEEP LEARNING WITH

LONG SHORT-TERM MEMORY

Abdulrazak Yahya Saleh and Lim Baiwei

10:15 – 10:30 58

A Markov Chain Model to Analyze the Entry-and-Stay

States of Frequent Visitors to Taiwan

I-Chen Lin and Wei-Hsi Hung

10:30 – 10:45 45

Automated translation for Yemeni’s Sign Language to

Text UsingTransfer Learning-based Convolutional Neu-

ral Networks

Rehab Abdualrahman Abdualkreem Mohammed Alsabaei,

Ruba Mansour Saleh Naji, Afnan Mahmoud Abdalkader Ah-

med, Dina Ahmed Ali Ghaleb Saeed and Mogeeb Mosleh

10:45 – 11:00 38

A Contactless Palm Veins Biometric System Based on

Convolutional Neural Network

Ebrahim A. M. Alrahawe, Vikas T. Humbe and G. N. Shinde

11:00 – 11:15 27

Yemeni Banknote Recognition Model based on Convolu-

tion Neural Networks

Ahmed Y. A. Saeed, Abdulfattah Ba Alawi and Ahmed N. Has-

san

11:15 – 11:30 52

IoT Based Temperature Control System of Home by us-

ing an Android Device

Musfiqur Rahman Foysal, Refath Ara Hossain, Mohammad

Monirul Islam, Shayla Sharmin and Nazmun Nessa Moon


xxii

11:30 – 11:45 6

Stock Market Analysis Using Linear Regression and De-

cision Tree Regression

Rezaul Karim, Md Khorshed Alam and Md Rezaul Hossain

11:45 – 12:00 41

A performance comparison of machine learning classifi-

ers for Covid-19 Arabic Quarantine tweets sentiment

analysis

Abdulqader Mohsen, Yousef Ali, Wedad Al-Sorori, Naseebah

A.Maqtary, Belal Al-Fuhaidi and Asma M.Altabeeb

12:00 – 12:15 61

Mobile Device and Social Media Forensic Analysis: Im-

pacts on Cyber-Crime

Debanjana Saha, Sajal Karmakar, Fernaz Narin Nur, Asma

Mariam, Nazmun Nessa Moon and Akash Ahmed

12:15 – 13:15 Break and Lunch

Parallel Session II

Day2: Wednesday August 11th, 2021 (10:00 – 12:15), Location: MBA Suite

(1)

Time ID Chaired by: Dr. Ibrahim Mohd Alsofyani

Co-chaired by: Dr. Jamil Sultan

10:00 – 10:15 73

Improve Energy and Spectral Efficiency in 5G Massive

MIMO System

Adeb Salh, Lukman Audah, Qazwan Tarbosh, Norsaliza Abdul-

lah, Nor Shahida Mohd Shah and Abdu Saif

10:15 – 10:30 75

A smart Access control for restricted buildings using ve-

hicle number plates Recognition System

Sharmarke Ali Kahie and Qazwan Tarbosh

10:30 – 10:45 37

Bridging the Digital Divide in Yemen

Ali Nagi Nosary and Ghada M. Al-Asadi


xxiii

10:45 – 11:00 68 Design of a EHG based Smart Labour Detection System

Nishanth Vg, Roshan E and Mohankumar N

11:00 – 11:15 16

High Bandwidth Triple-Band Microstrip Patch Antenna

for THz Applications

Esmat A. M. Aqlan, Redhwan Q. Shaddad, Ehab A. G. Abdo, Aseel

M. M. Alglal, Mohammed. A. A. Almogahed and Wahb. A. A. Ab-

dullah

11:15 – 11:30 30

Tethered UAV for Stable Energy of Emergency communi-

cation system

Abdu Saif, Kaharudin Kaharudin, Kamarul Kamarul Ariffin,

Nor Shahida Mohd Shah, Qazwan Abdullah and Saeed Alsamhi

11:30 – 11:45 14

Performance Analysis of OFDMA, UFMC, and FBMC for

Optical Wireless Communication

Sondos Alshami

11:45 – 12:00 31

Design A Compact Artificial Magnetic Conductor (Amc)

For SAR Reduction In WBAN Applications

Abdul Rashid. O. Mumin, Qazwan Abdullah Tarbosh, Abbas

Uğurenver, Y.A. Mahmud, Anisa Hussein, A.I. Salah and A.Y Ah-

med

12:00 – 12:15 72

A framework for designing students peer learning self-

regulation strategy system for blended courses

Rasheed Abubakar, Nor Aniza Abdullah, Amirrudin Kamsin,

Mustapha Abubakar Ahmed, Adamu Sani Yahaya and Kabir

Umar

12:15 – 13:15 Break and Lunch


xxiv

Parallel Session III

Day2: Wednesday August 11th, 2021 (13:15 – 15:00), Location: Auditorium

Time ID Chaired by: Dr. Radhwan Shadad

Co-chaired by: Dr. Amin Shaie

13:15 – 13:30 19

Surrogate Modeling Approach for Nonlinear Blending

Processes

Robert Franzoi, Tasabeh Ali, Aisha Al-Hammadi and Brenno

Menezes

13:30 – 13:45 48

Skin Lesions Recognition System Using Various Pre-

trained Models

Amer Farea, Abdulfattah Ba Alawi and Ahmed Y. A. Saeed

13:45 – 14:00 57

A Survey on Different Arabic Text Steganography Tech-

niques

Salah Al-Hagree, Mohammed Hadwan, Amal Aqlan, Fahd

Alqasemi, Mohammad Albazel and Maher Al-Sanabani

14:00 – 14:15 33

BirthRates Forecasting based on Artificial Neural Net-

works Versus Time Series Models

Fahd Alqasemi, Salah Al-Hagree, Muneer Alsurori, Mohammed

Hadwan, Zakaria Aljaberi and Amal Aqlan

14:15 – 14:30 66

Port-Scanning Attack Detection Using Supervised Ma-

chine Learning Classifiers

Akram Q. M. Algaolahi and Amer Sallam

14:30 – 14:45 71

Parasitized Cell Recognition Using AlexNet Pre-trained

Model

Abdulfattah Ba Alawi, Mogeeb Mosleh, Ziad Almohagry and

Ahmed Y. A. Saeed

14:45 – 15:30 Close and Certificate


xxv

Parallel Session III

Day2: Wednesday August 11th, 2021 (13:15 – 15:00), Location: MBA Suite

(1)

Time ID Chaired by: Dr. Jamil Sultan

Co-chaired by: Dr. Omer Alabsi

13:15 – 13:30 47

A review on applied Natural Language Processing to

Electronic Health Records

Anoual El Kah and Imad Zeroual

13:30 – 13:45 12

100-watt Matlab/Simulink Model LED Based Light

Source for Medical Endoscopy

Hussein Mohamad Wehby, Mariam Khayreldeen, Abdulhalim

Mohamad, Mohamad I.C. Hajjhassan, Mohamed Wadaane, Ah-

mad Elsayed, Kinana Rashwani, Ahmad Al-Naggar, Saeed

Bamashmos, Hassan Wehbi, Mohamad Hajjhassan, Mohamad

Abou Ali and Abdallah Kassem

13:45 – 14:00 18

The Digital Economy of Crowdsourcing: Crowd Shipping

Model as E-Business

Sarah Hassaan, Mohammed Yaqot and Brenno Menezes

14:00 – 14:15 17

Unmanned Aerial Vehicle (UAV) in Precision Agricul-

ture: Business Information Technology Towards Farm-

ing as a Service

Mohammed Yaqot and Brenno Menezes

14:15 – 14:30 20

Poverty in the Gaza Strip: Empowering the Unskilled

Workforce to Utilize International Crowdsourcing Mar-

kets and Platforms

Mustafa Abudalu, Brenno Menezes, Luluwah Al Fagih and Mo-

hammed Yaqot

14:30 – 14:45 35

Channel Estimation for Intelligent Reflection Surface in

6G Wireless Network via Deep Learning Technique

Redhwan Q. Shaddad, Esam M. Saif, Husam M. Saif, Zaid Y. Mo-

hammed and Ahmed H. Farhan

14:45 – 15:30 Close and Certificate

Table of Contents

xxvi

Organizing Committee ii

Technical Committee iv

Messages v

Keynote Speakers x

Conference Program xv

Paper Presentation Schedule xvii

Artificial Intelligence 1

Dengue Prediction Using Deep Learning with Long Short-Term

Memory

Abdulrazak Yahya Saleh and Lim Baiwei.

2

P300-based Speller Brain-Computer Interface

Tahany Alswoidy, Shaima Sharaf Adeen and Reham Alasbahi.

3

The Role of Pre-trained Models in Covid-19 Diagnosis using

Chest X-Ray Images

Abdulfattah Ba Alawi, Ahmed Y. A. Saeed and Murad Rassam.

4

Surrogate Modeling Approach for Nonlinear Blending Processes

Robert Franzoi, Tasabeh Ali, Aisha Al-Hammadi and Brenno Menezes.

5

Deep Attentional Bidirectional LSTM for Arabic Sentiment Anal-

ysis in Twitter

Hanane Elfaik and El Habib Nfaoui.

6

A Contactless Palm Veins Biometric System Based on Convolu-

tional Neural Network

Ebrahim A. M. Alrahawe, Vikas T. Humbe and G. N. Shinde

7

Automated translation for Yemeni’s Sign Language to Text Using

Transfer Learning-based Convolutional Neural Networks

Rehab Abdualrahman Abdualkreem Mohammed Alsabaei, Ruba

Mansour Saleh Naji, Afnan Mahmoud Abdalkader Ahmed, Dina Ah-

med Ali Ghaleb Saeed and Mogeeb Mosleh. 8

https://login.easychair.org/conferences/submission_reviews?a=26399683;submission=5459053



https://login.easychair.org/conferences/submission_reviews?submission=5444699;a=26399683









Table of Contents

Cybersecurity 9

Port-Scanning Attack Detection Using Supervised Machine Learn-

ing Classifiers

Akram Q. M. Algaolahi, Abdullah A. Hasan, Amer Sallam, Abdullah M.

Sharaf, Aseel A. Abdu and Anas A. Alqadi

10

Review of Internet Things (IoT) of Security Threats and Chal-

lenges

Fehim Köylü, Ahmed O. Ali, Mohamud M. Hassan, Muhiadin M. Sabriye,

Abdirisak Ali Osman, Ali Ammar Hilal and Qazwan Tarbosh.

11

Mobile Device and Social Media Forensic Analysis: Impacts on

Cyber-Crime

Debanjana Saha, Sajal Karmakar, Fernaz Narin Nur, Asma Mariam,

Nazmun Nessa Moon and Akash Ahmed.

12

A Survey on Different Arabic Text Steganography Techniques

Salah Al-Hagree, Mohammed Hadwan, Amal Aqlan, Fahd Alqasemi,

Mohammad Albazel and Maher Al-Sanabani.

13

Data Science 14

A Performance Comparison of Machine Learning Classifiers for

Covid-19 Arabic Quarantine Tweets Sentiment Analysis

Abdulqader Mohsen, Yousef Ali, Wedad Al-Sorori, Naseebah

A.Maqtary, Belal Al-Fuhaidi and Asma M.Altabeeb.

15

A Markov Chain Model to Analyze the Entry-and- Stay States of

Frequent Visitors to Taiwan

I-Chen Lin and Wei-Hsi Hung.

16













Table of Contents

Birth Rates Forecasting based on Artificial Neural Networks

Versus Time Series Models

Fahd Alqasemi, Salah Al-Hagree, Muneer Alsurori, Mohammed

Hadwan, Zakaria Aljaberi and Amal Aqlan.

17

Stock Market Analysis Using Linear Regression and Decision

Tree Regression

Rezaul Karim, Md Khorshed Alam and Md Rezaul Hossain.

18

Medical Informatics 19


MANAGEMENT: Benefits, Applications and Challenges

Mahmmod A. Bazel, Fathey Mohammed and Mazida Ahmad.

20

100-watt MATLAB/Simulink Model LED Based Light Source for

Medical Endoscopy

Hussein Mohamad Wehby, Mohamed Wadaane, Hassan Wehbi, Ma-

riam Khayreldeen, Ahmad Elsayed, Mohamad Hajjhassan, Abdul-

halim Mohamad, Ahmad Al-Naggar, Mohamad Abou Ali, Mohamad

I.C. Hajjhassan, Saeed Bamashmos, Abdallah Kassem and Kinana

Rashwani.

21

MATLAB/Simulink Medical CO2 Insufflator Model with PID-PQT

& MPC-PQT Controllers

Kinana Rashwani, Mohamed Wadaane, Hassan Wehbi, Hussein Mo-

hamad Wehby, Ahmad Elsayed, Mohamad Hajjhassan, Mariam Khay-

reldeen, Ahmad Al-Naggar, Mohamad Abou Ali, Abdulhalim Mohamad,

Saeed Bamashmos, Abdallah Kassem and Mohamad I.C. Hajjhassan.

22










Table of Contents

A Review on Applied Natural Language Processing to Electronic

Health Records

Anoual El Kah and Imad Zeroual.

23

Intelligent Computing and Communication Networks 24

Performance of Hrad Handover in 5G Heterogeneous Networks

Jamil Sultan, Mubarak Mohsen, Nashwan Al-Thobhani and Waheb Ab-

duljabbar.

25


Ali Nagi Nosary and Ghada M. Al-Asadi

26

A Smart Access Control for Restricted Buildings Using Vehicle

Number Plates Recognition System

Sharmarke Ali Kahie, Abdullahi Ahmed Nor, Ahmed Hashi Hasan, Asho

Mohamed Abdi, Liiban Mutafa Hassan, and Mohamed Ahmed Mo-

hamud

27

Performance Analysis of OFDMA, UFMC, and FBMC for Optical

Wireless Communication

Sondos Alshami

28

Improved Performance in Compact Antenna by Using E-slotted

and DGS for V and E band 5G Applications

Hamdi Saif, Ehab A. G. Abdo and Akram H. M. Qahtan

29

High Bandwidth Triple-Band Microstrip Patch Antenna for THz

Applications

Redhwan Q. Shaddad, Esmat A. M. Aqlan, Ehab A. G. Abdo, Mohammed.

A. A. Almogahed, Aseel M. M. Alglal and Wahb. A. A. Abdullah

30













Table of Contents

Trade-off Energy and Spectral Efficiency with Multi-Objective

Optimization Problem in 5G Massive MIMO System

Adeb Salh, Lukman Audah, Qazwan Tarbosh, Norsaliza Abdullah, Nor

Shahida Mohd Shah and Abdu Saif

31

Proposed Path Loss Model in Outdoor Environment at 28-GHz for

5G System in tropical region

Abdusalama Massoud Daho, Yamada Yoshihde, Ahmed Al-Samman,

TharekAbdrahman, Marwan Hadri Azmi and Arsany Arsad.

32

Channel Estimation for Intelligent Reflection Surface in 6G Wire-

less Network via Deep Learning Technique

Redhwan Q. Shaddad, Esam M. Saif, Husam M. Saif, Zaid Y. Mohammed

and Ahmed H. Farhan.

33

IoT Based Temperature Control System of Home by using an An-

droid Device

Musfiqur Rahman Foysal, Refath Ara Hossain, Mohammad Monirul Is-

lam, Shayla Sharmin and Nazmun Nessa Moon.

34

Business Information Technology 35

Unmanned Aerial Vehicle (UAV) in Precision Agriculture: Busi-

ness Information Technology Towards Farming as a Service

Mohammed Yaqot and Brenno Menezes.

36

Poverty in the Gaza Strip: Empowering the Unskilled Workforce

to Utilize International Crowdsourcing Markets and Platforms

Mustafa Abudalu, Brenno Menezes, Luluwah Al Fagih and Mohammed

Yaqot.

37

The Digital Economy of Crowdsourcing: Crowd Shipping Model as

E-Business

Sarah Hassaan, Mohammed Yaqot and Brenno Menezes.

38














Table of Contents

Image Processing and Computer Vision 39

Parasitized Cell Recognition Using AlexNet Pre-trained Model

Abdulfattah Ba Alawi, Mogeeb Mosleh, Ziad Almohagry and Ahmed Y.

A. Saeed.

40

Skin Lesions Recognition System Using Various Pre-trained Models

Amer Sallam, Abdulfattah Ba Alawi and Ahmed Y. A. Saeed.

41

Yemeni Banknote Recognition Model based on Convolution Neu-

ral Networks

Ahmed Y. A. Saeed, Abdulfattah Ba Alawi and Ahmed N. Hassan.

42

Smart Attendance System Based on Face Recognition Techniques

Amr Al-Sabaeei, Amer Al-Basser, Hesham Al-Khateeb, Habeb Al-

Sameai, Mohammed Derhem and Mohammed Alshameri.

43

Special Topics in Smart Technologies 44

A Framework for Designing Students Peer Learning Self-Regula-

tion Strategy System for Blended Courses

Rasheed Abubakar, Nor Aniza Abdullah, Amirrudin Kamsin, Mustapha

Abubakar Ahmed, Adamu Sani Yahaya and Kabir Umar

45

Design A Compact Artificial Magnetic Conductor (AMC) For SAR

Reduction in WBAN Applications

Abdul Rashid. O. Mumin, Qazwan Abdullah Tarbosh, Abbas Abbas

UĞurenver, Y.A Mahmud, Anisa Hussein, A.I Salah and A.Y Ahmed.

46

Energy-Efficient Tethered UAV Deployment in B5G for Smart En-

vironments and Disaster Recovery

Abdu Saif, Kaharudin Kaharudin, Kamarul Kamarul Ariffin, Nor Sha-

hida Mohd Shah, Saeed Alsamhi and Qazwan Abdullah.

47










Table of Contents

Trajectory Generation and Optimization Algorithm for Autono-

mous Aerial Robots

Yunes Al-Qadasi, Ayman Kassem and Gamal El-Bayoumi.

48

PCM Melting Process in a Quadruple Tube Heat Exchanger Using

Ansys Software

Abduljalil Alabidi.

49

Design of a EHG based Smart Labour Detection System

Nishanth Vg, Roshan E and Mohankumar N.

50






Abstracts

1

Artificial Intelligence

Abstracts

2

Dengue Prediction Using Deep Learning with Long Short-Term

Memory

Abdulrazak Yahya Saleh

FSKPM Faculty

Universiti Malaysia Sarawak

(UNIMAS)

Kota Samarahan, Sarawak, Malaysia

[email protected]

Lim Baiwei

FSKPM Faculty

Universiti Malaysia Sarawak

(UNIMAS)

Kota Samarahan, Sarawak, Malaysia

[email protected]

Abstract— Dengue is a severe infectious disease on the rise in Malaysia, and there is

a demand for artificial intelligence to support the health system. However, the appli-

cation of deep learning, specifically Long Short-Term Memory (LSTM) time series

forecasting, has not been explored by many in dengue prediction studies. However,

considering the availability of daily weather data being collected, the ability of LSTM

to capture long term dependencies can be leveraged in forecasting dengue cases.

Therefore, this study investigates the performance and viability of LSTM time series

forecasting on predicting dengue cases. An LSTM model is developed and evaluated

to be compared to a Support Vector Regression (SVR) model by utilising the availa-

bility of a dengue dataset consisting of weather and climate data. The results indicated

LSTM time series forecasting performed better than SVR, with R2 and MAE scoring

0.75 and 8.76. In short, LSTM has shown better performance and, in addition, cap-

turing trends in the rise and fall of dengue cases. Altogether, this research could con-

tribute to the fight against the increase of dengue cases without relying on forecasted

weather data but instead, history.

Keywords— LSTM, Time series forecasting, Deep learning, dengue.

Abstracts

3

P300-based Speller Brain-Computer Interface

Tahany Alswoidy

Electrical Engineering

Sana’a University

Sana’a, Yemen

tahan-

[email protected]

Shaima Sharaf_Adeen


Sana’a University

Sana’a, Yemen

shaima.ah-

[email protected]

Reham Alasbahi


Sana’a University

Sana’a, Yemen

[email protected]

Abstract— Millions of people with motor disabilities so severe that they cannot communicate

with their families. In spite of their motor disabilities, sensory and cognitive functions are usually

still enabled. For instance, people with spinal cord injuries or amyotrophic lateral sclerosis (ALS),

also called Lou Gehrig’s disease. For those people brain-computer interface (BCI) may be the only

hope. BCI is a system that conveys messages and commands directly from the human brain to a

computer. The described BCI system in this paper is based on the P300 wave. The P300 is a positive

peak of an event-related potential (ERP) that occurs 300 ms after a stimulus in the electroenceph-

alography (EEG) signals. One of the best-known and most widely used P300 applications is the P300

speller designed by Farwell-Donchin in 1988. In this project the used P300 paradigm is constructed

as a 6 X 6 matrix of letters and numbers is displayed, and the subject focuses on a target character

while rows and columns of characters flashing. Through detection of P300 for one row and one col-

umn, the target character can be identified. EEG recordings dataset of four subjects was used, with

each dataset consists of two different sessions data. In each session, the user spelt a total of (33, 36

characters including spaces) for train and test phases, respectively. The EEG data passes through

different stages those are resampling, preprocessing, feature extraction, classification, and perfor-

mance evaluation. The used classifier is a regularized linear discriminant analysis (RLDA) classifier

which is a type of linear discriminant analysis(LDA). Typical LDA is not likely to be adequate be-

cause of the degradation of classification accuracy due to the high dimensionality, in other words,

the number of features is greater than the number of samples. The classification results of ERP para-

digm resulted by an average classification accuracy of 97.57% across the four subjects and average

information transfer rates (ITRs) of 21.6 bits/min and 21.4 bits/min in the first and second sessions,

respectively. Finally, with this speller we tried to use technology in a way that benefits humanity

generally and medicine particularly and improves patient’s life.

Keywords—brain computer interface, speller, ERP, P300.

mailto:[email protected]





Abstracts

4

The Role of Pre-trained Models in Diagnosing Covid-19 Using

Chest X-Ray Images

Abdulfattah E. Ba Alawi

Software Engineering Dept.

Taiz University

Taiz, Yemen

baalawi.abdulfat-

[email protected]

Ahmed Y. A. Saeed

Software Engineering Dept.

Taiz University

Taiz, Yemen

[email protected]

Murad A. Rassam

Computer Networks & Dis-

tributed Systems Dept.

Taiz University

Taiz, Yemen

[email protected]

Abstract— the recent outbreak of the novel coronavirus affects the globe. It was in a

major city of China called "Wuhan" where COVID-19 first appeared. This new disease is

caused by a novel, or new coronavirus and deemed to be a worldwide pandemic. This

extreme virus, which spreads by human contact, is now invading more than two hundred

countries across the world. In comparison, new coronavirus signs are very close to the

general seasonal influenza. The screening of infected people in the war against COVID-

19 is seen as a crucial step for controlling and fighting the spread of this infectious virus.

Rapid diagnosis is of so high priority that suspected cases are identified as early as possi-

ble to guarantee a control over the spread of this disease. This paper investigates the use

of pretrained models in diagnosing Covid-19 infected patients using Chest X-ray (CXR).

The transfer learning techniques have been applied to pre-trained models for an image

classification task. The result obtained showed that these models have a high performance

in the diagnosis process. Results are so promising that they reached more than 94% in

testing cases.

Keywords— Covid-19, Chest X-ray, Radiologist, Coronavirus, Pre-trained Model.





Abstracts

5

Surrogate Modeling Approach for Nonlinear Blending Processes

Robert E. Franzoi

Division of Engineering Management and

Decision Sciences,

College of Science and Engineering Hamad Bin Khalifa University

Doha, Qatar

rfranzoi@ hbku.edu.qa

Tasabeh Ali


Decision Sciences,

College of Science and Engineering Hamad Bin Khalifa University

Doha, Qatar

[email protected]

Aisha Al-Hammadi

Division of Engineering Management and Decision Sciences,

College of Science and Engineering

Hamad Bin Khalifa University Doha, Qatar

[email protected]

Brenno C. Menezes

Division of Engineering Management and Decision Sciences,


Hamad Bin Khalifa University Doha, Qatar

[email protected]

Abstract— Surrogate models have been increasingly used for predicting the behavior of

functions or systems as an alternative to complex or unknown formulations. In this work, we

address the use of surrogates for the blending operations of continuous processes, in which

nonlinear equations are successfully approximated by simpler linear or bilinear formulas. The

surrogate model building framework consists of four main steps. First, training and testing data

sets are constructed by using the Latin Hypercube Sampling (LHS) technique in addition to

nonlinear blending equations derived from material balances. Second, a data improvement pro-

cedure based on data normalization is performed to mitigate numerical issues and biased sur-

rogates. Third, a mixed-integer quadratic programming (MIQP) formulation based on the least-

squares regression builds optimizable surrogate functions for the variables of interest from the

blending operations. Fourth, a performance check evaluates the accuracy and robustness of the

surrogate model. Several features concerning surrogate model building strategies are investi-

gated in this work, including data set size, surrogate size, complexity, and functional form,

statistical analyses on the reliability of the predictions, and performance of the surrogates when

embedded in optimization environments. The method is tested over a blending operations prob-

lem and the results indicate that the surrogates are properly built, have high accuracy, and suc-

cessfully replace the original blending formulation within optimization environments. This

methodology can be further employed for larger and more complex systems, especially when

multiple blending operations are performed throughout the plant.

Keywords — Surrogate modeling, Blending operations, Datadriven, Machine learning




Abstracts

6

Deep Attentional Bidirectional LSTM for Arabic Sentiment

Analysis in Twitter

Hanane ELFAIK LISAC

Laboratory, FSDM

Sidi Mohamed Ben Abdellah Univer-

sity

Fez, Morocco

[email protected]

El Habib NFAOUI LISAC

Laboratory, FSDM

Sidi Mohamed Ben Abdellah Univer-

sity

Fez, Morocco

[email protected]

Abstract—Along with the emergence of user reviews, emotions, feedback, and opin-

ions in social networks towards a specific topic, product, event, or such a service. Senti-

ment Analysis has recently considered one of the fundamental research areas which lie at

the intersection of numerous fields of research include data mining, computational lin-

guistics, and Natural Language Processing (NLP). It concerns classifying a given piece of

writing into sentiment polarity. Furthermore, deep learning has shown rich data modelling

abilities to deal with complex and large datasets, in addition, it is recognized as the state-

of-the-art based approach for different research fields. Although, the current state-of-the-

art sentiment analysis tailored to the Arabic language still needs improvements because

of its morphological richness, ambiguity, and lack of its resources. To advance this task,

a novel Attentional Bidirectional LSTM architecture was proposed in order to determine

richer semantic information and to extract the contextual information in both directions.

We also investigated the effect of the word2vec pre-trained model to produce the word

embeddings representation and to capture semantic information from Arabic tweets. To

validate the performance of the proposed architecture, we assessed it in a holistic setting

across three benchmark Arabic sentiment tweets datasets. Thus, the experimental results

demonstrate that the proposed architecture outperforms the current state-of-the-art deep

learning-based methods. Besides, it performs well compared with the baseline classical

machine learning methods.

Keywords— sentiment analysis, word2vec, deep learning, Bidirectional LSTM, At-

tention mechanism, Twitter, Arabic language.



Abstracts

7

A Contactless Palm Veins Biometric System Based on

Convolutional Neural Network

Ebrahim A. M. Alrahawe

School of Computational Sci-

ences

S.R.T.M. University

Nanded, Maharashtra, India

[email protected]

Vikas T. Humbe

School of Technology

S.R.T.M. University,

Sub Center Latur Maharash-

tra, India

[email protected]

G. N. Shinde

Yeshwant College Nanded,

Maharashtra, India

[email protected]

Abstract— Personal recognition systems have emerged as highly important in the in-

formation society. Biometric systems are widely used because its reliability in distinguish-

ing between the subjects. Contactless biometric systems are more important because of

their advantages, especially, recently, during the current pandemic of COVID19 as they

can be used to avoid the spread of such viruses. The use of hidden biometric traits is more

secure, which makes the trait unable to stolen or duplicated, especially if the recognition

in the live-ness process. Convolutional neural networks (ConvNet) have also gained a

great success in large-scale image. Especially, in case of use the transfer learning tech-

niques. In this study, we try to produce a contactless biometric system based on palm veins

and use of Tungji large-scale contactless dataset to implement the system. This paper,

divided into seven sections, starts with the general introduction; an overview on the related

work and techniques used are in the second section; the third section about motivations

and contribution of this work; the methodologies and dataset description the forth section;

the proposed work and its results with implementation steps in the fifth section; continu-

ally to the comparison the current proposed system with the available in the literature in

the section six, then the conclusion figured out in the last section.

Keywords— Palm vein, biometric, contactless, touchless, large-scale dataset, convo-

lutional neural networks (ConvNet).



Abstracts

8

Automated translation for Yemeni’s Sign Language to Text

UsingTransfer Learning-based Convolutional Neural Networks

Rehab A. A. Mohameed

Software Engineering Dept

Taiz University

Taiz,Yemen

[email protected]

Afnan M. A. Ahmeed


Taiz University

Taiz,Yemen

[email protected]

Ruba M. S.Naji


Taiz University

Taiz,Yemen

[email protected]

Dina A. A. Saeed


Taiz University

Taiz,Yemen

[email protected]

Mogeeb A. A. Mosleh


Taiz University

Taiz,Yemen Mogeeb

[email protected]

Abstract— Self-expression and understanding people language are among the most

important things to be considered. Deaf and dumb is a group of that they facing difficulty

to express themselves and communicate with others. This group of people is trying to

communicate with others using "sign language". This study is design to enhance the com-

munication channel between these people with their society using technology. A prototype

system was design to translate the Yemeni sign language into text. Deep learning algo-

rithms included in the system using convolutional neural network (CNN) with various

transfer Learning models. System evaluation is used torch and tensorflow libraries as

training and testing dataset of Yemeni sign language. Accuracy comparison results ob-

tained among various models included in this study such as Visual Geometry Group

(VGG16), Residential Energy Services Network (ResNet), Google Network (GoogleNet),

and Densely Connected Convolutional Network (DenseNet). We found that the accuracy

results obtained for each model were (ConveNet = 98.66%), (Sequential CNN= 98.34%),

(GoogleNet = 98.36%), (Vgg16 = 90,46%), (DenseNet = 99.65%), and the best result was

(ResNet152 = 99.78%). This study showed the ability of technology to enhance the com-

munication methods between deaf and their society with a suitable translation accuracy.

Keywords— Transfer learning, CNN, Arabic sign language, Deep learning, hand ges-

tures.






Abstracts

9

Cybersecurity

Abstracts

10

Port-Scanning Attack Detection Using Supervised Machine

Learning Classifiers

Akram Q. M. Algaolahi

Dept. of Computer Networks

and Distributed Systems

Faculity of engineering and

IT

Taiz University

Taiz, Yemen

[email protected]

Abdullah A. Hasan




IT

Taiz University

Taiz, Yemen

abdullahalmajeedy@out-

look.com

Amer Sallam




IT

Taiz University

Taiz, Yemen

[email protected]

Abdullah M. Sharaf




IT

Taiz University

Taiz, Yemen

[email protected]

Aseel A. Abdu




IT

Taiz University

Taiz, Yemen

aseelal-

[email protected]

Anas A. Alqadi




IT

Taiz University

Taiz, Yemen

[email protected]

Abstract—Different attacks are done on data confidentiality, integrity, and availability.

A famous type of network attacks is Port Scanning. Port Scanning attacks are done by

attackers to know gather information about the devices and to know what services are

running on. This study focuses on detecting port scanning attacks by using different ma-

chine learning algorithms and comparing between them to find the best one. Some algo-

rithms reach near 100 percent of accuracy with detecting this type of attacks like Decision

Tree and Random Forest with short time of training and testing.

Keywords—Cybersecurity, Machine learning, Port-Scanning, Intrusion Detection

System (IDS).


Abstracts

11

Review of Internet Things (IoT) of Security Threats and Challenges

Fehim Köylü

Faculty of Computer Engi-

neering

Erciyes University

Kayseri TURKEY

[email protected]

Ahmed O. Ali

Faculty of Computer Infor-

mation and Engineering

Technology

Zamzam University

Mogadishu, Somali

[email protected]

Mohamud M. Hassan



Technology

Zamzam University

Mogadishu, Somali

[email protected]

Muhiadin M. Sabriye



Technology

Zamzam University

Mogadishu, Somali

[email protected]

Abdirisak Ali Osman



Technology

Zamzam University

Mogadishu, Somali

[email protected]

Ali Ammar Hilal

Faculty of Computer Engi-

neering

Erciyes University

Kayseri TURKEY

[email protected]

Qazwan Abdullah

Faculty of Electrical and

Electronic Engineering

Universiti Tun Hussein Onn

Malaysia Johor, Malaysia

[email protected]

Abstract— In recent years, the Internet of Things (IoT) has received a lot of research

attention. The IoT is considered part of the Internet of the future and is made up of billions

of intelligent communication “things”. The future of the Internet will consist of heteroge-

neously connected devices that expand the world’s boundaries with physical entities and

virtual components. The Internet of Things (IoT) provides new functionality for related

things. This study systematically examines the definition, architecture, essential technol-

ogies, and applications of IoT. First, I will introduce various definitions of IoT. Next, it

will be discussed new techniques for implementing IoT. Third, several open issues related

to IoT applications will be investigated. Finally, the key challenges that need to be ad-

dressed by the research community and possible solutions to address them are investi-

gated.

Keywords – Internet of Things (IoT), Security Threats, Challenges






Abstracts

12

Mobile Device and Social Media Forensic Analysis: Impacts on

Cyber-Crime

Debanjana Saha

Department of Computer Sci-

ence and Engineering

Daffodil International Uni-

versity

Dhaka, Bangladesh

[email protected]

Sajal Karmakar

Department of Economics

Noakhali Science and Tech-

nology Engineering

Noakhali, Bangladesh

[email protected]

Fernaz Narin Nur



Notre Dame University

Dhaka, Bangladesh

[email protected]

Asma Mariam




versity

Dhaka, Bangladesh

[email protected]

Nazmun Nessa Moon




versity

Dhaka, Bangladesh

moon@daffodilvar-

sity.edu.bd

Akash Ahmed




versity

Dhaka, Bangladesh

[email protected]

Abstract—This research work has focused on a digital forensic analysis of social media

through mobile devices to determine the primary criminal. This proposed system consid-

ered the mobile device used by the prime suspect as the main evidence of cybercrime and

tried to find out the degree of criminal involvement in terms of probability likelihood. At

first, the most critical data elements were obtained, e.g., deleted files and keywords,

through the forensic analysis of the mobile device. This will also help in the identification

of the main culprits in the investigation of cybercrime. Next, the system classified the

criminals in one of three zones based on the analysis of the keywords to determine the

level of crime. The system also takes into account the most probable timeframe for the

crime. Thus, the proposed system helps to identify the main culprits in investigating cy-

bercrime more efficiently than the traditional approaches. The system is also looking into

the most probable timeframe for the crime, for example, it has been observed that most

cybercrime happens on the weekends. The proposed system investigates using cookies

and the logical image of the device that cyber criminals left behind.

Keywords—Cybercrime; Forensic analysis; Logical image; Mobile device; Timestamps.







Abstracts

13

A Survey on DifferentArabic Text Steganography Techniques

Salah AL-Hagree


ences & Information Tech-

nology

IBB University, Yemen.

[email protected]

Mohammed Hadwan

Department of Information

Technology,

College of Computer, Qassim

University

Buriydah, Saudi Arabia.


ence

Faculty of Applied Sciences

Taiz University, Taiz, Yemen.

[email protected]

Amal Aqlan


ences,

King Khalid University, KSA.

[email protected]

Mohammad Albazel

Information Technology De-

partment

University of Science and

Technology, Yemen.

[email protected]

Fahd Alqasemi

Information Technology De-

partment


Technology, Yemen.

[email protected]

Maher Al-Sanabani

Faculty of Computer Science

and Information Systems

ThamarUniversity,Yemen

[email protected]

Abstract—This research reviewed the different steganography techniques used to hide

secrets within Arabic text. In this paper, we aim to provide an overview of Arabic text

steganography techniques from literature and previous studies that used Arabic language.

Due to the rapid development in steganography techniques and different medium used to

hide secrets and send it over internet, review the Arabic text steganography is important.

Hiding text within Arabic language is the art of invisible communication to keep the in-

formation confidentiality due to the unique characteristics and features of Arabic lan-

guage. Arabic text Steganography technique has many benefits that can be further used

for Arabic-similar languages or any languages written in Arabic letters such as Pashto

language (the official of Afghanistan language), Persian language (the official of Iran lan-

guage) and Urdu language (the official of Pakistan language).Nevertheless, many Arabic

text steganography techniques have been introduced in Arabic, some of which will be

covered in this paper.

Keywords:—Arabic Language, Text Steganography, Arabic Steganography, Unicode

letters.







Abstracts

14

Data Science

Abstracts

15

A Performance Comparison of Machine Learning Classifiers for

Covid-19 Arabic Quarantine Tweets Sentiment Analysis

Abdulqader Mohsen

University of Science

and Technology

Sana’a, Yemen

mohsenabdul-

[email protected]

Yousef Ali


and Technology

Sana’a, Yemen

[email protected]

Wedad Al-Sorori


and Technology

Sana’a, Yemen

w.al-

[email protected]

Naseebah A.Maqtary


and Technology

Sana’a, Yemen

[email protected]

Belal Al-Fuhaidi


and Technology

Sana’a, Yemen

[email protected]

Asma M.Altabeeb


and Technology

Sana’a, Yemen

asmam.alta-

[email protected]

Abstract—The COVID-19 pandemic has spread across the world and has become an in-

ternational public health emergency. The outbreak of COVID-19 has focused attention on

the use of quarantine and social distancing as the primary defense strategies against com-

munity infection. Arabic language, as one of the most spoken languages in the world, and

the fastest-growing language on the Internet motivates us to provide reliable automated

tools that can perform sentiment analysis to reveal users’ opinions. This paper was pro-

posed to utilize machine learning (ML) methods for Arabic Sentiment Analysis to under-

stand the positive and negative opinions related to quarantine and social distancing during

the outbreak of COVID-19. We provided a model of different essential and ensembles

ML classifiers and compared their effectiveness in classifying the collected imbalanced

dataset. Moreover, the application of a variety of SMOTe (Synthetic Minority Over-sam-

pling Technique ) for our imbalanced dataset was evaluated. The results demonstrated that

SMOTe Edited Nearest Neighbor (SMOTEENN) outperformed other SMOTe techniques.

Moreover, the results showed that ensemble classifiers are more robust with imbalanced

datasets than single classifiers. On the other hand, the overall average of F1 score of single

classifiers is more robust than ensemble classifiers when applying SMOTEENN.

Index Terms—Arabic sentiment analysis, Coronavirus, Word embedding, Imbalanced

dataset, Ensemble learning

Abstracts

16

A Markov Chain Model to Analyze the Entry-and-Stay States of

Frequent Visitors to Taiwan

I-Chen Lin

Department of Management Information

Systems

National Chengchi University

Taipei, Taiwan

[email protected]

Wei-Hsi Hung

Department of Management Information

Systems

National Chengchi University

Taipei, Taiwan

[email protected]

Abstract—A model to predict the immigration behaviors of frequent visitors would help

to improve clearance services and resource allocation at a country’s border. This research

uses Markov process to analyze the entry-and-stay states of frequent visitors based on

their immigration records. Prior studies have lacked quantitative information about the

entry and stay states of travelers at the border. In this study, the following attributes were

drawn from the immigration records: (1) entry and exit date, (2) entry and exit frequency,

and (3) duration of stay. We calculated a transition probability matrix containing all tran-

sition probabilities between each entry-and-stay states of visitors. When entry event of a

visitor occurs in a certain state, we can estimate the possible state in the next period and

the equilibrium probability by using the transition matrix. We determines the transition

state of visitors entering Taiwan, and to consider the overall transition probabilities to

predict the immigration behaviors. The model results in the steady-state probability. The

state S5 (Entering 2 to 8 times and staying 3 to 6 days) has the highest probability of

27.99%. The definition of frequent visitor can be revised by the implication of state S5 to

improve future decisions and immigration services based on these results.

Keywords—frequent visitors; transition matrix; Markov chains; Markov process;

Datamining

Abstracts

17

BirthRates Forecasting based on Artificial Neural Networks Versus

Time Series Models

Fahd Alqasemi

Information Technology

Department


Technology ,Yemen.

[email protected]

Salah AL-Hagree

Department of Computer

Sciences

& Information Technology

IBB University,Yemen.

[email protected]

Muneer Alsurori


Sciences


IBB University,Yemen

[email protected]

Mohammed Hadwan


Technology,

College of Computer, Qas-

sim University Buriydah,

Saudi Arabia.


Science Faculty of Applied

Sciences

Taiz University, Taiz,

Yemen.

[email protected]

Zakaria Aljaberi


Sciences


IBB University,Yemen

Zakari-

[email protected]

Amal Aqlan


Sciences,

King Khalid University,

KSA.

[email protected]

Abstract—Birthrates forecasting can help decision-makers to understand population in-

crement patterns, in addition to many issues that support governmental decisions, espe-

cially in developing countries as Yemen. Data Mining has important new emerged tech-

nologies, support business, and decision-making requirements. Forecasting is one of Ar-

tificial Neural Networks (ANN) and Time Series (TS) applications, as data mining tech-

niques. In this paper, birthrates two forecasting models have experimented with. The ANN

and TS are used for forecasting Yemeni hospital births data. Monthly birthrates data of

four years are processed by each model. The forecasting of monthly next four years had

produced, based on each model. Outcomes evaluation is showed the accuracy of forecast-

ing results. Besides, TS outperforms the ANN model, in the context of monthly births data

forecasting of Yemeni hospital data.

Keywords:—Data Mining, Time Series, ARIMA Time Series, Birthrates Estimation, Ar-

tificial Neural Networks, Forecasting Model, Yemen healthcare.

Abstracts

18

Stock Market Analysis Using Linear Regression and Decision Tree

Regression

Rezaul Karim*

School of Big Data &

Software engineering

Chongqing University

Chongqing, China

Rezaulka-

[email protected]

Md Khorshed Alam

School of Big Data &

Software engineering

Chongqing University

Chongqing, China

khorsheda-

[email protected]

Md Rezaul Hossain

Daffodil International

University

Dhaka, Bangladesh

rezaulhoss-

[email protected]

Abstract— In business, the Stock market or Share market is a more perplexing and so-

phisticated way to do business. Every business owner wants to reduce the risk and make

an immense profit using an effective way. The bank sector, brokerage corporations, small

ownerships, all depends on this very body to earn profit and reduce risks. However, using

the machine learning algorithm of this paper to predict the future stock price and shuffle

by using subsist algorithms and open source libraries to assist in inventing this unsure

format of business to a bit more predictable. The proposed system of this paper works in

two methods – Linear Regression and Decision Tree Regression. Two models like Linear

Regression and Decision Tree Regression are applied for different sizes of a dataset for

revealing the stock price forecast prediction accuracy. Moreover, the authors of this paper

have revealed some development that could be the club to acquire better validity in these

approaches.

Keywords —Data Analysis, Linear Regression, Decision Tree Regressor, Big Data, Stock

Market Analysis, Supervised Machine Learning.

Abstracts

19

Medical Informatics

Abstracts

20


MANAGEMENT: Benifites, Applications and Challenges

Mahmood A. Bazel

School of Computing

Universiti Utara Malaysia

(UUM)

06010 Sintok

Kedah, Malaysia

mahmood_abdul-

[email protected]

Fathey Mohammed

School of Computing


(UUM)

06010 Sintok

Kedah, Malaysia

[email protected]

Mazida Ahmed

School of Computing


(UUM)

06010 Sintok

Kedah, Malaysia

[email protected]

Abstract—Healthcare transformation has become a major priority in a world where ex-

traordinary technological breakthroughs are occurring. Current healthcare data manage-

ment systems are centralized, posing the possibility of a single point of failure in the event

of a natural disaster. Blockchain has rapidly risen to become one of the most talkedabout

innovations that can tackle many of current data management challenges in the healthcare

industry. The use of blockchain technologies for the delivery of safe and secure healthcare

data has sparked a lot of interest. Blockchain has the potential to reduce or eliminate many

of the most significant challenges of today's healthcare big data management such as pa-

tient consents, data ownership, information governance, data auditing, privacy, security,

traceability, immutability, flexible access and the reconciliation of conflicting changes

from multiple sources. With these potential benefits of blockchain, there are few previ-

ously published researches have focused on the role of blockchain in healthcare big data

management. In this paper, we aim at enriching the body of literature by exploring the

potentials of blockchain for improving healthcare big data management systems. The pa-

per provides an expanded view of the important aspects of the blockchain including the

main features, the opportunities of implementation in the management of healthcare big

data, as well as the challenges that impedes its acceptance in healthcare context

Keywords— Blockchain, Health, Healthcare, Healthcare data management, healthcare

big data




Abstracts

21

100-watt MATLAB/Simulink Model LED Based Light Source for

Medical Endoscopy

Hussein Wehby

Dept. of Biomedical Engineer-

ing

Lebanese International Uni-

versity

Joub Jannine, Beqaa, Lebanon

[email protected]

Mohamad Wadaane


ing

Lebanese International Univer-

sity


[email protected]

Hassan Wehbi

Research & Development,

INGENIOUS

Medical GmbH,

Germany

Hassan.wehbi@ingenious-

medical.de

Mariam Khayreldeen

Dept. of Biomedical Engineering


sity


[email protected]

Ahmad ElSayed


ing


versity


[email protected]

Mohamad HajjHassan

Department of Biomedical En-

gineering,

American International Univer-

sity,

Kuwait

[email protected]

Abdulhalim Mohamad


ing


versity


[email protected]

Ahmed N. Al-naggar



sity

Sana’a, Yemen

ahmed.al-

[email protected]

Mohamad Abou Ali


ing


versity


Mo-

[email protected]

Mohamad I.C. HajjHassan


ing


sity


[email protected]

Saeed Bamashmos


ing


versity

Sana’a, Yemen

saeed.bam-

[email protected]

Abdallah Kassem

ECCE Dept., Faculty of Engi-

neering,

Notre Dame University-Louaize,

Zouk Mosbeh, Lebanon

[email protected]

Kinana Rashwani


Lebanese International University


[email protected]

Abstract— This work is a step forward to develop, design and manufacturing of 100-watt enoscopic LED light sources

for the sponsor of this work endoscopic German manufacturer and supplier “Ingenious Medical”. The Greek prefix “endo”

means “within, inside”. Endoscopes are scopes to view inside. More precisely, medical endoscopes are devices used to view

internal human body organs and cavities to diagnose or perform a surgery. This needs optimum control of light intensity to

provide comfortable surgeon’s view during surgery. There are three major categories of light sources used in endoscopy:

LED, halogen and xenon. Based on its benefits, LED light sources dominate in surgical theatres. In our work, 100-watt

endoscopic LED light source MATLAB/Simulink model has been developed and tested virtually. Our 100-watt LED power

supplier and controller MATLAB/Simulink model consists of: AC-DC medical SMPS converter with an input “AC -

220V/0.45A” & an output “DC - 12V/8.3A”, DC-DC buck converter with an input “DC - 12V/8.3A” & an output “DC -

3.6V/1-28A”, voltage and current control units (LED’s light intensity regulator), thermally controlled silent Fan (LED’s

thermal management), and 100-watt LED. The model has been simulated and the results are recorded. The role behind the

simulation of this model is to develop a real physical 100-watt LED light source with optimum design and best control for

the German Ingenious Medical Company. Based on the simulation’s results, the second step will be the application of learned

experience to make real electronic boards to start the long process of manufacturing. Thus, this work stresses the importance

of computational model in the design and manufacturing process of safe and reliable medical devices.

Keywords— Endoscopy, Rigid endscope, Light source, MATLAB, Simulink, AC-DC converter, DC–DC converter,

LED driver, CBT-140 White LED, forward power converter, SMPS, IGBT, Mosfet, IEC, Raspberry PI 4.

Abstracts

22

MATLAB/SIMULINK Medical CO2 Insufflator Model with PID-

PQT & MPC-PQT Controllers

Kinana Rashwani


ing


versity


kinana-

[email protected]

Mohamad Wadaane


ing


sity


[email protected]

Hassan Wehbi

Research & Development,

INGENIOUS

Medical GmbH,

Germany

Hassan.wehbi@ingenious-

medical.de

Hussein Wehby



sity


[email protected]

Ahmad ElSayed


ing


versity


[email protected]

Mohamad HajjHassan

Department of Biomedical En-

gineering,

American International Univer-

sity,

Kuwait

[email protected]

Mariam Khayreldeen


ing


versity


[email protected]

Ahmed N. Al-naggar



sity

Sana’a, Yemen

ahmed.al-

[email protected]

Mohamad Abou Ali


ing


versity


Mo-

[email protected]

Abdulhalim Mohamad


ing


sity


[email protected]

Saeed Bamashmos


ing


versity

Sana’a, Yemen

saeed.bam-

[email protected]

Abdallah Kassem

ECCE Dept., Faculty of Engi-

neering,

Notre Dame University-Louaize,

Zouk Mosbeh, Lebanon

[email protected]

Mohamad I.C. HajjHassan


Lebanese International University


[email protected]

Abstract—Medical Carbon Dioxide (CO2) insufflator is used in a minimally invasive sur-

gery creating abdominal cavity to provide surgeons with a direct view of internal organs. In our

previous work, MATLAB/SIMULINK medical CO2 insufflator has been developed with only

abdominal cavity’s pressure via a Proportional Integral Derivative (PID) controller. This work

permits the simultaneous control of three parameters pressure, flow and temperature through a

PID controller. Then, a Model Predictive Controller (MPC) has been implemented to enhance

the precision, accuracy, and the response time of the system. The results are promising due to

the efficiency of MPC controller in multi-input/multi-output system over PID controller. In the

future work, high flow CO2 insufflator will be developed.

Keywords— Medical CO2 insufflator; computational modeling; MATLAB/SIMULINK-

Simscape; PID and MPC controllers

Abstracts

23

A Review on Applied Natural Language Processing to Electronic

Health Records

Anoual El Kah

Faculty of Sciences

Mohamed First University

Oujda, Morocco

[email protected]

Imad Zeroual

L-STI, T-IDMS, Faculty of Sciences

and Techniques

Errachidia Moulay Ismail University

Meknes, Morocco

[email protected]

Abstract— Over the last decades, the healthcare sector has witnessed massive growth

in the use of various information technologies such as Electronic Health Records(EHRs),

a digital version of a patient’s paper chart that electronically stores all information related

to patient care. After the emergence of the EHRs, a large amount of language data is being

produced. This data is a collection of documents or text files that include essential infor-

mation, but most of them are unstructured to be properly analyzed by computers. To han-

dle the human language complexity and make this data more machine-analyzable, re-

searchers often rely on using Natural Language Processing (NLP) techniques. This paper

presents a review that features the application of NLP and machine learning to EHRs and

present associated challenges. Besides, we outline various applications and initiatives in

the healthcare sector. Finally, we provide promising directions for future research.

Keywords—Artificial Intelligent, Natural Language Processing, Electronic Health

Records, Medical Informatics



Abstracts

24

Intelligent Computing and Communication Networks

Abstracts

25

Performance of Hard Handover in 5G Heterogeneous Networks

Jamil Sultan

Telecommunication Engineer-

ing Technology (TCET) De-

partment Sana’a community College

(SCC)

Sana’a, Yemen

[email protected]

Mubarak S. Mohsen

Computer Application and

Programming Technology De-

partment Sana’a community College

(SCC)

Sana’a, Yemen [email protected]

Nashwan S. G. Al-Thob-

hani

Computer Network Engineer-ing Technology (CNET) De-

partment

Sana’a community College (SCC) and

University of Modern Sciences

(UMS) Sana’a, Yemen

[email protected]

Waheb A. Jabbar

Faculty of Electrical & Electronic Engineering Technology

Universiti Malaysia Pahang, 26600 Pekan, Pahang, &

Centre for Software Development & Integrated Computing

Universiti Malaysia Pahang, 26300 Gambang, Pahang, Malaysia

[email protected]

Abstract—To satisfy the high data demands in future cellular networks, an ultra-densifi-

cation approach is introduced to shrink the coverage of base station (BS) and improve the

frequency reuse. In an ultra-densification approach, small cells such as relay node (RN),

micro, pico and femto base stations (BSs) are deployed to the network of macro cells in

the same geographic region, forming HetNet. HetNets introduce some notable challenges

like inter-cell-interference-coordination (ICIC), mobility management and backhaul pro-

visioning. In this paper, we investigate the performance of the hard handover (HHO) in

5G HetNets. The performance metrics are the total number of handovers and the outage

probability. Simulation results show that the average outage probability is decreased in

HetNet scenario compared the macro only scenario. However, this improvement comes

at the expense of increase number of handovers.

Keywords—-Hard Handover; 5G; Relay Node (RN); HetNets; Ultra Densification





Abstracts

26


Ali Nagi Nosary

Faculty of Engineering, Communica-

tions & Electronics

Sana’a University

Sana’a, Yemen

[email protected]

Ghada M. Al-Asadi

Faculty of Engineering, Communica-

tions & Electronics

Sana’a University

Sana’a, Yemen

[email protected]

Abstract—This paper conceptualizes the current information and communication tech-

nology (ICT) development progress in Yemen to provide an indication of the growing

digital divide between Yemen and the rest of the world. It presents a detailed analysis of

the indicators related to ICT status, which can give a clear indication of the width of the

digital divide. It also explores the main barriers of ICT development in Yemen including

political, economic and social difficulties in addition to the ongoing war impact on the

overall progress. Furthermore, we underlined Covid-19 role in spotlighting the essential-

ity of ICTs. The results of the study show clearly that there is a huge digital gap in Yemen

depriving its people of many new technologies advantages. To shrink this gap, we pro-

posed a number of practical solutions to overcome the ICT development main obstacles

in order to avoid any further decline and to enable Yemen to start moving forward towards

the emerging ICT trends and applications such as the Internet of things and artificial in-

telligence. Such progress in bridging the digital divide can improve all aspects of people’s

lives in Yemen and accelerate sustainable development at the national level.

Keywords—ICT development index, infrastructure, ICT availability, ICT affordabil-

ity, digital gap, war impact, Covid-19 impact, enabling ICT emerging trends



Abstracts

27

A Smart Access Control for Restricted Buildings Using Vehicle

Number Plates Recognition System

Sharmarke Ali Kahie

Faculty of Computer and


Jamhuriya University of

Science and Technology,

Mogadishu, Somali

[email protected]

Abdullahi Ahmed Nor





Mogadishu, Somali

[email protected]

Ahmed Hashi Hasan





Mogadishu, Somali

[email protected]

Asho Mohamed Abdi





Mogadishu, Somali

[email protected]

Liiban Mutafa Hassan





Mogadishu, Somali

[email protected]

Mohamed Ahmed Mo-

hamud





Mogadishu, Somali

[email protected]

Abstract— The increased security concerns in hotels, government facilities and busi-

ness buildings require identifying entering vehicles and controlling access to these facili-

ties. The platform is automated with license plate recognition based on images of vehicles.

However, in situations where standardized plates are not used, image-based recognition.

License plate, police and background deformation. Traditionally human beings do this

job, and gate keepers need to stay alert for long hours, check vehicles entering to the

facility and manually keep data about those cars. This tedious and inefficient process de-

mands excessive energy from security personnel and creates inconveniences and possibly

security loophole in these premises. To overcome these shortcomings, this work proposes

a prototype design for an automatic gate access controlling system which scans the vehicle

plate numbers using a camera and optical recognition algorithm and compares it with the

records stored in the database to decide whether to allow the car or not. The researchers

developed this prototype design using a raspberry connected to a pi camera and a servo

motor, Python was also used as a development tool. The system was successfully tested

and showed to be a viable solution to the problem defined.

Keywords – AVLPR, raspberry pi, Optical character recognition (OCR)







Abstracts

28

Performance Analysis of OFDMA, UFMC, and FBMC for Optical

Wireless Communication

Sondos Alshami

Telecommunication Engineering

Libanese International University

Sana’a Yemen

[email protected]

Abstract—Optical Wireless Communications have become an essential research topic

due to their potential spectrum efficiency. Nowadays, OWC evaluates many applications

such as internet of things (IoT), visible light communication (VLC), and light fidelity (Li-

Fi). OFDMA, FBMC, UFMC, recently used in 4G and 5G. This work is concentrated on

providing a detailed study for the new modulation schemes. This article compared be-

tween BER, PAPR, spectral Density, and spectral efficiency of FBMC, UFMC, and

OFDM modulation techniques to analyze the merits of them. The simulation results show

that OFDMA has a higher BER, lower PAPR, compared to FBMC while FBMC has

greater spectral efficiency and better performance of spectral density which makes it the

optimum modulation schema among the rest. Furthermore, UFMC produces better results

than OFDM and eliminates the complexity of FBMC.

Keywords— OFDMA, UFMC, FBMC, OWC, LiFi, VLC, BER, PAPR.


Abstracts

29

Improved Performance in Compact Antenna by Using E-slotted and

DGS for V and E band 5G Applications

Hamdi M. A. Saif

Dept. of Communication

& Computer Eng.

Faculty of engineering &

IT


Yemen

[email protected]

Akram H. M. Qahtan


& Computer Eng.


IT


Yemen

[email protected]

Ehab A. G. Abdo


& Computer Eng.


IT


Yemen

ehab1997alme-

[email protected]

Redhwan Q. Shaddad

Dept. of Communication & Computer Eng.

Faculty of engineering & IT

Taiz University, Taiz, Yemen

IEEE Member

[email protected]

Abstract— Recently, demand for fifth generation (5G) wireless communication is very

high due to its bandwidth-efficient and high data rate. Thus, a high-performance mi-

crostrip patch antenna (MPA) is required to be designed. In this paper, we propose a com-

pact E-shaped MPA for the V and E band and backhaul applications. The proposed an-

tenna has small size dimensions of 3 × 2.9 × 0.508 mm3 and a low-cost Rogers/ RT Duroid

is used as a substrate material with a loss tangent of 0.0012. E-shaped slots and Defected

ground structure (DGS) are implemented on patch and ground, respectively. Both tech-

niques are used to improve the performance of the proposed antenna in terms of bandwidth

and return loss. This achieves 14.56 GHz bandwidth from 63.05-77.61 GHz with a gain

of 7.11 dB and return loss of -45.71 dB at centered frequency equals 66.33 GHz. For

further enhancement, the insert feed technique is used. As a result, the proposed design

has a good performance in terms of antenna return loss, gain, bandwidth, characteristics

impedance, and high efficiency at the resonant frequency. Therefore, it can be a candidate

for V and E band and backhaul outdoor environments applications. Higher Frequency

Structural Simulator (HFSS) tool is used for simulation.

Keywords—microstrip antenna, backhaul, 5G application, Millimeter-wave, E-

shaped, DGS.






Abstracts

30

High Bandwidth Triple-Band Microstrip Patch Antenna for THz

Applications

Redhwan Q. Shaddad

Faculty of Engeneering & IT

Taiz University Taiz, Yemen

IEEE Member

[email protected]

Esmat A. M. Aqlan

Communication and Com-

puter Dep.



[email protected]

Ehab A. G. Abdo


puter Dep.



ehab1997alme-

[email protected]

Mohammed A. A. Almoga-

hed


puter Dep.



mohamedalmo-

[email protected]

Aseel M. M. Alglal


puter Dep.



[email protected]

Wahb A. A. Abdullah


puter Dep.



[email protected]

Abstract—To meet demands of the future realization, new progresses in communica-

tion systems require a low-cost, lightweight, low-profile, and high-performance antenna.

In this paper triple-band microstrip patch antennas (MPAs) is proposed and designed for

THz applications. The proposed antenna has the dimensions of 56.8× 66.8× 5μm3, uses

Quartz-glass as a substrate material with a loss tangent =0 and thickness of 5 μm. Partial

ground technique is implemented to improve the return loss and bandwidth of proposed

antenna. This obtains bandwidth of 140, 700 and 410 GHz with return loss of -19.3, -29.2

and - 22.5 dB at resonant frequencies 2.5 THz, 4 THz, and 5.4 THz respectively. The

proposed antenna has been fed by means of microstrip feed line having impedance of 50

Ω. The results of antenna designed are suitable for THz applications. Higher Frequency

Structural Simulator (HFSS v13) tool is used to simulate the proposed antenna.

Keywords—terahertz, MPA, triple-band









Abstracts

31

Trade- off Energy and Spectral Efficiency with Multi-Objective

Optimization Problem in 5G Massive MIMO System

Adeb Salh

Faculty of Electrical and Electronic Engineer-

ing Universiti Tun Hussein

Onn Malaysia Johor, Malaysia

[email protected]

Lukman Audah

Faculty of Electrical and Electronic Engineering

Universiti Tun Hussein Onn Malaysia Johor, Malaysia

[email protected]

Qazwan Abdullah

Faculty of Electrical and Electronic Engineering


[email protected]

Norsaliza Abdullah

Faculty of Electrical and Electronic


[email protected]

Nor Shahida Mohd Shah

Faculty of Applied Sci-ences and Technology,

Universiti Tun Hussein Onn Malaysia,

Pagoh, Muar, Johor, Ma-laysia.

[email protected]

Abdo saif

Department of Electrical Engineering

University of Malaya Kuala Lumpur, Malaysia

[email protected]

Abstract— In fifth-generation cellular networks (5G), a large multiple-input multiple-

output (MIMO) technique is critical for optimizing the trade-off between energy effi-

ciency (EE) and spectral efficiency (SE). The challenges for the next generation depend

on increasing the high data traffic in the wireless communication system for both EE and

SE. The trade-off between EE and SE in downlink massive MIMO systems has been in-

vestigated in this paper using the first derivative of transmit antennas and transmit power.

The EE-SE trade-off has been investigated using a multi-objective optimization problem

to reduce transmit power. The EE and SE based on constraint maximum transmits power

allocation and a number of antennas by computing the first derivative of transmit power

to maximize the trade-off EE – SE has been improved. The optimal trade-off between EE

and SE can be obtained based on the first derivative by selecting the optimal antennas

with a low cost of transmit power showing good simulation results. Therefore, based on

an optimal optimization problem is flexible to make trade-offs between EE-SE for distinct

preferences.

Keywords—Massive MIMO, energy efficiency, spectral efficiency, 5G.









Abstracts

32

Proposed Path Loss Model for Outdoor Environment in Tropical

Climate for the 28-GHz 5G System

Abdusalama Daho

Faculty of Electrical Engineering, and Wireless

Communication Center

UniversityTechnology Malaysia

81310 Johor Bahru, Malaysia, and Department

of electrical and electronic engineering

Faculty of Engineering, Sebha University, Libya

[email protected]

Yoshihide Yamada

Department of Electronic Systems Engi-

neering [ESE], MJIIT

University Technology Malaysia

54100 Kuala Lumpur

[email protected]

Ahmed Al-samman

Department of Manufacturing and Civil Engi-

neering, Norwegian University of Science and

Technology,

2815 Gjøvik, Norway

[email protected]

Tharek Abdrahman

Faculty of Electrical Engineering, and

Wireless Communication Center


81310 Johor Bahru, Malaysia

[email protected]

Marwan Hadri Azmi

Faculty of Electrical Engineering, and Wireless

Communication Center



[email protected]/[email protected]

Arsany Arsad

Faculty of Electrical Engineering, and

Wireless Communication Center

University Technology Malaysia


[email protected]

Abstract— This study summarizes the results of the measurement campaigns con-

ducted at 28 GHz in the outdoor environment for the 5G system. The study takes place in

University Technology Malaysia (UTM) in the tropical climate of Kuala Lumpur. The

path loss models are extensively investigated, including the line-of-sight (LOS) measure-

ment results for the co-polarization antenna. The co- polarization antenna makes use of

high directional horn antennas at the transmitter and receiver. The path loss models for

close-in free space and close-in break point for a unique environment have been analyzed

on the basis of the data measured. The results indicate that for the LOS scenario, the path

loss exponent varies depending on the antenna configuration. The study reveals that the

CIB path loss model is appropriate for LOS scenarios since it fits the data of a specific

environment.

Keywords: - Co-polarization antenna, close-in free space, closein break point, tropical

region, 28GHz, 5G





mailto:[email protected]/[email protected]


Abstracts

33

Channel Estimation for Intelligent Reflecting Surface in 6G

Wireless Network via Deep Learning Technique

Redhwan Q. Shaddad

Communication Engineering, Taiz Uni-

versity

Taiz,Yemen

[email protected]

Esam M. Saif


versity

Taiz, Yemen

[email protected]

Husam M. Saif


versity

Taiz, Yemen

[email protected]

Zaid Y. Mohammed


versity

Taiz, Yemen

[email protected]

Ahmed H. Farhan

Communication Engineering, Taiz

University

Taiz, Yemen

[email protected] om

Abstract— Channel estimation for the wireless link has several challenges the hardest

challenge is the randomness in the real channel. In the 6G wireless networks, the Intelli-

gent Reflecting Surface (IRS) mitigate the problems in massive multiple input multiple

output (mMIMO) in 5G like high cost, low coverage and high-power consumption. Com-

munication network with (mMIMO) and IRS must approach smart network to enhance

quality of service and reduce path loss. In this paper, simulation of the direct channel and

the cascade channel was implemented with multipath for different users as point to mul-

tipoint transmission to improve robustness of the estimation. Channel estimation for the

network makes base station (BS) and IRS work with each other adaptively by using deep

learning. The output performance of the estimation is checked by root mean square error

(RMSE), training loss, complexity and time delay for channel training. The validation

RMSE in the direct channels arrives to 0.375 while it arrives to 1.116 in the cascade chan-

nels. Normalize mean square error (NMSE) is studied with respect to signal to noise ratio

(SNR) to show the more stable channel with SNR.

Keywords— Intelligent Reflecting Surface, Deep Learning, Channel Estimation, 6G

Wireless Networks.





Abstracts

34

IoT Based Temperature Control System of Home by using an

Android Device

Musfiqur Rahman Foysal


Science and Engineering


versity Dhaka, Bangladesh

[email protected]

Refath Ara Hossain





[email protected]

Mohammad Monirul Islam





monirul@daffodilvar-

sity.edu.bd

Shayla Sharmin



Daffodil International Univer-

sity Dhaka, Bangladesh

[email protected]

Nazmun Nessa Moon





moon@daffodilvar-

sity.edu.bd

Abstract—This IoT-based architecture research project is created for people who are

familiar with emerging smart technologies. This project is primarily based on controlling

the voltage of AC-supported equipment and developing an automatic temperature venti-

lation system that can make a space fully temperate. Additionally, this will protect our

appliances from overheating. Using the widely used Node MCU microcontroller and IP

networking for remote access and control, this project aims to automate machines and

appliances. You can also use an Androidbased smartphone app to access these computers

while you are not at work. Many electrical and appliances, such as lamps, fans, and re-

frigerators, can be controlled by an Android smartphone, which can also help against

overheating. This technology is more valuable in today's world in business environments

where temperature control is a big concern. The proposed voltage control scheme has been

combined with products such as an AC lamp, an AC fan, and a DC cooling fan to demon-

strate its feasibility and effectiveness.

Keywords—IoT, Node MCU, Microcontroller, Blynk App, Voltage Control, Temper-

ature Sensor, LDR








Abstracts

35

Business Information Technology

Abstracts

36

Unmanned Aerial Vehicle (UAV) in Precision Agriculture: Business

Information Technology Towards Farming as a Service

Mohammed Yaqot


Decision Sciences,


Hamad Bin Khalifa University

Doha, Qatar Foundation, Qatar

[email protected]

Brenno C. Menezes


Decision Sciences,


Hamad Bin Khalifa University

Doha, Qatar Foundation, Qatar

[email protected]

Abstract—Humanity has facing emerging global issues as new virus diseases, extremes in

weather conditions, increasing climatic changes, depletion of the environment and natural re-

sources, sharply rising demand for food, to just name a few. Therefore, the agriculture industry

has been challenged in its processes and products, resulting in a surge of application of novel

technologies and practices to maintain itself sustainable. Despite that, this industry is still re-

sponsible for 37% of the worldwide workforce, consumes 34% of the global arable land, uti-

lizes 70% of the total water, and emits up to 30% of greenhouse gases (GHG). Progressively

widespread in the sector, smart farming is a high-tech, efficient, and sustainable approach

achieved by applying integrated technologies within the agriculture value chain processes. It

includes increasing feed and food production and decreasing of their waste, prediction of dis-

eases, better estimation of product yields ahead of time, determination of the best harvest time,

monitoring of plantsgrowth cycles, etc. The results are going to yield a sustainable use of soil

and water resources while maintaining the green landscape and biodiversity of nature. Emerg-

ing remote-sensing technologies and artificial intelligence applications have become essential

tools to address these challenges. Drones, also known as Unmanned aerial vehicles (UAVs) are

among the most promising industry 4.0 (I4) applications for the next generation of agriculture.

This paper is a forehead into applications of drones from the innovation economy's standpoint

as a viable tool and an effective manpower replacement in the agroindustry. In such a field,

artificial intelligence (AI) has the potential to be the engine for automation of processes to be

integrated into cyber-physical systems and enhanced modeling towards improved agriculture,

more efficiently than the previous stages of the applications of technologies in this sector. Ag-

ricultural communities and businesses must take a strategic approach for continuous improve-

ment production processes by implementing quicker, safer, and cheaper plans through data

analytics and farming as a service (FaaS).

Keywords—UAV, drones, information and communication technologies, innovation econ-

omy, data analytics

Abstracts

37

Poverty in the Gaza Strip: Empowering the Unskilled Workforce to

Utilize International Crowdsourcing Markets and Platforms

Mustafa Abudalu

Division of Engineering Man-agement and Decision Sci-

ences, College of Science and Engineering

Hamad Bin Khalifa Univer-sity

Doha, Qatar Foundation, Qa-tar

[email protected]

Brenno Menezes

Division of Engineering Man-agement and Decision Sci-

ences, College of Science and Engineering

Hamad Bin Khalifa Univer-sity

Doha, Qatar Foundation, Qa-tar

[email protected]

Luluwah Al-Fagih

Division of Sustainable De-velopment, College of Science

and Engineering, Hamad Bin Khalifa Univer-

sity Qatar Foundation, Education

City, Doha 34110, Qatar

[email protected]*

Mohammed Yaqot

Division of Engineering Man-agement and Decision Sciences,

College of Science and Engi-neering

Hamad Bin Khalifa University Doha, Qatar Foundation, Qatar

[email protected]

Abstract—Despite global advances in well-being, healthcare, and the economy, poverty remains widespread, with many people worldwide lacking opportunities to overcome it. Living in an envi-

ronment where basic human needs are not continuously met can prevent people from achieving the

work outcomes that would otherwise be possible without the poverty barrier. To overcome inequality and a lack of local jobs, technology can provide opportunities to sell services and products globally

via online markets, crowdsourcing platforms, and other business models. The skills needed to partic-

ipate in online markets vary from the basic to the highly specialized. Learning basic skills is a realistic possibility for many people; however, empowerment initiatives supported by governments and busi-

nesses are required to provide the necessary technology, infrastructure, and training to those living

in poverty, so that they can make their services, skills, and products available to global customers. The application of such initiatives will impact participants’ lives, reduce unemployment rates, and

alleviate poverty, in addition to offering benefits to stakeholders and other involved parties. This

paper highlights the need for investment in providing opportunities in the Gaza Strip to people whose choices have been limited by poverty, empowering them to overcome these barriers and to play in-

novative roles in shaping their local economies. A model is proposed for running social enterprises

with a focus on the micro-tasks offered by popular crowdsourcing platforms, and utilizing market demand to train and empower motivated individuals to gain a source of income and to exploit the

potential opportunities.

Index Terms—Poverty, crowdsourcing, Gaza Strip, freelancing, community empowerment.

mailto:[email protected]*

Abstracts

38

The Digital Economy of Crowdsourcing: Crowd Shipping Model as

E-Business

Sarah Hassaan

Division of Engineering

Management and Deci-

sion Sciences, College of


Hamad Bin Khalifa Uni-

versity

Doha, Qatar Foundation,

Qatar

[email protected]

Mohammed Yaqot






versity


Qatar

[email protected]

Brenno C. Menezes






versity


Qatar

[email protected]

Abstract— Today’s business worldwide is navigating in the digital economy that utilizes

services of the crowds for the completion of tasks. Traditional models dependent on in-

ternal human resources (in-source) are now being outsourced to the public, expanding

faster into new market sectors. With evolving information and communication technolo-

gies (ICT) and the internet of things (IoT), novel and customized business models

emerged, moving toward decentralized network systems where individuals (peer-to-peer)

may participate in the so-called crowdsourcing. This paper focuses particularly on the

delivery of products in crowd shipping, creating a delivery service through crowd usage.

A generic business model for applications in crowd shipping is addressed, whereby we

proposed a crowd shipping delivery model, that utilizes commercial airplanes for low

weight packages (below 1 Kg). The responsiveness is advantageous for the continuous

flight schedules, while the lightweight involves more travelers for facilitating the delivery

of products. It has been shown how large this brand-new transportation mode (based on

the crowd) will grow if the appropriate infrastructure is implemented to evolve with the

digital economy.

Keywords— Crowdsourcing, crowd shipping, digital economy, matching, platform,

peer-to-peer.

Abstracts

39

Image Processing and Computer Vision

Abstracts

40

Parasitized Cell Recognition Using AlexNet Pretrained Model


Software Engineering Department

Taiz University

Taiz, Yemen

[email protected]

Mogeeb A. A. Mosleh


Taiz University

Taiz, Yemen

[email protected]

Ziad Almohagry

Information Technology Department

Taiz University

Taiz, Yemen

[email protected]

Ahmed Y. A. Saeed


Taiz University

Taiz, Yemen

[email protected]

Abstract— Malaria is globally known as one of the most prevalent diseases that kill thou-

sands of people every year. Plasmodium parasites are the product of malaria disease that

infects the red blood cells of humans. These parasites are transmitted by a female mos-

quito class that is known as anopheles. The diagnostic process of malaria involves isola-

tion and manual counts in microscopic bloodstreams of parasitized cells by medical prac-

titioners. In large-scale screening, Malaria diagnostic accuracy is largely affected because

of resource unavailability. In this paper, we proposed an intelligent diagnosis system using

advanced techniques based on a deep learning algorithm precisely AlexNet pre-trained

model. As the bright side of machine learning techniques, CNN has greatly led to numer-

ous image recognition activities. This method shows encouraging results. In terms of ac-

curacy, the proposed model achieved 97.33% in the validation phase. Therefore, in some

places where there are no medical services, this approach can be widely used for diagnos-

ing parasitized cells.

Keywords— Malaria, Parasites, AlexNet, Microscopist, Deep Learning, Pre-trained

Model.

Abstracts

41

Skin Lesions Recognition System Using Various Pre-trained Models

Amer Sallam

Computer Network & Dis-

tributed

Systems Dept.

Taiz University

Taiz, Yemen

[email protected]


Software Engineering

Dept.

Taiz University

Taiz, Yemen

baalawi.abdulfat-

[email protected]

Ahmed Y. A. Saeed


Dept.

Taiz University

Taiz, Yemen

[email protected]

Abstract— globally, skin lesion is known as one of the deadliest diseases among humans.

Such that skin cancer, which is recognized as dangerous cancer, causes death in many

cases. Therefore, many scholars have investigated in this area to design automated skin

lesion recognition systems. The variability of the skin diseases' appearance makes the di-

agnostic task very difficult. This paper presents an image-based diagnosis system using

convolutional neural networks (CNNs) to exploit an automatic recognition model for three

common skin lesions (Melanoma, Nevus, Benign Keratosis Lesion BKL) using dermo-

scopic images. In this study, eight pre-trained models have been implemented ResNet18,

ResNet-50, ResNet101, VGG11, DenseNet121, InceptionResNetV2, AlexNet, and Goog-

LeNet. Different classifiers are used including neural networks and a multilevel fine-tun-

ing method. The experiments were carried out based on a new version of the ISIC dataset.

In terms of accuracy, the best results among the implemented models were achieved by

Inception_ResNet-V2, which reached 0.875 and 0.87 in the training phase and testing

phase respectively.

Keywords— Skin Lesions, DenseNet121, GoogLeNet, CNNs, Dermatologists.

Abstracts

42

Yemeni Banknote Recognition Model based on Convolution Neural

Networks

Ahmed Y. A. Saeed


Dept.

Taiz University

Taiz, Yemen

[email protected]



Dept.

Taiz University

Taiz, Yemen

baalawi.abdulfat-

[email protected]

Ahmed N. Hassan


Dept., Taiz University

Taiz, Yemen

ahmed.alhas-

[email protected]

Abstract— Differentiating between paper currencies with different designs is a challeng-

ing task for visually impaired individuals and automated banking machines. Safe and ac-

curate paper currency recognition systems are highly required, because of the wide use of

Automated Teller Machines (ATMs), foreign exchange, automatic selling of goods, and

automated banking services. With the advances of pattern recognition techniques, many

real-life problems have been resolved. This paper presents a robust method to recognize

various Yemeni paper currency using pre-trained models. To perform effective recogni-

tion processes, deep learning approach is used. Three pre-trained models are implemented

which are AlexNet, DenseNet121, and ResNet50. The obtained results of the proposed

method achieved high validation accuracy. This robust model reaches a value of 96.99%,

96.83%, and 99.04% in terms of validation accuracy using ResNet-50, DenseNet121, and

AlexNet respectively.

Keywords—paper currency, banknote recognition, currency identification, deep learn-

ing.

Abstracts

43

Smart Attendance System Based on Face Recognition Techniques

Amr Al-sabaeei

Mechatronics and Robotics

Engineering Dept.

Taiz University

Taiz, Yemen

[email protected]

Hesham Al-khateeb


Engineering Dept.

Taiz University

Taiz, Yemen

heshamalkht-

[email protected]

Amer Al-basser


Engineering Dept.

Taiz University

Taiz, Yemen

[email protected]

Habeb Al-Sameai


Engineering Dept.

Taiz University

Taiz, Yemen

habeebabdu.alkha-

liq1230@gma

il.com

Mohammed Alshameri


Mechatronics

UTM University

Johor,Malaysia

[email protected]

Mohammed Derhem

Information and Technology

Engineering Dept.

University of Scince And

Technology

Taiz, Yemen

mohammedad-

ham736666666@

gmail.com

Abstract- Most academic facilities and institutions still use the traditional methods of em-

ployee attendance recording. This is currently done manually which may be a burden on

employees and takes a long time to do. Manipulation may also occur with the manual

process; thus, it loses its credibility. But now, with the advent of many deep learning al-

gorithms, we propose in this paper the use of an automated system to implement and man-

age the attendance recording process automatically by a face recognition technique using

convolutional neural networks. Our structure is based on a modern high-precision face

detection algorithm using the YOLO v4 (You Only Look Once). The Yolo v4 superior

using a single GPU achieving a high speed in detecting objects comparing with other

models that require to use many GPUs. Using the Darknet-53 layers for face detection we

get an accuracy of 100%. The system was designed using PyQt5; an easy-use and high

accuracy system which also displays attendance information in the main interface and

stores it automatically in an excel file so that it can be reviewed periodically.

Keywords: Convolution neural network (CNN), YOLO V4 (You only look once), Dark-

net-53, Face recognition, Attendance management, PyQt5.

Abstracts

44

Special Topics in Smart Technologies

Abstracts

45

A Framework for Designing Students Peer Learning Self-Regula-

tion Strategy System for Blended Courses

Rasheed Abubakar Rasheed

Department of Comuter Sys-

tem

and Technology

University of Malaya,

Kuala Lumpur, Malaysia

[email protected]

Nor Aniza Abdullah


System

and Technology



[email protected]

Amirrudin Kamsin


System

and Technology



[email protected]

Mustapha Abubakar Ahmed


Technology,

Bayero University Kano,

Kano, Nigeria

[email protected]

Adamu Sani Yahaya


Technology,


Kano, Nigeria

[email protected]

Kabir Umar

Department of Software

Engineering


Kano, Nigeria

[email protected]

Abstract— Blended learning has been considered the most effective and the most widely

adopted form of instruction currently in practice in most part of the world. The leading

existing challenge in blended learning is students’ inability to properly self-regulate their

learning activities as self-regulation has proven to be an integral competence for success

in online learning environments. This study proposed a framework for designing students

peer learning self-regulation strategy system for scaffolding student’s online component

studying for blended courses which has been identified as the main obstacle that is halting

blended learning from reaching its climax in instructional excellence. The system was

designed based on group affinity and learning potential structures; designing system func-

tionalities to instigate group dynamics that influence small group learning, as well as in-

centivization in the form of codependency and peerempath for combating reluctance to

peer learning participation and social loafing. Experimental results show that students

have achieved significantly higher academic scores and learning outcomes with the use

of the proposed system.

Keywords—Online learning, blended learning, peer learning, self-regulation, group

dynamics

Abstracts

46

Design A Compact Artificial Magnetic Conductor (AMC) For SAR

Reduction in WBAN Applications

Abdul Rashid.O. Mumin

Faculty of Engineering

Zamzam University of Sci-

ence and

Technology,

Mogadishu, Somali

1abdulra-

[email protected]

Qazwan Abdullah

Faculty of Electrical and Elec-

tronic

Engineering

Universiti Tun Hussein Onn

Malaysia

Johor, Malaysia

[email protected]

Abbas Uğurenver

Faculty of Electrical Engi-

neering

İstanbul Aydin University,

Istanbul, Turkey

abbasugurenver@ay-

din.edu.tr

Y.A.Mahmud

Telecommunication Engi-

neering

SIMAD University, Moga-

dishu, Somalia

yuusufmacani @gmail.com

Anisa.A. Hussein,

Telecommunication Engineer-

ing SIMAD

University, Mogadishu, Soma-

lia

[email protected]

A.I.Salah

Telecommunication Engi-

neering SIMAD

University, Mogadishu, So-

malia

aabdiriza-

[email protected]

A.Y.Ahmed

Telecommunication Engineering

SIMAD University, Mogadishu,

Somalia

[email protected]

Abstract— This article tests Specific Absorption Rate (SAR) reduction in WBAN square

patch antennas using various types of AMC structures. The AMC structure is designed.

The AMC structure can reduce surface waves and prevent unwanted radiation from the

ground surface. Thus, the AMC structure designed for WBANs allows you to adhere to

exposure guidelines. Simulations and measurements show a reduction in radiation pat-

terns and SAR values towards the human head. In addition, AMC increased the FBR by

15.3 dB, gained 7.61 dBi and radiation efficiency exceeded 88%. AMC achieved a 93.7%

reduction from the initial SAR value, while metal reflectors achieved a 77.7% reduction.

Then, the antenna is fabricated and measured to validate the concept.

Keywords – SAR, Square ring patch, body, WBAN.

Abstracts

47

Energy-Efficient Tethered UAV Deployment in B5G for Smart En-

vironments and Disaster Recovery

Abdu Saif

Department of Electrical

Engineering

University of Malaya


saif.ab-

[email protected]

Kaharudin Dimyati

Department of Electrical

Engineering



[email protected]

Kamarul Ariffin Noordin

Department of Electrical En-

gineering



[email protected]

Nor Shahida Mohd Shah

Faculty of Engineering

Technology

Universiti Tun Hussein

Onn Malaysia

Johor, Malaysia

[email protected]

S. H. Alsamhi

Software Research Insti-

tuteAthlone

Institute of Technology

Athlone, Ireland & IBB

University, Ibb,

Yemen

[email protected]

Qazwan Abdullah

Faculty of Electrical and

Electronic

Engineering, Universiti Tun

Hussein

Onn Malaysia, 86400 Parit

Raja, Batu

Pahat, Johor, Malaysia

[email protected]

Abstract— Due to Unmanned aerial vehicles (UAVs) limitations in processing power and

battery lifetime. The tethered UAV (TUAV) offers an attractive approach to answer these

shortcomings. Since a tethered connected to UAV is one potential energy solution to pro-

vide a stable power supply that connects to the ground would achieve impressive perfor-

mances in smart environments and disaster recovery. The proposed solution is intended

to provide stable energy and increase the coverage area of TUAV for smart environments

and disaster recovery. This paper proposed that the tethered connected to UAV will pro-

vide the continuous supply and exchange the data with ground terminals. Besides the ad-

justable tether length, elevation angels act to increase the hovering region, leading to the

scalability of coverage in many applications. Moreover, the power consumption and trans-

mission distance while achieving a trade-off between the hovering and coverage proba-

bilities. The simulation results demonstrate efficient performance in terms of line-of-sight

probability, path loss, and coverage probability for scalability coverage smart environ-

ments and disaster recovery scenarios. Furthermore, maximum coverage probability is

achieved versus increased tethered length because of the gain and fly over a region of

maximum tethered.

Keywords— Unmanned aerial vehicles, tethered UAV, smart environments, disaster,

B5G, IoT

Abstracts

48

Trajectory Generation and Optimization Algorithm for Autono-

mous Aerial Robots

Yunes Sh. Alqudsi

Department of Aeronauti-

cal and Aerospace Engi-

neering

Cairo University

Giza, Egypt

[email protected]

Ayman H. Kassem



neering

Cairo University

Giza, Egypt

[email protected]

Gamal M. El-Bayoumi



neering

Cairo University

Giza, Egypt

[email protected]

Abstract—This paper presents a new trajectory generation and optimization algorithm

(TGOA) for an agile and aggressive flight of quadrotor UAVs. The optimizer considered

the constraints associated with robot dynamics, actuator inputs, and flying environment

to produce collision-free dynamically feasible trajectories. The algorithm is developed

based on time-parametrized polynomials trajectories consist of a predefined sequence of

waypoints indicating the robot’s desired state over time. This work is an extension of

existing studies that utilized the differential flatness property and polynomial-based tra-

jectories. Doing so will lead to eliminating the need for iterative searching and computa-

tionally intensive sampling in the high dimensional state space of the quadrotor system

dynamics. The main advantage of the proposed algorithm lies in its numerical stability for

a large number of waypoints and high-order polynomials. The TGOA addressed the ill-

conditioned problem of Quadratic Programming (QP) based methods, by reformulating

the trajectory generation and optimization problem into unconstrained quadratic program-

ming (UCP). To do so, the numerically stable null-space factorization method is used. The

Proposed TGOA produces minimum derivatives trajectories along with minimum way-

points’ arrival times. Several scenarios and comparisons have been conducted to reveal

the numerical stability and computational advantages of the proposed TGOA. They also

demonstrate the variety of aggressive trajectories that can be rapidly generated so that

utilizing the full maneuvering capabilities of quadrotor robots.

Keywords— UAV Trajectory Generation, Trajectory Optimization, Motion Path Plan-

ning, Flying Aerial Robot, Autonomous Motion Control, Quadrotor Trajectory Genera-

tion.




Abstracts

49

PCM Melting Process in a Quadruple Tube Heat Exchanger Using

Ansys Software

Al-Abidi, Abduljalil A

Department of HVAC Engineering

Sana’a Community College

P.O. Box 5695, Sana’a, Yemen

[email protected]

Abstract— Thermal energy storage (TES) effectively contributes in the energy efficiency

improving and the energy supply/demand discrepancy eliminating of solar thermal tech-

nology. Among the different types of TES, phase change materials (PCMs) exhibit a high

thermal energy density per unit mass. The present work numerically investigates the melt-

ing process of PCM (RT82) in a quadruple tube heat exchanger (QTHX). ANSYS (Fluent)

version 18.2 software program is used to develop a 2D numerical model for the melting

process of the QTHX, and pure conduction and natural convection are considered in the

simulation. Two models of QTHXs are studied with respect to the PCM position in the

tubes. In model (a), the PCM inserted in the first tube and the third tube while in model

(b), the PCM inserted in the second tube and the fourth tube. Moreover, the melting pro-

cess of the QTHX is compared with a triplex tube heat exchanger (TTHX) and double

pipe heat exchanger (DPHX). The computational results indicated that the melting rate of

model (b) was achieved in a 63.2% of that of model (a). In addition, the results indicated

that PCM was melted earlier in the QTHX compared to TTHX and DPHX. The numerical

model was validated with a previous experimental work. Numerical results show a con-

sistent agreement with the experimental results.

Keywords— Thermal energy storage, PCM, melting process, quadruple tube heat ex-

changer

Abstracts

50

Design of an EHG based Smart Labour Detection System

Nishanth VG.

Department of Electronics

and Communication Engi-

neering,

Amrita School of Engineer-

ing, Coimbatore,

Amrita Vishwa Vidyape-

etham, India.

[email protected]

Roshan E.



neering,


ing, Coimbatore,


etham, India.

[email protected]

Mohankumar N.*



neering,


ing, Coimbatore,


etham, India.

[email protected]

rita.edu

Abstract— The purpose of this paper is to develop a portable noninvasive system to meas-

ure the EHG recordings and to distinguish between true and false labour. This proposed

system would help the medical personnel to achieve a quicker and clearer diagnosis,

which will reduce medical complications. This will also help the patients monitor their

uterine contractions without any medical assistance and seek medical attention at the ap-

propriate time. The EHG signals represent uterine muscle contractions and can provide

useful information. These signals are recorded using electrodes and sampled using the

ADC unit in the microcontroller. The recorded signals are processed and analyzed using

the machine learning model on the microcontroller. The algorithm decomposes the signals

and extracts their corresponding features using a regression model. These features are then

used to train a classifier, which is used to distinguish between true labour and false labour.

The Icelandic 16-electrode Electrohysterogram Database was used as the dataset for train-

ing and testing the model. This algorithm managed to produce an accuracy of 97.78%, an

F1 score of 97.87% and a standard deviation of 3.5%.

Keywords—EHG, uterine EMG, machine learning, embedded system, bio-medical sys-

tems, PCA, WPD, empirical mode decomposition, SVM

The First International Conference on Emerging

Documents

Transcript of The First International Conference on Emerging