See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/361607151

Smart Attendance Management System

Article · June 2022

DOI: 10.22937/IJCSNS.2022.22.6.96

CITATIONS READS

8 13,645

8 authors, including:

Alaa Albahrani Atta Rahman

Imam Abdulrahman Bin Faisal University Imam Abdulrahman Bin Faisal University
1 PUBLICATION 8 CITATIONS 260 PUBLICATIONS 4,596 CITATIONS

SEE PROFILE SEE PROFILE

Gomathi Krishna
Imam Abdulrahman Bin Faisal University
19 PUBLICATIONS 335 CITATIONS

SEE PROFILE

All content following this page was uploaded by Atta Rahman on 29 June 2022.

The user has requested enhancement of the downloaded file.

762 IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022

Smart Attendance Management System

Alaa Albahrani1, Zainab Ali AL-Ali1, Zainab Yousef Al-Ali1, Aqeela Al-Mssri1, Mashael AL-Shalan1,
Atta-ur-Rahman1,* and Gomathi Krishnasamy2

1
Department of Computer Science (CS), College of Computer Science and Information Technology (CCSIT), Imam
Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia
2
Department of Computer Information System (CIS), College of Computer Science and Information Technology (CCSIT),
Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam, 31441, Saudi Arabia

Abstract wellbeing. Similarly, it can be utilized for smart

Keeping track of attendance while engaging students in the attendance by means of facial recognition, iris
classroom may be tough, especially when the class is big. The
conventional method of calling pupils' names is tedious and time-
detection and fingerprints etc. [2]. The development is
consuming, and proxy attendance is always a possibility. To constant, as during the new situation in the pandemic
address this problem and maintain track of students' attendance, some of the available techniques used in attendance
we presented a smart attendance management system (SAMS) process are prevented like fingerprint and signature in
using face recognition, fingerprints, and location. SAMS assists the paper (at campus), to save the spread the virus.
the instructor in two ways. First, it provides an automatic and
error-free rollcall. Second, it records the attendance of pupils over This opens the opportunity to find an alternative
time to share with the advising unit, and to generate a DN list of technique such as the face detection which is smart
students with short attendance before the exam for the academic enough to recognize the face with mask and other
affairs unit. SAMS notifies students when the rollcall window on ambient hazards and inbuilt in many smartphones
their smartphone is activated/opened, based on the precise
date/time slot for a class (under instructor ID, subject ID, and
operating systems like Apple iOS 12 and above. The
classroom location). It allows students to register for classes using authentication based on multiple conditions provides
their smartphone's face recognition and/or fingerprint sensor. As a high security for that reason used GPS technology
result, the student's rollcall is recorded in the system, along with (geo tags) with face detection, to track the movement
the classroom location identifier. The system uses deep learning and availability in the specific area. Furthermore,
(DL) approaches for biometrics, such as the histogram of oriented
gradient approach for facial and fingerprint recognition. The should manage the risk and prepare for it, be put into
proposed system can also be used for rollcall in online classrooms. consideration in case of loss of services, by providing
Keywords: alternative choices instead such as the fingerprint.
SAMS, smart rollcall, Location based services, DN list, face This paper is organized as follows. The next section
recognition, fingerprints. describes the related work. Section 3 discusses the
problem statement. In section 4, we discuss proposed
1. Introduction system architecture. Section 5 summarizes the
implementation and section 6, concludes the paper.
The modern educational environments require
building an integrated system for provisioning of 2. Related Work
educational resources in all forms, as well as pay
attention to the way to access them this is where smart This section covers the well-the results of
attendance comes in. The goal is not to force the known technologies and systems currently in
student to attend, but rather to ensure the presence of practice for smart attendance. Each technology
students and their acquisition of the rich knowledge mentioned here has its own pros and cons.
for his/her own good and to build the country. Proposed system tries to overcome the possible
The Saudi Vision 2030 recommend the development research and development gap.
of educational systems by applying new technologies A) Fingerprint-Based Attendance Management system
[1]. As artificial intelligence (AI) plays its role in
enhancing this part to perform the basic daily tasks Fingerprint has evolved into the most advanced and
automatically like health factors etc. and improve the widely utilized biometrics technique for automated
Manuscript received June 5, 2022
Manuscript revised June 20, 2022
https://doi.org/10.22937/IJCSNS.2022.22.6.96
IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022 763

personal identification. The popularity of fingerprint cryptographic keys, have a significant level of
verification can be attributed to fingerprints' unpredictability. There is a lot of variances between
uniqueness, stability, permanence, and ease of use [4]. biometric samples obtained at various times from the
This system proposes a new automatic attendance same individual. As a result, the match is always made
management system that incorporates fingerprint on a probabilistic basis. This contrasts with password
authentication into the attendance management and token-based methods, which need a precise match.
process for both employees and students. Enrolment False Acceptance Rate (FAR) and False Rejection
and authentication are the two procedures that make Rate (FRR) are two types of mistakes caused by
up this system. The user's biometrics are collected inexact matching [6].
during enrolment, and the minutiae data is extracted False Acceptance: An imposter may be mistaken
and saved in a database as a template for the topic, for a real user if his template is close enough to the
along with the user's ID. After feature extraction, the actual user's intra-user variation.
enrollment module's goal is to accept a user into a False Reject: Even a valid user may be denied during
database using his or her ID and fingerprints. These authentication if the biometric signal obtained is of
characteristics create a template for determining the poor quality. A 'false reject' is the term for this type of
user's identification and formulating the mistake. If you don't match against your own template,
authentication procedure. An administrator of the you've been rejected incorrectly.
attendance management system handles the
enrollment process. During authentication, the user's B) Barcode-based Attendance Management System
biometrics are collected once more, and the extracted
characteristics are compared to those previously Every employee must be given a badge/card with
stored in the database to see if they match. Following a barcode as part of the barcode attendance system.
a successful match, attendance is recorded using the The badge/card is exchanged on the time clock to
user's id that was used to match the templates. The check into or out of the firm, and the data is recorded
project used a fingerprint reader as an input to capture by the clock. Data is encoded in the magnetic stripe of
pictures and built a program with a fingerprint the employee card in the magnetic stripe attendance
recognition and identification system as well as a system. The information on the card's magnetic stripe
database to store user data. The fingerprint templates is captured by the time clock when the card is swiped
and other biodata of the users, as well as the through the employee time clock [7]. This method
attendance records kept by the users, are stored in the scans one card at a time and requires that the reader be
database. The attendance management system's design in touch with it. RFID is a technology that uses radio
is depicted in Figure 1. waves to send data from an electronic tag, also known
as an RFID tag or label, affixed to an object to a reader
for the purpose of identifying and tracking the thing.
Employee ID cards have an RFID tag inserted in them,
which is read by a reader. This RFID technology uses
a computer to connect to a database. When an
employee enters or departs, an RFID card is used, and
the data is recorded by the reader [8]. The RFID-based
attendance management system architecture is
depicted in Figure 2. Although the benefits of RFID
for tracking and controlling daily things are obvious,
wireless RFID sensors (both digital and analog) have
yet to become widely used in the home and personal
electronics sector. RFID sensing is now being held
Fig. 1. Architecture of the fingerprint-based attendance back by several major roadblocks. Collisions between
management system [5].
sensor responses, An RFID sensing application
consists of at least one reader and multiple RFID
In a realistic situation, one would like to evaluate
sensors, each of which has at least one sensor. When
the accuracy and speed of a fingerprint matcher.
interrogating these tags, the tag collision problem
Biometric templates, unlike passwords and
764 IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022

becomes the major emphasis. Because they share the not connected to the internet. The drawback is that the
same communication channel, their replies must be QR Codes generated are only for that single event. As
arbitrated to avoid collisions caused by simultaneous a result, students in a university context will be
responses. This issue is one of the leading causes of required to preserve and maintain upwards of 10 codes
energy waste, longer identification times, and lower every year for all their courses [14].
read rates [10].

Fig. 2. Architecture of the RFID-based attendance

management system [9].
Fig. 3. Architecture of the QR-based attendance
C) Quick Response (QR) based Attendance
management system [13].
Management System
D) NFC-based Attendance Management System
A Quick Response code (QR-code) is a code that
is arranged in black and white rows and columns and
Near Field Communication (NFC) is a
is designed to be read by a smart phone [11]. Using
technology that allows a device to detect information
Quick Response (QR) codes as student tags guarantees
and/or commands from a tag by bringing them near
a cost-effective advantage. QR codes are powerful in
together or even touching them. Each NFC tag
that they may contain almost any sort of data,
contains a one-of-a-kind ID that can't be replicated.
including numeric, alphabetic, special, and binary
These NFC tags are subsequently distributed to
information [12].
students in every college faculty and department.
Scanning is a rapid process as the system is
While students tap these tags on the lecturer's NFC
functioning. To produce an encrypted QR code with
equipped mobile phone [15], the lecturer's NFC
specified information, the system requires a simple
readers software reads individual tags, identifies, and
login process by the class instructor using its Server
verifies students from their respective NFC tags [16],
Module. This may be done before class at any time.
and sends attendance data to the lecturer's smart phone
The lecturer shows an encrypted QR code to the
[17]. By the end of the lecture, or by the end of the day,
students during or at the start of class. The students
depending on the instructor desire, the smart phone
can then use their smartphones to scan the displayed
uploads all the attendance data it has collected to the
QR code to record the attendance. The entire
main server [18]. A model NFC-based attendance
procedure should take no more than a minute for each
management system architecture is depicted in Figure
kid and the entire class to complete their attendance
4. That is comprised of card NFC based smartphone,
confirmation. The QR-based attendance management
backend server and reporting equipment.
system architecture is depicted in Figure 3. The QR
Because NFC technology often includes a suite
code is simple to create and is completely free. QR
of associated devices, equipment, and upgrade-
code generators are accessible for free online, and
dependent standards, it may be too costly for some
there is also software that allows you to download the
campuses. This technique is not entirely risk-free.
generators for free and use them even when you are
IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022 765

Hackers have devised creative methods of getting database for all students. The system will request
illegal access to personal data held on phones, and the student login with the id. At the time of taking
battle to protect that data is never-ending. attendance, the location of the student is determined,
will be checked If the student is inside the class
building, the system will record the student as present
in the class, and if it is not there, the student is
considered absent. Furthermore, the id and location
will be encrypted and sent to the server. The system
workflow is depicted in Figure 6. But it is not very
effective because, like the current days, some lecture
is performed online, and it is not possible to track
location when outside the class building because the
location of the student may be diverse as it is possible
for the student to complete the lecture outside the
home, such as the cafe or the library.

Fig. 4. Architecture of the NFC-based attendance

management system [9].

E) GPS-based Attendance Management System

Global Positioning System (GPS) is a satellite-based

navigation system that provides continuous positioning and
timing information [19]. Using GPS technology in the
attendance system is considered trusty. The based goal is to
Fig. 6. The workflow of GPS-based attendance
make sure the students are in the class. By applying real- management system [20].
time tracking and continuous monitoring, instead of taking
the attendance manually two times at the begging of the 3. Problem Statement
lecture and at the end, to ensure the student attends on the
full hour. So, it has a big role in reducing the time- It is commonly observed that students’ rollcall in
consuming and providing accurate time recording. the universities is a time-consuming process,
especially when the class size is large say twenty-five
and above on average. In semester system, the faculty
members are required to conduct roll call once or
twice in each lecture. If the total time consumed
during rollcall is accumulated, it becomes significant.
The situation demands a smart, efficient, and reliable
attendance system. As current practice, the instructors
either rollcall or pass a sheet to be signed by the
students. Both ways are time consuming as well as
vulnerable to manipulation, where students proxy the
Fig. 5. Architecture of the GPS-based attendance attendance. This issue even elevated in the partition
management system [20]. classrooms, where male faculty members are unable
to see the female students beyond the glass [3].
The GPS-based attendance management system Moreover, during the pandemic as the classes are
architecture is depicted in Figure 5. The system is an taken online and some issues were observed as another
application that is installed on student devices. The person attended instead of a student. In the proposed
application is connected to the server that holds the system, students will login by their face ID and/or
766 IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022

fingerprint (using their smartphones) and together the identity of the student by checking the fingerprint
with the date/time stamp and location ID of the or Real-time face verification, as it is one of the
classroom. Consequently, the app running on the recently used technologies based on deep learning by
students’ smartphone will upload the information to CNN model as it is used before in visual analyzing the
the server unit to confirm attendance. Smartphones image to find the pattern, by training the model to
may communicate with the server either through local detect the face and then preprocessing the image to
intranet coverage provided by the universities or extract features and the output will be number stored
through the internet. System will only assist in terms in an array. Real-time face verification is achieved
of smart attendance, but also help in calculating the with MobileFaceNets. in addition to checking the
aggregate attendance during or at the end of semester. location of the student to prove that the student is in
It will help the instructor in calculation the defaulters the classroom. all the techniques used will provide
(DN) students list, who would not be able to appear in high accuracy and security in attendance management
the exam due to short attendance policy of the rather than manually processing. The SAMS intends
university. to be a mechanism for documenting student
attendance using smartphones, which will save a lot of
A) Goal paperwork from the existing, manual attendance
system. The SAMS is a standalone mobile application
The main goal of SAMS is enabling university or that will be beneficial for instructors and students at
college students to use smart attendance. Its ability to universities to keep track of attendance using location,
individually identify each student based on their face ID, and/or fingerprints. This is the system's most
fingerprint or face ID and class location makes important feature. The system should generate a report
providing security access easier, faster, and more on attendance. There should primarily be interfaces
secure than in the past. that are linked to a single database. Figure 7 Show the
overall architecture of the system. In general, the
B) Scope/Limitation instructor is responsible to manage the attendance. As
for the student can check the attendance performance.
The suggested SAMS was created with
universities in mind. There was a range for students as
well as a range for instructors. The project's design and
platform are an iOS-based system and android-based
system that keeps track of students' attendance. In
addition, the system assists the instructor in
calculating the DN students list.
The proposed attendance system SAMS should
be able to enroll the student in the courses Fig. 7. Overall architecture of the system
automatically. But that shall be excluded from the
project due to restrictions, we postpone this feature
because it requires to connect with "PeopleSoft"
system to get access the information of students and
will be the instructor enrolled her students through
importing CSV file of enrolled students.
SAMS require the students must have a smartphone
device during the class having inbuilt camera and/or
fingerprint sensor. Failing to which, students won’t be
able to get the access.
Fig. 8. General view of the system
4. Proposed System Architecture The DFD context depicts the intended SAMS
implementation's capabilities and limits. The context
Building a mobile application to manage the DFD depicts the system's limits as well as its
attendance based on the biometrics in order to prove interactions with its surroundings. The DFD context is
IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022 767

to show the user's connection and how they exchange 5. Implementation

information within the system. This section contains a
flow diagram for additional functions in SAMS that The below figures are snapshots of some
are common to all users, instructors, and students, as interfaces from the proposed SAMS prototype built
well as how they interact with the system. Figure 8 for assessment.
depicts how data travels between the system and all Figure 11 shows the home screen for the student
users at DFD Level 0 for more typical functions. to select his/her class. Figure 12 shows the
Following provides a graphical representation of how classes/subject students enrolled in and upcoming
an instructor interacts with the system. classes time. Figure 13 provides the option to select
Figure 9 shows the Level-0 DFD of the instructor either biometric option that is facial recognition or
subsystem and describes how the data flow between fingerprint. Figure 14 and Figure 15 shows the
the system. interfaces for facial recognition system and fingerprint
scanning system, respectively.

Fig. 9. Instructor subsystem

Following provides a graphical representation of

how a student interacts with the system. Figure 10
shows the Level-0 DFD of the student subsystem and
describes how the data flow between the system.
Fig. 11. Home screen Fig. 12. Class schedule

Fig. 10. Student subsystem

Fig. 13. Biomertric select Fig. 14. Facial interface

768 IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022

Engineering, Faculty of the Graduate School of the State

University of New York at Buffalo.
[7] Ononiwu G. C and Okorafor G. N (2012): Radio Frequency
Identification (RFID) Based Attendance System With
Automatic Door Unit, Academic Research International. Vol
2, No 2, March, 2012.
[8] K. Domdouzis, B. Kumar, and C. Anumba, “RadioFrequency
Identification (RFID) applications: A brief introduction.”,
Advanced Engineering Informatics, Vol. 21, 2007, pp 350-
355.
[9] “Sensors-enabled smart attendance systems using NFC and
RFID technologies - Document - Gale Academic OneFile.”
https://go.gale.com/ps/i.do?id=GALE%7CA419413112&sid
=googleScholar&v=2.1&it=r&linkaccess=abs&issn=22209
085&p=AONE&sw=w&userGroupName=anon%7E41f134
46 (accessed Nov. 11, 2021).
Fig. 15. Fingerprint interface [10] Arjona, L.; Landaluce, H.; Perallos, A.; Parks, A. Survey and
analysis of RFID DFSA anti- collision protocols and their
6. Conclusion physical implementation capabilities. In NOVA Chapter:
RFID Technology: Design Principles, Applications and
Controversies; NOVA Science Pub.: Hauppauge, NY, USA,
Smart attendance management system is designed to
2018; ISBN 978-1-53613-250-2.
solve the issues of existing manual systems. We have used
[11] D.-H. Shin, J. Jung, B.-H. Chang, The psychology behind QR
face recognition and fingerprint concept to mark the codes: user experience perspective, Computers in Human
attendance of student and make the system better. The smart Behavior 28 (2012), 1417–1426.
Attendance System helps in increasing the accuracy and [12] I.C. Zupanovic and E. Tijan.: QR Codes as a time
speed ultimately to achieve the high-precision real-time management tool in m-learning. Proc. MIPRO 2012, Opatija,
attendance and its evaluation process. In future, we are Croatia, pp. 1470–1474 (2012).
intended to investigate more machine learning and deep [13] “MOBILE ATTENDANCE SYSTEM USING QR CODES
learning-based system in contrast to the cloud computing TECHNOLOGY | Semantic Scholar.”
for sake of smart attendance with added security solutions https://www.semanticscholar.org/paper/MOBILE-
[21-55]. ATTENDANCE-SYSTEM-USING-QR-CODES-
TECHNOLOGY-Talip-
Zulkifli/334b9d1554bb7ddd18aebf325a79dd806af03788
(accessed Nov. 11, 2021).
References [14] QR Bubble – attendance tracking. Web 15 May 2015.
[15] NFC connectivity information.
[1] Yusuf, N. (2017). Changes required in Saudi universities http://developer.android.com/guide/topics/connectivity/nfc/i
curriculum to meet the demands of 2030 vision. International ndex.html
Journal of Economics and Finance, 9(9), 111. [16] How to use NFC tag in android:-
https://doi.org/10.5539/ijef.v9n9p111. http://www.howtogeek.com/212117/how-to-use-
[2] M. Mahmud, A. Rahman, M. Dhafferi and A. Alqahtani, programmablenfc-tags-with-your-android-phone/
“Security Analysis of Liveness Authentication of Human Iris [17] Google. Near Field Communication | Android Developers
Templates: A Deep Learning Approach”, Journal of Medical [Online]. Available:
Imaging and Health Informatics, vol. 8, pp.1021-1025, 2018. http://developer.android.com/guide/topics/nfc/index.html
[3] M. A. Elhussein, D. Düştegör, N. Nagy and A. K. H. [18] Jay A. Kreibich, Using SQLite, O'Reilly Media, 2010.
Alghamdi, "The Impact of Digital Technology on Female
[19] El-Rabbany, A. (2001). Introduction to Gps: The global
Students’ Learning Experience in Partition-Rooms:
positioning system by Ahmed El-Rabbany. Artech House.
Conditioned by Social Context," in IEEE Transactions on
Education, vol. 61, no. 4, pp.
[20] M. S. Uddin, S. M. Allayear, N. C. Das, and F. A. Talukder,
“A Location Based Time and Attendance System,”
[4] Khan B., Khan M. K. and Alghathbar K. S. (2010):
International Journal of Computer Theory and Engineering,
Biometrics and identity management for homeland security
pp. 36–38, 2014, doi: 10.7763/ijcte. 2014.v6.832.
applications in Saudi Arabia. African Journal of Business
Management Vol. 4(15), pp. 3296-3306, 4 November, 2010.
[21] A. Rahman, S. Abbas, M. Gollapalli, R. Ahmed, S. Aftab et
[5] A. C.O, A. A.O, O. O.O, and I. E.O, “Fingerprint-Based al., “Rainfall Prediction System Using Machine Learning
Attendance Management System,” Journal of Computer Fusion for Smart Cities,” Sensors, vol. 22, no. 9, pp. 1-15,
Sciences and Applications, vol. 1, no. 5, pp. 100–105, Nov. 2022. https://doi.org/10.3390/s22093504.
2013, doi: 10.12691/jcsa-1-5-4. [22] T. M. Ghazal, H. Al Hamadi, M. U. Nasir, A. Rahman, M.
[6] Sharat S. Chikkerur (2005): Online Fingerprint Verification Gollapalli, M. Zubair, M. A. Khan, C.Y. Yeun, “Supervised
System, A MTech Thesis, Department of Electrical Machine Learning Empowered Multifactorial Genetic
IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022 769

Inheritance Disorder Prediction,” Computational Intelligence Human Comput (2020). https://doi.org/10.1007/s12652-020-

and Neuroscience, vol. 2022, Article ID 1051388, 10 pages, 02174-w.
2022. https://doi.org/10.1155/2022/1051388. [35] F. Alhaidari, A. Rahman, & R. Zagrouba, “Cloud of Things:
[23] F. Alhaidari, N. Shaib, M. Alsafi, H. Alharby, M. Alawami, architecture, applications and challenges.” J Ambient Intell
R. Aljindan, A. Rahman, R. Zagrouba, “ZeVigilante: Human Comput (2020). https://doi.org/10.1007/s12652-020-
Detecting Zero-Day Malware Using Machine Learning and 02448-3.
Sandboxing Analysis Techniques,” Computational [36] A. Rahman, S. Dash, & A.K. Luhach, “Dynamic MODCOD
Intelligence and Neuroscience, vol. 2022, Article ID 1615528, and power allocation in DVB-S2: a hybrid intelligent
15 pages, 2022. https://doi.org/10.1155/2022/1615528 approach.” Telecommun Syst, vol. 76, pp. 49–61, 2021.
[24] M. Jamal, N.A. Zafar, A. Rahman, D. Musleh, M. Gollapalli, https://doi.org/10.1007/s11235-020-00700-x.
S. Chabani, “Modeling and Verification of Aircraft Takeoff [37] M.T. Naseem, I.M. Qureshi, A. Rahman, M.Z. Muzaffar,
Through Novel Quantum Nets,” Computers, Materials and “Robust and fragile watermarking for medical images using
Continua, vol. 72, no. 2, pp. 3331-3348, 2022. redundant residue number system and chaos,” Neural
[25] N. M. Ibrahim, D. G. I. Gabr, A. Rahman, S. Dash, A. Nayyar, Network World, vol. 30, no. 3, pp. 177-192, 2020.
“A deep learning approach to intelligent fruit identification [38] M. Ahmad, M.A. Qadir, A. Rahman et al., “Enhanced query
and family classification,” Multimedia Tools and processing over semantic cache for cloud based relational
Applications, 2022. https://doi.org/10.1007/s11042-022- databases.” J Ambient Intell Human Comput (2020).
12942-9. https://doi.org/10.1007/s12652-020-01943-x.
[26] M Gollapalli, A. Rahman, D. Musleh, N. Ibrahim et al., “A [39] D.A. Almubayedh, G. Alazman, M. Alkhalis et.al.,
Neuro-Fuzzy Approach to Road Traffic Congestion “Quantum bit commitment on IBM QX.” Quantum Inf
Prediction,” Computers, Materials and Continua, vol. 72, no. Process vol. 19, no. 55 (2020).
3, pp. 295–310, 2022. https://doi.org/10.1007/s11128-019-2543-8.
[27] F. Al-Jawad, R. Alessa, S. Alhammad, B. Ali, M. Al-Qanbar, [40] A. Rehman, A. Athar, M.A. Khan, S. Abbas, A. Rahman, A.
A. Rahman, “Applications of 5G and 6G in Smart Health Saeed, “Modelling, Simulation, and Optimization of Diabetes
Services,” International Journal of Computer Science and Type II Prediction using Deep Extreme Learning Machine”,
Network Security, vol. 22, no. 3, pp. 173-182, 2022. Journal of Ambient Intelligence and Smart Environments, vol.
[28] N. AlDossary, S. AlQahtani, H. AlUbaidan, A. Rahman, “A 12, no. 2, pp. 125-138, 2020.
Survey on Resource Allocation Algorithms and Models in [41] M. Mahmud, A. Rahman, M. Lee, J. Choi, “Evolutionary-
Cloud Computing,” International Journal of Computer based image encryption using RNA codons truth table”,
Science and Network Security, vol. 20, no. 3, pp. 776-782, Optics & Laser Technology, vol. 121:1-8, 2020.
2022. [42] G. Zaman, H. Mahdin, K. Hussain, A. Rahman, N. Ibrahim,
[29] H. Wafa, A. Aldweesh, R. Alzaher, A. Rahman, “A Survey N.Z.M. Safar, “Digital Library of Online PDF Sources: An
on Scheduling Algorithms in Real-Time Systems,” ETL Approach,” IJCSNS, vol. 20 (11), pp. 172-181, 2020.
International Journal of Computer Science and Network [43] M.A. Khan, S. Abbas, A. Atta, A. Ditta, H. Alquhayz, M.F.
Security, vol. 22, no. 4, pp. 686-690, 2022. Khan, A. Rahman, R.A. Naqvi, “Intelligent cloud based heart
[30] H. Alghamdi, W. Dawwas, T.H. Almutairi, A. Rahman, " disease prediction system empowered with supervised
Extracting ToC and Metadata from PDF Books: A Rule- machine learning,” Computers, Materials & Continua, vol. 65,
Based Approach," ICIC Express Letters: Part B, vol. 13, no. no.1, pp. 139–151, 2020.
2, pp. 133-143, 2022. [44] A. Rahman, S. Dash, M. Ahmad, T. Iqbal, “Mobile Cloud
[31] A. Rahman, K. Sultan, I. Naseer, R. Majeed et.al., Computing: A Green Perspective,” Intelligent Systems,
“Supervised Machine Learning-based Prediction of COVID- Lecture Notes in Networks and Systems book series (LNNS,
19,” Computers, Materials & Continua, vol. 69, no.1, pp. 21- volume 185), pp. 523-533, 2021.
34, 2021. [45] A. Rahman, S. Dash, A.K. Luhach, N. Chilamkurti, S. Baek,
[32] S. M. Alotaibi, A. Rahman, M. I. Basheer and M. A. Khan, Y. Nam, “A Neuro-Fuzzy Approach for User Behavior
“Ensemble machine learning based identification of pediatric Classification and Prediction”, Journal of Cloud Computing,
epilepsy,” Computers, Materials & Continua, vol. 68, no.1, 8(17), 2019.
pp. 149–165, 2021. [46] A. Rahman, “Memetic Computing based Numerical Solution
[33] G. Zaman, H. Mahdin, K. Hussain, A. Rahman, J. Abawajy to Troesch Problem”, Journal of Intelligent and Fuzzy
and S. A. Mostafa, “An Ontological Framework for Systems, 37(1):1545-1554, 2019.
Information Extraction From Diverse Scientific Sources,” [47] A. Rahman, “Optimum Information Embedding in Digital
IEEE Access, vol. 9, pp. 42111-42124, 2021. Watermarking”, Journal of Intelligent and Fuzzy Systems,
[34] A. Rahman, “GRBF-NN based ambient aware realtime 37(1):553-564, 2019.
adaptive communication in DVB-S2.” J Ambient Intell
 770 IJCSNS International Journal of Computer Science and Network Security, VOL.22 No.6, June 2022

[48] A. Rahman, K. Sultan, N. Aldhafferi, A. Alqahtani, M.

Mahmud, “Reversible and Fragile Watermarking for Medical
Images”, Computational and Mathematical Methods in
Medicine, June 2018.
[49] A. Rahman, K. Sultan, Naheir Aldhafferi, A. Alqahtani, D.
Abdullah, M. Mahmud, “Robust and Fragile Watermarking
for Medical Images: A Joint Venture of Coding and Chaos
Theories”, Journal of Healthcare Engineering, June 2018.
[50] A. Rahman, S.A. Alrashed, A. Abraham, “User Behavior
Classification and Prediction using FRBS and Linear
Regression” Journal of Information Assurance and Security,
vol. 12, no. 3, pp. 86-93, 2017.
[51] A. Rahman, M. Ahmed, G. Zaman, T. Iqbal, M.A.A Khan et
al., “Geo-Spatial Disease Clustering for Public Health
Decision Making,” Informatica, vol. 46, no. 6, pp. 21-32,
2022.
[52] S. Arooj, A. Rahman, M. Zubair, M.F. Khan, K. Alissa, M.A.
Khan and A. Mosavi, “Breast Cancer Detection and
Classification Empowered with Transfer Learning.” Front.
Public Health 10:924432. doi: 10.3389/fpubh.2022.924432.
[53] M.B.S. Khan, A. Rahman, M.S. Nawaz, R. Ahmed, M.A.
Khan, A. Mosavi, “Intelligent breast cancer diagnostic
system empowered by deep extreme gradient descent
optimization,” Mathematical Biosciences and Engineering,
vol. 19, no. 8, pp. 7978-8002, 2022. doi:
10.3934/mbe.2022373.
[54] A. Rahman, A. Alqahtani, N. Aldhafferi, M.U. Nasir, M.F.
Khan, M.A. Khan, and A. Mosavi, “Histopathologic Oral
Cancer Prediction Using Oral Squamous Cell Carcinoma
Biopsy Empowered with Transfer Learning,” Sensors 22, no.
10: 3833, 2022. https://doi.org/10.3390/s22103833.
[55] M.U. Nasir, T.M. Ghazal, M.A. Khan, M. Zaheer, A. Rahman
et al., “Breast Cancer Prediction Empowered with Fine-
Tuning", Computational Intelligence and Neuroscience, vol.
2022, Article ID 5918686, 9 pages, 2022.
https://doi.org/10.1155/2022/5918686.

View publication stats