DEVELOPMENT OF RFID ATTENDANCE SYSTEM WITH PAYROLL

MANAGEMENT USING MACHINE LEARNING

An Undergraduate Thesis

Presented to

COLLEGE OF TECHNOLOGY AND ENGINEERING

CEBU TECHNOLOGICAL UNIVERSITY

San Francisco, Campus

San Francisco Cebu

In Partial Fulfillment

of the Requirements for the course

IM 328 -PRODUCT OUTPUT (Research)

Bachelor in Industrial Technology

major in Computer Technology

(BIndTECH-CT)

Honey D. Barrida
Cyrus F. Cartagena
Aseneth S. Del Corro
Angeles R. Estremos
Hiljun B. Florentino
John Niño O. Gonzales
Carl Niño B. Lilibios
Zyrill Jay C. Mollaneda
Teresa A. Nulla
Minio Franz M. Vosotros

MAY 2025
 i

APPROVAL SHEET

This thesis entitled Development of RFID Attendance System with

Payroll Management Using Machine Learning prepared and
submitted by Minio Franz M. Vosotros, Angeles R. Estremos, Zyril
Jay C. Mollaneda, Aseneth S. Del Corro, Hiljun B. Florentino, Carl
Niño B. Lilibios, John Niño O. Gonzales, Cyrus F. Cartagena, Teresa
A. Nulla, Honey D. Barrida in partial fulfillment of the requirements for
the course IM 328- PRODUCT OUTPUT (RESEARCH) has been examined
and is recommended for acceptance and approval for Final Defense.

THESIS ADVISORY COMMITTEE

MARIA CRISTINAL L. NUDALO-GONZAGA, Ph.D.TM

Chairman
KENT MERLOU C. MOLLANEDA JOVINCENT B. CABAHUG,
MSIT
Member Member

MARK JOHN P. LADO, MIT MARY JANE P. DAVASOL,

MSIT
Member Member

MARICAR H. NUDALO, MSIT CARMELITA JOY S. CUNATO,

LPT
Member Member

ENGR.GEMALIE LOR G. CARTAGENAS

Member
___________________________________________________________________________________

PANEL OF EXAMINERS
MARIA CRISTINAL L. NUDALO-GONZAGA, Ph.D.TM
Chairman
KENT MERLOU C. MOLLANEDA JOVINCENT B. CABAHUG,
MSIT
Member Member

MARK JOHN P. LADO, MIT MARY JANE P. DAVASOL,

MSIT
Member Member

MARICAR H. NUDALO, MSIT CARMELITA JOY S. CUNATO,

LPT
Member Member

ENGR.GEMALIE LOR G. CARTAGENAS

Member
 ii

ACCEPTED and APPROVED in partial fulfillment of the requirements for

Bachelor of Industrial Technology major in Computer Technology for the IM
328- PRODUCT OUTPUT course.

Date of Final Defense: May 11, 2025

ABSTRACT

DEVELOPMENT OF RFID ATTENDANCE SYSTEM WITH PAYROLL

MANAGEMENT USING MACHINE LEARNING

Minio Franz M. Vosotros [email protected] ,

Angeles R. Estremos [email protected] , Zyril Jay C.
Mollaneda [email protected] , Aseneth S. Del Corro
[email protected], Hiljun B. Florentino
[email protected], Carl Niño B. Lilibios
[email protected], John Niño O.
[email protected] , Cyrus F. Cartagena
[email protected] , Teresa A. Nulla
[email protected] , Honey D. Barrida
[email protected]
CEBU TECHNOLOGICAL UNIVERSITY –SAN FRANCISCO
CAMPUS

This research developed an integrated RFID-based attendance

system with payroll management capabilities enhanced by machine
learning algorithms. Through RFID scanning real-time employee
tracking is handled automatically by the system while preventing
human-based logging and reducing chances of mistakes. The
system utilizes logged work hours in its payroll calculation to
accelerate the pay processing. The system uses machine learning
algorithms to identify unusual attendance behavior including
multiple late arrivals and unauthorized absence patterns while also
improving administrative oversight and accountability. The web
application allows system operations by providing real-time
employee monitoring and comprehensive reporting abilities and
record maintenance for employees. The system evaluation tested at
Cebu Technological University – San Francisco Campus
demonstrated high user satisfaction scores of 4.24 on a standard
quality scale that ranked the results as “Very Good.” The system has
achieved positive outcomes but runs from a local server because of
limited resources which would prevent expansion when scaling up
its implementation. This system aligns seamlessly with
organizations that manage limited numbers of employees since it
provides them with cost-efficient and automated attendance and
payroll management. The system can benefit through updates that
will enable cloud connectivity along with better networking
 iii

capabilities and machine learning functions for predictive analytics

capabilities and enlargement of future deployments. The study
makes progress toward better smart administrative systems and
answers the increasing public sector need for digital transformation.

Keywords:

Applied Research, Attendance system, Agile, Daan Secante,

Raspberry Pi

ACKNOWLEDGEMENT

Thank you to our IM 312 instructor MJ Davasol and our AST

315 instructor Maricar Hall Nudalo for giving us motivation and

encouragement to continue our research. We are also very grateful

to our instructor Joceliston Nagsuban in IM 313 for providing

guidance on the safety protocols that must be followed in the

implementation of our research.

We also thank our Research Instructor, Mr. Jovincent Cabahug,

through him, we increased our knowledge in developing our

manuscript and how to plan and make a research paper. Thank you

very much, Sir, for your guidance and support.

We are also very grateful to our instructor in Microprocessor

who is the one we approached to get an idea about the components

we need and he also helped us in the programming process.

Because of him, we learned a lot that helped in the successful

development of our prototype. Thank you all so much!

 iv

DEDICATION

This project is dedicated to our instructors who never stop

guiding and inspiring us to improve our knowledge and abilities.

Your support and dedication gave us the strength to successfully

complete this research.

We also dedicate this to our family and friends who always

support us despite difficulties and shortages. Your faith and love

gave us courage and determination to achieve our goals.

We are also very grateful to our classmates who always

helped and united in contributing ideas and efforts. This is why it is

a symbol of unity, effort, and dedication for success. We will

dedicate all of this for everyone who has given us help and support

in our journey.

To ourselves, who are honest and continue to strive, this is a

symbol of our dedication and determination for success. This

research is dedicated to everyone who has given us help and

support in our journey.

 v

TABLE OF CONTENTS

APPROVAL SHEET...................................................................
ABSTRACT.............................................................................
ACKNOWLEDGEMENT............................................................
DEDICATION.........................................................................
TABLE OF CONTENTS..............................................................
LIST OF FIGURES.................................................................viii
LIST OF TABLES....................................................................
CHAPTER I.............................................................................
Introduction..................................................................1
Rationale of the Study..............................................................1
Background of the Study..........................................................2
Objectives of the Study.................................................3
General Objectives...................................................................3
Specific it aimed to;..................................................................3
Scope and Delimitation of the Study..............................4
Scope........................................................................................4
Delimitation..............................................................................4
RELATED LITERATURE AND PRIOR ARTS SEARCH..............
Related Literature.........................................................5
Prior Arts......................................................................6
Synthesis......................................................................8
RESEARCH METHODOLOGY................................................11
System Design............................................................11
Figure 1.Conceptual Framework.............................................11
System Architecture Diagram................................................12
Software Development Life Cycle Model.......................13
Application Architecture..............................................15
Front end................................................................................15
Use-Case Diagram.......................................................18
Software Requirements...............................................21
Functional Requirements........................................................21
Hardware Requirements.........................................................22
Networking Requirements......................................................22
Development Tools and Technologies...........................23
 vi

Evaluators..................................................................24
Environment...............................................................25
Instrument..................................................................27
Gathering the Data......................................................28
Treatment of Data.......................................................29
Scoring Procedure.......................................................30
Significance of the Study.............................................34
Definition and terms....................................................34
CHAPTER II..........................................................................36
System Testing and Evaluation....................................36
Usability..................................................................................36
Performance Evaluation.........................................................37
Determine the Quality of the System...........................39
Functionality...........................................................................39
Reliability................................................................................40
Determine the Usability of the System.........................42
Maintainability........................................................................42
Portability...............................................................................43
Compatibility..........................................................................44
Security..................................................................................46
Interpretation of Results.............................................47
System Testing and Evaluation....................................47
Determine the Quality of the System...........................47
Determine the Usability of the System.........................47
OVER ALL TOTAL.........................................................47
Chapter 3............................................................................49
Summary of Findings...................................................49
Conclusion..................................................................50
Recommendations.......................................................50
Recommendation for System Improvement...........................50
Recommendations for Future Research..................................51
Chapter 4............................................................................52
Rationale....................................................................52
Objectives...................................................................53
Expected Outcome......................................................53
Scheme of Implementation..........................................54
Scheme of Implementation..........................................55
 vii

TRAINING PLAN FOR THE USE OF ATTENDANCE SYSTEM 55

PROPOSED OUTPUT OF THE STUDY..............................59
BIBLIOGRAPHY....................................................................70
BIBLIOGRAPHY....................................................................71
Ahmed et al., (2020). Biometric fingerprint access control.....71
APPENDICES........................................................................72
Appendix A: Transmittal Letter....................................73
Appendix B: Advisee and Adviser Agreement Form.......75
Appendix C: Certificate of Presentation........................77
Appendix D: System Evaluation Instrument..................78
Appendix E: Screenshot and Photos.............................90
Appendix F: Pseudocode..............................................93
Appendix G: Similarity Index Certificate.....................102
CURICULUM VITAE..............................................................103
 viii

LIST OF FIGURES

Figure 1.Conceptual Framework...........................................11

Figure 2. System Architecture Diagram................................12

Figure 3. Agile Model...........................................................13

Figure 4. Front-End Architecture..........................................15

Figure 5. Back-end Architecture...........................................17

Figure 6. Use-Case Diagram.................................................19

Figure 7. Location Map of the Study.....................................25

 ix

LIST OF TABLES

Table 1. Functional Requirments..........................................21

Table 2. Non-Functional Requirements.................................21

Table 3. Hardware Requirements..........................................22

Table 4. Networking Requirements.......................................22

Table 5. Evaluator................................................................24

Table 6. System testing and Evaluation................................31

Table 7. The Quality of the System.......................................32

Table 8. The Usability of the System.....................................33

Table 9. Usability.................................................................36

Table 10. Performance Evaluation........................................38

Table 11. Functionality........................................................39

Table 12. Reliability.............................................................41

Table 13. Maintainability......................................................42

Table 14. Portability............................................................43

Table 15. Compatibility........................................................45

Table 16. Security................................................................46

 1

CHAPTER I

THE PROBLEM AND ITS SCOPE

Introduction

Rationale of the Study

The rapid advancement of technology today has led

organizations to adopt modern and efficient systems to facilitate

their operations. According to Smith and Brown (2020), automated

systems have significantly improved organizational efficiency by

reducing manual errors and enhancing data accuracy.

The proposed RFID with Payroll Management Using Machine

Learning aims to resolve challenges related to manual attendance

tracking, and payroll computation. Studies such as Johnson et al.,

(2019) emphasize the importance of integrating RFID technologies

to streamline operations and improve security.

Despite modern advancements, many organizations still face

issues such as poor data recording, inefficient payroll processes

according to (Doe et al., 2021). By integrating machine learning

algorithms, this system offers predictive insights and anomaly

detection capabilities, enhancing reliability and scalability

Background of the Study

Modern organizations increasingly rely on technology to

improve efficiency and security. Smith and Brown (2020)

 2

emphasized that RFID streamline attendance tracking and reduce

manual errors.

This study, conducted at the Barangay Hall in Daan Secante,

Tudela, Cebu, addresses inefficiencies in manual attendance and

payroll systems. Garcia (2019) noted that manual processes often

lead to errors and delays, highlighting the need for automation.

The proposed Development of RFID and Door Control System

with Payroll Management Using Machine Learning combines RFID

technologies to enhance security and simplify payroll computation.

According by Lee and Kim (2021) stated that machine learning

improves efficiency through predictive analytics and anomaly

detection.

By integrating modern tools, this system aims to deliver

accurate attendance logs, secure door access, and automated

payroll processing offering a smart and scalable solution for

barangay operations.

Objectives of the Study

General Objectives

This study aimed to developed an RFID attendance and payroll

management using machine learning. This aligns to 17 Sustainable

 3

Development Goals, in 8th goal which states “Decent Work and

Economic Growth”, and 9th goal “Industry, Innovation and

Infrastructure”

Specific it aimed to;

1. design a hardware and software-based attendance and

door control system using RFID,

2. develop a SQL lite database system for storing attendance

logs and payroll records,

3. create a machine learning named performance analytics

for automating payroll computation and detecting

anomalies, and

4. determine the functionality of the developed system using

ISO/IEC 25010 systems and Software Quality Requirements

and Evaluation (SQUARE)

Scope and Delimitation of the Study

Scope

This study focuses on the development and implementation of

an RFID based attendance system using the RC522 module,

integrated with a payroll management feature enhanced by

 4

machine learning algorithms. The system includes RFID scanning for

attendance tracking, and automatic salary computation based on

logged data. The project also involves the creation of a web-based

interface for real-time monitoring, administrative control, and

reporting functionalities. The system will be conducted in brgy. Hall

of Daan Secante, Tudela, Cebu with a small group of users to assess

its functionality, reliability, and usability.

Delimitation

This study is limited to the development and deployment of

the RC522 RFID Attendance System with Payroll Management within

a local environment. One major delimitation is that the system can

only be accessed via localhost and does not support online or

remote access. This constraint is primarily due to limitations in time

and financial resources, which restricted the implementation of web

hosting and cloud-based technologies. Additionally, the system was

only tested in a small-scale setting within a barangay office and was

not designed for large enterprise environments or institutions with a

high volume of use.

RELATED LITERATURE AND PRIOR ARTS SEARCH

Related Literature

The study by Garcia (2019) emphasized that RFID-based

systems improve security through access control integration,

preventing unauthorized entry and enhancing organizational

 5

efficiency. Similar study of but improved Smith and Brown (2020)

highlighted the use of RFID technology for automating attendance

tracking, reducing manual errors, and improving data accuracy and

security. Their study demonstrated that RFID systems provide quick

identification and seamless data logging, making them ideal for

schools and offices.

Tan and Cruz (2022) explored the use of machine learning

algorithms in payroll systems, highlighting their ability to automate

payroll computations, detect anomalies, and predict trends based on

attendance data. Their study found that integrating machine

learning improves efficiency, minimizes computation errors, and

provides decision-making insights, making payroll management

faster and more reliable.

Another study introduced by Nur et al. (2025) enhancing

payroll system developed using PHP, JavaScript, and MySQLi. The

system aimed to improve accuracy, efficiency, and flexibility in

salary computations, providing a user-friendly interface for

employers to manage payments, allowances, and deductions

effectively.

Kashif and Bibi (2023) introduced IoT-based attendance

systems that combined RFID technology with cloud-based data

storage. This integration enabled real-time synchronization and

accessibility, proving useful in large-scale deployments.

Hernandez et al., (2022) developed a framework for automatic

payroll calculation based on RFID attendance data. Their system

 6

processed attendance records to calculate regular hours, overtime,

late arrivals, and absences with 99.7% accuracy compared to

manual calculations. The automation reduced payroll processing

time by 87% in their case study of a manufacturing company with

500 employees. And the study of Johnson and Kim (2023) focused

on real-time payroll visualization integrated with RFID attendance.

Their system provided employees with immediate access to

accumulated work hours and estimated earnings through a mobile

application. User satisfaction surveys indicated a 62% improvement

in payroll transparency and a 47% reduction in payroll disputes.

Prior Arts

Wang et al. (2016) developed the first commercially deployed

system that incorporated machine learning algorithms for analyzing

RFID attendance data as part of an integrated payroll solution. Their

system utilized clustering algorithms to identify attendance patterns

and basic predictive models to forecast staffing needs, achieving

modest but significant improvements over non-ML systems.

Upgraded by AttendPro (2017) introduced a cloud-based platform

that combined RFID attendance tracking, automated payroll

processing, and machine learning analytics. This system

represented a milestone in the field by offering predictive absence

management and anomaly detection capabilities within a

commercially available integrated solution.

 7

RFID technology has been effectively utilized to automate

attendance recording processes. For instance, Mohammed Ansari,

Sana Pasha, and Arjun Shetty (2019) developed an RFID and

biometric-based attendance system enhanced with GSM features,

allowing for real-time updates and alerts. Similarly, Praveen

Konatham, Ravi Rao, and Santosh Kumar (2017) designed an RFID-

based system that automatically logged student attendance and

notified parents via SMS. These systems, while reliable, were

primarily limited to attendance tracking without integration into

broader administrative systems.

Zhang (2011) conducted pioneering research on applying

basic machine learning algorithms to attendance data for pattern

recognition. Using decision trees and simple clustering algorithms,

this work demonstrated the potential for identifying attendance

anomalies but was limited by the computational capacity and data

volumes available at the time. And Kumar and Rodriguez (2013)

expanded on Zhang's work by implementing more sophisticated

algorithms, including Support Vector Machines, to analyze

attendance patterns from card-based systems. Their research

achieved 73% accuracy in identifying potential time theft incidents

but required significant human verification of results.

Synthesis

The evolution of RFID-based attendance systems has

proceeded through several distinct phases, beginning with basic

 8

identification and tracking capabilities. Early systems, as developed

by Mohammed Ansari et al. (2019) and Praveen Konatham et al.

(2017), focused primarily on automating attendance recording and

providing notifications through SMS, but lacked integration with

broader administrative functions. Garcia's study (2019) advanced

this concept by emphasizing security applications through access

control integration, while Smith and Brown (2020) demonstrated

significant improvements in reducing manual errors and enhancing

data accuracy through automated attendance tracking.

The integration of attendance systems with payroll processing

marked a critical advancement in this technology. Hernandez et al.

(2022) achieved a significant breakthrough with their automatic

payroll calculation framework that processed attendance records

with 99.7% accuracy and reduced processing time by 87% in a

manufacturing setting with 500 employees. Johnson and Kim (2023)

further enhanced this integration by developing real-time payroll

visualization that provided employees with immediate access to

accumulated work hours and earnings estimates, resulting in a 62%

improvement in payroll transparency and 47% reduction in disputes.

Nur et al. (2025) continued this evolution with a

PHP/JavaScript/MySQLi-based payroll system focused on improving

accuracy, efficiency, and flexibility in salary computations.

The application of machine learning represents the cutting

edge of development in this field. Zhang's pioneering work (2011)

demonstrated the potential for using basic machine learning

 9

algorithms to identify attendance anomalies, though with limitations

due to computational capacity at that time. Kumar and Rodriguez

(2013) improved on this foundation by implementing Support Vector

Machines that achieved 73% accuracy in identifying potential time

theft. Wang et al. (2016) marked a milestone with the first

commercially deployed system incorporating machine learning for

analyzing RFID attendance data, while Tan and Cruz (2022)

specifically highlighted how machine learning algorithms can

automate payroll computations, detect anomalies, and predict

trends based on attendance data.

Cloud computing and IoT integration have further enhanced

the capabilities of these systems. AttendPro (2017) introduced a

cloud-based platform that combined RFID tracking, automated

payroll processing, and machine learning analytics, offering

predictive absence management and anomaly detection in a

commercial solution. Kashif and Bibi (2023) expanded on this

approach with IoT-based attendance systems that combined RFID

technology with cloud-based storage, enabling real-time

synchronization and accessibility for large-scale deployments.

This project has the opportunity to address several gaps in the

current research landscape. While existing systems have made

significant progress in automation and integration, there remains

room for developing more sophisticated real-time analytics

dashboards, enhancing machine learning model accuracy beyond

the current benchmarks, implementing a fully integrated approach

 10

that connects attendance and payroll with broader HR functions,

creating adaptive learning techniques that personalize the

experience, developing a more comprehensive security framework,

and designing a system with true mobile-first architecture and cross-

platform compatibility. By addressing these gaps, your project could

make a meaningful contribution to the evolution of RFID attendance

systems with payroll management.

 11

RESEARCH METHODOLOGY

System Design

The figure below shows the IPOO model, Input-Process-

Output-Outcome, is a framework used to analyze and understand

systems, and process.

Figure 1.Conceptual Framework

As showned in Figure the Attendance and payroll management

system that uses multiple technologies to streamline workforce

management. The system begins with inputs like RFID card

scanning for employee identification, payroll management

capabilities, machine learning analytics for performance tracking,

and administrative configuration options. These inputs feed into

processes that include data collection from RFID users, automatic

payroll calculations five hours after clock-out, machine learning

algorithms that analyze employee behavior patterns, and

adjustments for holidays, sick leave, and other time-related factors.

The central output is a comprehensive attendance system with

 12

integrated payroll management. The ultimate outcomes deliver

significant benefits simplified attendance tracking with reduced

manual effort, automatic computation and report generation,

predictive analytics for employee performance and behavior, and

enhanced capabilities for users that improve overall attendance

management.

System Architecture Diagram

This figure shows the system architecture, which includes four main

of the system raspberry pi 4 model B, RFID Module, mouse, monitor

and sd card

Figure 2. System Architecture Diagram

The image illustrates the hardware setup for the development

of an RC522 RFID attendance system integrated with payroll

 13

management. At the center of the configuration is a Raspberry Pi,

which acts as the main processing unit. Connected to the Raspberry

Pi is the RC522 RFID reader module, responsible for scanning RFID

cards or tags used by employees to log their attendance. An SD card

is inserted into the Raspberry Pi to store the operating system and

necessary software, including attendance logs and payroll data. A

monitor is connected via HDMI to provide a graphical user interface

for real-time monitoring and system management. Additionally, a

mouse is connected to allow user interaction and navigation within

the system interface. This setup forms the foundation of a cost-

effective, standalone attendance and payroll management system

that can be deployed in small to medium-sized organizations.

Software Development Life Cycle Model

The Agile SDLC (Software Development Life Cycle) is a

flexible, iterative approach to software development that

emphasizes collaboration, adaptability, and continuous feedback.

 14

Figure 3. Agile Model

In this Figure our design phase, we created architectural

blueprints using the IPOO model, developed hardware connectivity

diagrams, and designed front-end and back-end architectures. We

used HTML, CSS, and JavaScript for the front-end, while

implementing Python with Flask, SQLite, and machine learning

components for the back-end.

During development, we employed Python 3.x, Flask

Framework, database systems, RFID libraries, and machine learning

tools, building the system specifically for Barangay Daan Secante in

Tudela, Cebu. We integrated machine learning algorithms to analyze

attendance patterns and detect payroll anomalies.

For testing, we applied ISO/IEC 25010 standards to verify the

system's functionality. After successful testing, we will deploy the

system at Barangay Hall with a comprehensive training plan for

officials and workers, though with localhost-only limitations due to

resource constraints.

In our review phase, we will observ efficiency improvements

compared to traditional manual systems and recommended future

 15

enhancements including web hosting, mobile features, and cloud

integration. The iterative nature of Agile enabled continuous

refinement based on stakeholder feedback throughout our

development process.

Application Architecture

Front end

The frontend of the Attendance and Payroll Management

System serves as the vital interface between users and the system's

functionality, providing intuitive access points for both employees

and administrators.
 16

Figure 4. Front-End Architecture

This section is the frontend of the Attendance and Payroll

Management System features a comprehensive user interface

design that serves distinct user roles while maintaining a consistent

visual identity. Built with modern web technologies, it employs HTML

for structure, CSS for styling, and JavaScript for interactive

functionality. The Bootstrap framework provides responsive layouts

that adapt to various screen sizes from desktop monitors to mobile

devices.

For employees, the frontend offers a streamlined attendance

interface with prominent digital clock display, clear time-in/time-out

toggle buttons, and real-time status indicators. The authentication

process is simplified through RFID card scanning with immediate

visual feedback confirming successful operations.

Administrators access a more extensive interface with a

navigation sidebar providing access to several key sections: a

dashboard with statistical overviews and recent activity feeds, an

employee management module with directory views and credential

management, attendance record displays with filtering capabilities,

 17

payroll generation and reporting tools, and the performance

analytics section showing ML-powered insights.

The UI components include modal dialogs for confirmations,

toast notifications for system messages, data tables for information

display, and interactive charts for visualizing attendance patterns

and performance metrics. A kiosk mode is available for dedicated

attendance stations, providing fullscreen operation with larger touch

targets and simplified

Back end

The backend of the Attendance and Payroll Management

System represents the system's operational core, handling all data

processing, business logic, and hardware interactions invisible to the

end user. Built on Python with the Flask framework, this robust
 18

architecture manages authentication through RFID cards. .

Figure 5. Back-end Architecture

The backend of system attendance and Payroll Management

System is a comprehensive multi-layered architecture built on

Python using the Flask web framework. At its core, Flask handles

HTTP requests, routing, and template rendering to serve the web

interface. The business logic layer contains specialized modules like

attendance.py and payroll.py that implement critical functionality

for time tracking and compensation calculations. For data

persistence, the system uses SQLite with a custom data access

layer (database.py and models.py) providing abstractions for

database operations. A notable feature is the machine learning

component implemented through performance_analysis.py and

 19

performance_predictor.py, which uses scikit-learn models to analyze

employee performance metrics and predict future patterns.

The system interfaces directly with hardware through

dedicated modules for the RC522 RFID reader and R307 fingerprint

scanner, enabling the dual authentication feature. All these

components run on a Raspberry Pi 4, which provides the necessary

GPIO, SPI, and UART interfaces for connecting the hardware

peripherals. This architecture efficiently separates concerns while

maintaining cohesive integration between web serving, business

logic, data access, ML analytics, and hardware interfacing, creating

a complete solution for attendance tracking and payroll

management.

Use-Case Diagram

Presents the use-case diagram showing how the system

administrator can manage employee data, monitor attendance, and

manage payroll. Employees can log their attendance via RFID. The

system handles real-time attendance recording, payroll processing,

access control, and anomaly detection.

 20

Figure 6. Use-Case Diagram

The use case diagram provides a comprehensive visualization

of the system's functional boundaries and user interactions,

revealing important aspects of your Attendance and Payroll

Management System's architecture. For the Admin actor, the

diagram shows a hierarchical relationship structure where the Admin

Dashboard serves as a central hub connecting to five major

subsystems: Employee management, Attendance oversight, Payroll

processing, Machine Learning analytics, and Settings configuration.

Each of these branches further extends to specific use cases that

represent distinct administrative capabilities creating and editing

employee profiles, managing attendance records, generating payroll

reports, accessing performance insights, and configuring system

parameters. This structure emphasizes the system's role-based

permission model, where administrative users have privileged

access to data management and system configuration features.

 21

The Employee actor's interaction pattern reflects a deliberate

design choice to simplify the attendance recording process, focusing

solely on authentication via RFID scanning and time tracking

functionality. This streamlined approach removes potential barriers

to consistent attendance recording while ensuring accurate data

collection for administrative purposes. The relationship between the

RFID scanning action and both user types highlights the dual-

authentication approach of your system serving as a security

mechanism for administrative access and as a daily attendance

tracking tool for regular employees.

The diagram implicitly suggests the system's event flow,

where employee actions (scanning RFID cards, recording time)

generate data that administrators can then view, analyze, and use

for payroll processing and performance evaluation. This

interconnected workflow demonstrates how the system creates a

feedback loop between employee activities and administrative

oversight, supporting organizational efficiency and data-driven

decision-making. The machine learning component specifically

indicates the system's advanced analytical capabilities, moving

beyond basic attendance tracking toward predictive performance

analysis and employee insights.

 22

Software Requirements

Functional Requirements

Table 1. Functional Requirments

REQUIRMENTS DESCRIPTION

Attendance Tracking Capture and log attendance using

RFID cards

Payroll Management Compute salaries automatically

based on attendance logs.

Database Management Store and retrieve employee

information, attendance records,
and payroll data.

Machine Learning Analyze attendance patterns and

detect anomalies in payroll
Integration computations.

Web-Based Interface Provide login authentication for

secure system access.

Non-Functional Requirements

Table 2. Non-Functional Requirements

REQUIREMENTS DESCRIPTION

Performance Ensure the system can process

attendance logs and payroll
computations in real-time.

Reliability Maintain 99% uptime to ensure

system availability during
operations

Scalability Allow for future expansion to

accommodate more employees
and additional features.

Usability Provide a user-friendly interface

for easy navigation.

Maintainability Provide documentation for

future system enhancements.
 23

Hardware and Other Required Devices

Hardware Requirements

Table 3. Hardware Requirements

REQUIREMENTS DESCRIPTION

Main Controller Raspberry Pi 4 Model B (4GB

RAM or higher) Serves as the
central processing unit for the
system.
Input Devices RC522 RFID scanner

Output Devices LCD Display or Monitor

Storage Devices MicroSD Card (32GB or higher)

and External Usb for back up
data

Networking Requirements

Table 4. Networking Requirements

REQUIREMENTS DESCRIPTION

Internet Connection Wi-Fi Router or LAN

Connection – Provides network
connectivity for remote access
and database synchronization.

Protocols Supported HTTP/HTTPS For web-based

access to the system's
dashboard.
TCP/IP Protocol For data
communication and remote
monitoring.

Server Requirements Database Server (SQLite or

MySQL) Stores logs, user data,
and payroll information.
 24

Development Tools and Technologies

1. Python 3.x Selected for its simplicity, extensive libraries, and

compatibility with Raspberry Pi

2. Flask Framework – Used for building a lightweight and

responsive web application. It supports real-time interaction

between the system's front-end and back-end, enabling

smooth data flow and management of attendance records and

payroll data.

3. HTML, CSS, and JavaScript Utilized to create a responsive

and user-friendly web interface. These technologies ensure

that employees and administrators can easily access and

manage logs, payroll computations, and access control

through any web browser.

4. SQLite/MySQL Database Chosen for storing employee

information, attendance logs, and payroll details. These

databases provide reliability, scalability, and easy integration

with Python and Flask.

5. MFRC522 Libraries Used for interfacing with hardware

components such as the RC522 RFID module

6. Machine Learning Algorithms (Scikit-learn) – Integrated to

automate payroll computation, detect anomalies, and analyze

patterns in attendance data, enhancing security and decision-

making.
 25

Evaluators

The evaluators of the study are faculty members from

the College of Technology and Engineering. They were purposively

selected due to their limited number and their specialized

qualifications relevant to the objectives of the research.

Table 5. Evaluator

Group of Respondents Sample PERCENTAGE

(Faculty)

BIndTech-CT 4 66.67%
BSIE 2 33.33%
TOTAL 6 100%

The table shows the total number of evaluators from the

BindTech-CT and BSIE Faculty. The instructors from BindTech-CT

were purposively selected because of their extensive experience

and expertise in programming, systems development, and software

evaluation. On the other hand, the BSIE faculty members were

included due to their strong foundation in engineering principles,

practical applications, and their familiarity with technical project

assessments. Their combined knowledge and skills ensure a well-

rounded and comprehensive evaluation of the study's design,

functionality, and technical feasibility.

 26

Environment

Figure 7. Location Map of the Study

Camotes Islands are a group of islands located to the east of

Cebu province in the Philippines. These islands are part of Cebu and

are made up of four municipalities: San Francisco, Tudela, Poro, and

 27

Pilar. Among these, Pilar stands out as it is an island municipality

that is geographically separated from the main group of the

Camotes Islands, making it more isolated compared to the other

three.

Traveling to Camotes is relatively accessible by sea. One way

to reach the islands is by taking a ferry from Pier 88 in Liloan, Cebu,

to Poro Port in Camotes. The sea travel usually takes around 2 hours

and 30 minutes, depending on weather conditions. Another common

and convenient route is via Danao Port in northern Cebu. From

there, passengers can board a ferry operated by Jomalia Shipping,

which travels directly to Consuelo Port in San Francisco, Camotes.

This route also takes approximately 2 hours and 30 minutes.

Once on the island, traveling between towns is easy. For

instance, the distance from Consuelo Port to Tudela town proper is

about 11 kilometers, which can be traveled by motorcycle or tricycle

in around 30 to 1 hour. Meanwhile, the nearby town of Poro is only

about 4 kilometers away from Tudela, making travel between these

two towns quick and convenient.

As of the most recent population data, the municipality of

Tudela has a total population of 19,268 people based on the office of

the Comelec in tudela municipality hall. This growing number

reflects the development and activity in the area, despite its

relatively small land size. Within Tudela, one of the barangays is

Daan Secante, which is located around 3 kilometers from the town

 28

center. Daan Secante itself has a population of 2,159 residents,

making it one of the low populated barangays in the municipality.

The area is known for its peaceful rural atmosphere and its close-

knit community.

We haved specifically selected Barangay Daan Secante as the site

where we conducted our undergraduate research. The study will

take place at the Barangay Hall of Daan Secante, which provides a

central, accessible, and official location for our research.

Instrument

1. Functional Suitability: Measures how well the system’s

functionalities meet the specified requirements, such as

accurately logging attendance and controlling access.

2. Performance Efficiency: Evaluates how efficiently the

system uses resources and responds to user requests, such as

quick RFID scanning and processing of payroll data.

3. Compatibility: Assesses the system's ability to integrate with

other systems and hardware, such as different RFID readers or

payroll software.

4. Usability: Focuses on how easy and intuitive the system is for

users, including both administrators and employees.

5. Reliability: Measures the system’s ability to function

consistently without failure over time, ensuring data accuracy

and operational stability.

 29

6. Security: Evaluates the system's ability to protect sensitive

data, including user credentials and attendance logs, through

secure authentication and encryption.

7. Maintainability: Assesses the ease with which the system

can be updated, debugged, or extended, ensuring long-term

usability and adaptability.

Gathering the Data

Our research title was submitted to the committee and

received formal approval, marking the beginning of our project

development process. After careful consideration of the scope and

objectives, the committee endorsed our proposed study on an

"Development of RFID attendance system" recognizing its potential

contribution to workplace efficiency and security.

Following the approval, we diligently worked on developing

Chapter 1 of our research paper, which established the foundation

of our study. This chapter included comprehensive sections on the

background of the problem, statement of the problem, research

objectives, significance of the study, and scope and limitations. We

ensured that each section was meticulously crafted to provide a

clear roadmap for our research.

After submitting our initial chapter, we underwent a pre-oral

defense where we presented our research proposal to the panel.

Based on their valuable feedback and suggestions, we initiated a

systematic revision process to refine our research approach.

Simultaneously, we began the gradual development of the system,

 30

carefully implementing the core functionalities while ensuring

alignment with our research objectives.

As part of the project formalization process, we secured

necessary permissions by submitting a Letter of Intent to the

relevant authorities. Additionally, we established a formal adviser-

advisee relationship through proper documentation, ensuring that

our research received appropriate guidance throughout the

development process.

In the final stages of our preparation, we focused on the

embedded system components required for the project evaluation.

This involved configuring the RFID reader and fingerprint scanner

hardware, setting up the Raspberry Pi environment, and testing the

integration between these components. We meticulously prepared

all technical aspects to ensure a smooth evaluation process and

demonstrate the practical implementation of our research.

Treatment of Data

The following are the tools used in the treatment Data.

Simple Percentage

The simple percentage approach counts the number of

responses each category in the given rating scale (Very Good, Good,

Fair, Poor, Very Poor) receives so administrators can determine

proportional statistics. The approach requires dividing the responses

in a category by the total number of responses before multiplying

the value by 100 for calculation purposes. The percentages show

directly which number of respondents belong to each performance

 31

evaluation category. When analyzing 20 responses the simple

percentage shows that 10 participants selected "Good" making it

50% of the total responses. The method makes it convenient to see

data distribution patterns through visual representations within

rated categories.

Weighted mean

The mean was used to determine the average values of key

data points, such as the time taken for the RFID and Finger system

to log attendance or process payroll. This allowed for an overall

assessment of system performance. Standard deviation was used

to measure the variability or consistency in the system’s

performance. By calculating the standard deviation, we could assess

how much the results deviated from the average, such as the time

variations in RFID scans or processing payroll data.

Scoring Procedure

The scoring procedure converts numerical scores submitted

through the rating scale into descriptive categories together with

their verbal identifying labels. The four levels of assessment express

a rating distribution where 4.21–5.00 rates projects as Very Good

(VG) and 1.81–2.40 identifies them as Poor (P). The intermediate

ratings of Good (G) or Fair (F) fall between 3.22–4.20 or 2.41–3.21.

The evaluation process gathers each performance score separately

to create a whole assessment through averaging methods. The

score average determines the rating category through scale

 32

measurement while providing verbal descriptions which create a

qualitative performance summary from quantitative data.

Table 6. Categorical rating in terms of System testing and

Evaluation

Rating Range Categorial Verbal Description

Scale response
5 4.21-5.00 Very Good (VG) Excellent performance
with minimal to no
issues.

4 3.22-4.20 Good (G) Meets expectations with

minor improvements
needed.

3 2.41-3.21 Fair (F) Acceptable but requires

noticeable
improvements.

2 1.81-2.4 Poor (P) Adequate performance

but moderate issues
present.

1 1.00-1.80 Very Poor (PL) Below expectations with

several issues.

The document outlines specific performance evaluation

standards which will be used for testing purposes. A five-point rating

scale covers assessments from "Very Poor" (1.00–1.80) to "Very

Good" (4.21–5.00) while providing both response categories and

complete verbal explanations for each rating. The table enables

users to evaluate overall system functionality and determines the

 33

system's performance alignment with expectations or identification

of improvement needs and significant problems. The system

evaluation becomes simpler because this standardized process

enables clear identification of performance benefits and

weaknesses.

Table 7. Categorical Rating in terms of determining the

Quality of the System.

Rating Range Categorial Verbal Description

Scale response
5 4.21-5.00 Very Good (VG) The system fully meets
specified requirements,
produces accurate
results.

4 3.22-4.20 Good (G) Accurate and performs

securely, with minor
issues in compatibility or
completeness

3 2.41-3.21 Fair (F) Lack full accuracy,

completeness, or
seamless
interoperability

2 1.81-2.4 Poor (P) Functionality and shows

weak security or
integration

1 1.00-1.80 Very Poor (PL) The system fails to meet

essential requirements,
lack accuracy, and
shows serious weakness
in security
 34

The framework delivers a standardized method to assess

system quality through evaluation. The assessment follows the

structure of Table 6 by using an identical evaluation rating system

spanning from "Very Poor" to "Very Good." Evaluators can judge

system quality by following the descriptive statements that focus on

performance alongside usability and reliability aspects. Users can

identify objectively whether the system meets quality requirements

through table application.

Table 8. Catergorical Rating in terms of determining the

Usability of the System

Rating Range Categorial Verbal Description

Scale response
5 4.21-5.00 Very Good (VG) The system easy to
analyze, modify, install,
adapt, and test, showing
excellent
maintainability.

4 3.22-4.20 Good (G) Maintainable and

portable, with only
minor issues in
adaptability or
installation

3 2.41-3.21 Fair (F) Maintenance and

portability are
acceptable but require
improvement for better
system flexibility and
ease of use

2 1.81-2.4 Poor (P) The system present

challenge in testing
adapting, or updating,
indicating poor
maintainability or
portability

1 1.00-1.80 Very Poor (PL) The system is difficult to

 35

maintain or transfer,
with major usability and
adaptability limitations.

The measurements only assessed the usability aspects of the

system specifically. This measurement scale offers descriptive

categories that assess accessibility levels through a five-level rating

system. Users experience acceptable interface operation when

measurements confirm they receive necessary features while

reporting minimal encountered problems. The table offers an

organized system for usability evaluation and improvement using

both end-user feedback and operational experiences.

Significance of the Study

This study holds significant value for organizations,

particularly local government units (LGUs) , educational institutions,

businesses that rely on manual attendance and payroll systems. By

integrating RC522 RFID technology for attendance tracking. The

system provides a safer, more efficient, and organized approach to

administrative processes. The incorporation of machine learning for

anomaly detection and predictive analytics enhances the system’s

reliability and intelligence. These features minimize administrative

workload, eliminate human errors, and ensure accurate payroll

computations based on real-time data.

Moreover, employees and officials can benefit from the

system’s automated and transparent management of attendance

 36

and payroll, leading to reduced errors and improved efficiency. With

real-time monitoring and automated features, organizations can

make data-driven decisions more effectively, improving overall

operations. This integration promotes a safer, organized, and

productive environment, contributing to better resource

management and more informed decision-making, ultimately

benefiting society.

Definition and terms

RFID (Radio Frequency Identification) – A technology that uses

electromagnetic fields to automatically identify and track tags

attached to objects, commonly used for access control systems.

Machine Learning Algorithm – A computational method that

enables systems to learn patterns from data, make predictions, and

improve performance over time without explicit programming.

Anomaly Detection – A process used in data analysis and machine

learning to identify unusual patterns or deviations from expected

behavior, often used to flag errors or security threats.

Database Management System (DBMS) – A software

application used to create, manage, and store structured data,

ensuring data consistency, integrity, and security.

Flask Framework – A lightweight Python-based web framework

used for developing web applications, enabling communication

between the user interface and database.

 37

User Interface (UI) – The visual and interactive platform through

which users communicate with the system, including buttons, forms,

and displays.

Scalability – The ability of a system to handle increasing amounts

of data or users without compromising performance.

Algorithmic Efficiency – The measure of how effectively a

machine learning algorithm processes data to deliver results with

minimal computational resources.

CHAPTER II

PRESENTATION, ANALYSIS, AND INTERPRETATION OF DATA

This chapter presents, analyzes, and interprets the data that

was gathered by the researchers through tables to illustrate

alignment with the objectives of the study.

System Testing and Evaluation

Usability

Refers to how easily users can interact with the software

interface. A user-friendly design helps employees to easily access

the attendance system by scanning the RFID card and also generate

the payroll system.

Table 9. Usability

n=6
 38

Characteristic Description Mea

Learnability To what extent is the developed 4.33

system or device easy to learn and
understand?

Operability To what extent is the developed 4.33

system or device easy to use and
navigate?

Use error To what extent does the 4.33

protection developed system or device
protect users from making errors?

User interface To what extent is the developed 4.17

aesthetics system or device visually
appealing and easy on the eyes?
TOTAL MEAN 4.29

For the Attendance System with Payroll Management, the

mean overall score is acceptable 4.29 and is placed under a

“VeryGood” according to the scale used for the evaluation of the

usability. This result indicates the great success of the system based

on the user satisfaction and usability for a variety of aspects. Users

found the system easy to learn 4.33 Very Good, even if they did not

have technical expertise. This is especially critical in work settings,

where the users may be highly technology. Next we had

“Operability” 4.33Very Good, as they were able to comfortably

interact and navigate within the application anchoring on interface

consistency flow and a properly designed inputs.

While the system had a “User error protection” score of 4.33

Very Good, it gave user protections sufficient to prevent mistakes

while in use, which is essential for real-time monitoring

 39

responsibilities that involve the salary of an employee. In summary,

“User interface aesthetics” had been rated 4.17 Good, indicating

that the visual of the user interface can still be improved and the

actual design appeared to be visually and easy to use. The system's

ability to offer a readily accessible and convenient for controlling

attendance in employees use is further supported by its overall high

usability score.

Performance Evaluation

Refers to the software’s ability to respond quickly and

efficiently, especially during real-time data collection and

transmission. This includes system resource usage, and response

time in monitoring attendance and payroll.

Table 10. Performance Evaluation

n=6

Characteristic Description Mean

Resource To what extent does the 4.50

Utilization developed system or device
make efficient use of system
resources?

Time Behavior To what extent does the 4.33

developed system or device
provide fast response times?

Capacity To what extent does the 4.33

developed system or device
handle large amounts of data or
users?
TOTAL MEAN 4.39
 40

Overall scores for the Attendance System with Payroll

Management reached 4.39 indicating it belongs to the "Very Good"

classification of the assessment scale. The system demonstrates

effective performance in real-time environmental monitoring

applications because of its high ranking in resource management

domains and responsiveness categories. The system effectively

uses its software and hardware “Resource” according to the 4.50

score during monitoring durations to maintain performance stability

through various operation periods.

The system delivers exceptional data processing capability

together with rapid responsiveness based on the 4.33 ratings for

both “Time behavior” and “Capacity”. Employee time and

attendance reports through the fast time-in time-out system run

without delay due to its internet independence also performing

automatic salary deductions for late or absent events. The system's

dependable operational stability serves users requiring constant

monitoring by allowing it to maintain performance during consistent

use. Performance results verify that the software system meets the

requirements of high-demand real-world applications while ensuring

sustainable work ethic promotion.

Determine the Quality of the System

Functionality

Refers to the extent to which the software meets its specified

requirements and performs its intended functions. This

 41

characteristic assesses the ability of the software to provide the

features and capabilities that are necessary to achieve the intended

goals of the user.

Table 11. Functionality

n=6

Characteristic Description Mean

Completeness To what extent does the 4.17

developed system or device fulfill
all specified requirements?

Correctness To what extent does the 4.17

developed system or device
produce the correct results?

Interoperabilit To what extent does the 4.17

y developed system or device
interact effectively with other
systems and developed system or
devices?

Security To what extent does the 4.00

developed system or device
protect against unauthorized
access or malicious attacks?

Suitability To what extent does the 4.17

developed system or device meet
the needs of its intended users?
TOTAL MEAN 4.13

A functional evaluation of the system determined its ability to

meet specified requirements of the created Attendance System with

Payroll Management. The collected data points to “good”

functionality since participants scored a mean of 4.13 on the

functioning scale. Users declare the "Correctness" feature and its

4.17 mean score as the top among all system capabilities because it

offers precise and trusted monitoring data collection for attendance

 42

and payroll functions. The system proves its capability to merge

with different systems and external devices by earning a score of

4.17 at the second position in the assessment. Most necessary

elements found their place effectively in the system according to

the "Completeness" score average of 4.17. A large number of areas

showed system reliability but "Security" achieved the lowest

average of 4.00 which resulted in a "Good" classification. There is

room for enhancement in system security despite its ability to keep

unauthorized access at bay. The "suitability" evaluation score

amounted to 4.17 thus demonstrating that the system meets user

requirements. The system operates with dependable security

features to fulfill its purpose of monitoring employee applications

according to the collected data.

Reliability

Refers to the consistency and dependability of the software in

delivering accurate and uninterrupted monitoring of attendance and

payroll. This ensures users can trust the system to perform under

varying conditions.

Table 12. Reliability

n=6

Characteristic Description Mean

Availability To what extent is the developed 4.50

system or device operational and
accessible when needed?

Fault To what extent does the 4.17

Tolerance developed system or device
continue to operate correctly in
the presence of faults?
 43

Recoverabilit To what extent can the developed 4.50

y system or device recover from
failures?
TOTAL MEAN 4.39

The system dependability assessment reflects this system's

capability to deliver accurate and continual attendance and payroll

monitoring over time because this reliability enhances operational

performance assurance across various environments. An

assessment of 4.39 indicates that the system's reliability exists

within the favorable "Good" range leading to its dependability and

time-based performance stability. Evaluation data showed that both

"Availability" and “Recoverability” obtained the peak rating of any

assessed component at score 4.50. The system remains operational

and functional to meet the needs of present-time attendance and

payroll tracking because this essential feature ensures constant

data availability. The system shows positive capability to operate

and prevent errors based on its “Good” range “Fault Tolerance”

score of 4.17. Modifications to its current approach could strengthen

a decent level of resilience which this score represents. The existing

recovery capabilities demonstrate promising results although more

improvements can be done to enhance efficiency during recovery

periods. The system maintains reliable operations based on

comprehensive ratings yet added strategic improvements focused

on fault tolerance could boost its reliability performance

 44

Determine the Usability of the System

Maintainability

Refers to how easily the software can be updated, debugged,

or enhanced over time. This ensures that future improvements, bug

fixes, or feature additions to the monitoring system can be

performed with minimal effort.

Table 13. Maintainability

n=6

Characteristic Description Mean

Analyzability To what extent can the developed 3.83

system or device be analyzed for
faults and deficiencies?

Changeability To what extent can the developed 4.33

system or device be modified or
extended?

Stability To what extent do changes to the 4.17

developed system or device have
unintended effects?

Testability To what extent can the developed 4.17

system or device be tested for
correctness?
TOTAL MEAN 4.13

The system maintainability category earned an overall score

of 4.13 which rating experts defined as "Good". The program

becomes immediately ready for updates following which debugging

and improvement processes occur that enable fast implementation

of additional features and bug fixes with minimal effort.

“Changeability” obtained the highest rate of 4.33 Very Good among

all individual attributes thus demonstrating excellent system

performance. The invested ratings reached 4.17 good for both

 45

“Stability” and “Testability” based on the results. “Analyzability”

received a score of 3.83 good indicating the system is testable for

flaws yet testing methods require some enhancement to achieve

greater simplicity.

Portability

Refers to the ease with which the software can be transferred

or adapted to other environments or devices, allowing the

monitoring system to be deployed in different locations or upgraded

systems without significant changes.

Table 14. Portability

n=6

Characteristic Description Mean

Adaptability To what extent can the developed 4.33

system or device be adapted to
different environments or
platforms?

Install ability To what extent is the developed 4.50

system or device easy to install
and set up?

Co-existence To what extent can the developed 4.00

system or device coexist with
other software and hardware on
the same system?

Replaceability To what extent can the developed 4.17

system or device be replaced by
another developed system or
device with similar functionality?
TOTAL MEAN 4.25

The system proves its flexibility through multiple platforms

and hardware and software “Install ability” rendering it a 4.50 Very

Good score in specific characteristics assessment. The system

 46

demonstrates easy installation abilities and replaceable functionality

through its score of 4.00 Good for co-existence with 4.17 Good for

replaceability. Research on the system portability produced an

average score of 4.25 Very Good that placed the software in the

"Good" rating category due to its excellent capability to shift

between different environments or devices. This allows simple

deployment across various barangay locations and upgraded setups

using minimal development and configuration. The systematic

analysis demonstrates that the system design features both future

scalability and simple deployment abilities.

Compatibility

Refers to the software’s capacity to operate effectively across

different devices, platforms, and browsers. This ensures that the

attendance and payroll monitoring system works seamlessly with

various hardware and other connected systems.

Table 15. Compatibility

n=6

Characteristic Description Mean

 47

Co-existence To what extent can the developed 4.00

system or device coexist with
other software and hardware on
the same system?

Interoperabilit To what extent does the developed 4.17

y system or device interact
effectively with other systems and
developed system or devices?

Replaceability To what extent can the developed 4.17

system or device be replaced by
another developed system or
device with similar functionality?
TOTAL MEAN 4.11
The analysis of system compatibility yielded an overall mean

score of 4.11 which qualified as "Good". The program demonstrates

strong capability to work across different platforms and devices and

browsers which provides seamless access to various hardware

systems and connected platforms. Both “Interoperability” and

“Replaceability” scored 4.17 Very Good points out of a possible total

5 points during reviews which demonstrated strong potential for

system or device replacement with similar functionality. The lowest

range called “Co-existence” received a score of 4.00 to indicate how

effectively this system interrelated with other systems or produced

devices. A system demonstrates this capability when it operates

together with existing hardware and other software components on

a single platform.
 48

Security

Refers to the ability of the software to protect data and

operations against unauthorized access, ensuring the confidentiality

and integrity of attendance and payroll data collected and

transmitted from the monitoring system.

Table 16. Security

n=6

Characteristic Description Mean

Confidentiality To what extent does the 3.83

developed system or device
protect against unauthorized
access to sensitive
information?

Integrity To what extent does the 4.00

developed system or device
protect against unauthorized
modification of data?

Non-repudiation To what extent does the 4.17

developed system or device
provide evidence that an
action or event occurred?

Authenticity To what extent does the 3.83

developed system or device
ensure that users are who
they claim to be?
TOTAL MEAN 3.96

The system protection capabilities were evaluated during

assessment to establish how well it safeguards operations from

unauthorized access and maintains attendance and payroll data

precision and reliability. The system demonstrates robust security

through its total mean security score of 3.96 that falls into the "fair

leaning toward good" category. “Non-repudiation” as one of the

 49

security features scored 4.17 indicating the system's capability to

log that specific events and actions occurred thus demonstrating

accountability and traceability. The features of "Confidentiality" and

"Authenticity" received 3.83 while showing average performance

but users confirmed these system components still function reliably.

The results indicate that the system operates securely thus users

can feel assured about their data protection. Future development

work focused on confidentiality measures could boost this benefit to

an even greater extent.

Interpretation of Results

This table the result of all evaluation based on ISO/IEC

250102011

Table 17. ISO/IEC 250102011

ISO CRITERIA MEAN DESCRIPTION

System Testing and Evaluation 4.34 Very Good
Determine the Quality of the 4.26 Very Good
System
Determine the Usability of the 4.11 Good
System

OVER ALL TOTAL 4.24 Very Good

The evaluation results demonstrate that the Attendance and

Payroll Management System with RFID and Fingerprint

Authentication has achieved excellent performance across all

measured criteria based on the ISO/IEC 25010:2011 quality model

framework. With an overall mean score of 4.24 described as "Very

Good," the system has successfully met its design objectives. The

system testing and evaluation category received the highest rating

 50

of 4.34 (Very Good), indicating robust performance under various

test conditions. The quality of the system scored 4.26 (Very Good),

confirming the reliability and effectiveness of its core functionality.

The usability aspect scored 4.11 (Good), suggesting the interface is

intuitive and user-friendly while leaving some minor room for

enhancement. These consistently high ratings validate that the dual

authentication approach using RFID and fingerprint biometrics has

been successfully implemented, providing a secure, efficient

solution for attendance tracking and payroll management that

meets professional standards.

 51

Chapter 3

SUMMARY, CONCLUSION, AND RECOMMENDATION

This chapter presents the summary of findings, conclusions

from the results of the study, and recommendations based on the

data gathered. The summary highlights the necessary outcomes of

the research, while the conclusion outlines how the findings relate to

the objectives of the study. The recommendations are intended to

provide suggestions for future studies based on the results and

observations of the research.

Summary of Findings

During the evaluation, it was said that our device functioned

correctly and met the required standards. They suggested adding

undertime data and a notification that floats on the screen upon

login and does not disappear quickly. A notification should appear on

the screen whenever an employee accumulates multiple absences,

late arrivals, and undertime. The result of the rating was very good

with the average of (4.29).

Its usability received the highest rating of (4.3). The system

demonstrates good overall usability, meeting expectations with only

minor improvements needed, as reflected in the consistent scoring

between “fair leaning toward good” (3.5) and “good” (4.4) across

maintainability, portability, compatibility, and security criteria. While

the system performs well in key areas, enhancements can be made

to further improve its functionality. Specifically, it is recommended

 52

to incorporate features that track and display undertime data more

comprehensively. Additionally, implementing a notification system

that alerts users when an employee accumulates multiple instances

of absences, delay, or undertime would strengthen the system’s

monitoring capabilities and support proactive management

decisions.

Conclusion

The evaluation results indicate that the system performs

effectively and meets the required standards, particularly in terms

of usability, where it achieved the highest rating. With an overall

score of 4.29 and consistent ratings across other quality criteria

such as maintainability, portability, compatibility, and security, the

system demonstrates a strong performance. To further enhance its

functionality and monitoring capabilities, it is recommended to

integrate comprehensive undertime tracking and a persistent

notification feature for employees with frequent absences, delays,

or undertime. These enhancements will contribute to more proactive

personnel management and increased system efficiency.

Recommendations

Recommendation for System Improvement

The system should become publicly accessible through web

hosting in order to eliminate limitations of local computer access.

The system may benefit from future updates that add mobile

usability and cloud storage and other payroll system connectivity.

The system enables barangays, schools along with small businesses

 53

to enhance their productivity while decreasing mistakes. The system

needs straightforward implementation capabilities which enable its

expansion when offices with more user.

Recommendations for Future Research

Our embedded system named “Development of RFID

Attendance System with Payroll Management using Machine

Learning” shows excellent scalability potential in its future

development trends. The system registers and manages more than

400 employees by employing RFID technology to track attendance

in real time with automated buzzer notifications for time-entry and

time-exit activities. The system provides internet-less operation in

remote locations yet allows remote monitoring of attendance data

and payroll records through online access for administrators. The

system benefits from machine learning capabilities which enable it

to examine employee conduct while tracking attendance behavior to

forecast absenteeism patterns for HR decision support and

workforce efficiency enhancement. The design of this system can be

improved through implementing biometric security elements that

use facial or fingerprint scans for time fraud prevention together

with automated alerts for detecting administrative irregularities.

Visual analytics technology provides managers access to summary-

based data about employee performance metrics alongside payroll

information. The implementation of solar-powered RFID terminals

with IoT and low-power design principles will improve the system's

ability to serve locations without main power supply. This system

 54

demonstrates commercial viability because it offers practical

features together with a user-friendly interface while maintaining

high registration capacities which positions it as a solution for

efficient intelligent workforce and payroll management.

 55

Chapter 4

OUTPUT OF THE STUDY

“Development of RFID Attendance System with Payroll

Management Using Machine Learning”

Rationale

The proposed of RFID Attendance System with Payroll

Management using Machine Learning addresses challenges in

manual attendance tracking, access control, and payroll

computation. By integrating FRID technology, and machine learning,

the system aims to provide a streamlined, efficient, and secure

solution for organizations.

Many current systems face issues such as poor data recording

and lengthy payroll processes, often due to a lack of integration.

This proposed solution combines attendance tracking and payroll

management with predictive insights and anomaly detection

powered by machine learning.

The system automates administrative tasks, simplifies payroll

computation, and offers intelligent insights for better organizational

decision-making. It’s designed to modernize management

processes, reduce errors, and enhance operational efficiency.

 56

Objectives

1. To introduce an integrated R307 Fingerprint Attendance and

Door Control System with Payroll Management using Machine

Learning as a modern solution to address challenges in

attendance tracking, access control, and payroll computation.

2. To train users on effectively operating the fingerprint

attendance and payroll system for seamless integration into

organizational processes.

3. To demonstrate the system's ability to automate attendance

tracking, enhance security, and streamline payroll

management using machine learning.

4. To provide an efficient and secure solution for attendance

tracking, access control, and payroll management using

machine learning.

Expected Outcome

The training on the R307 Fingerprint Attendance and Payroll

Management using Machine Learning is expected to equip

participants with the knowledge and skills to effectively use the

system. Participants will become proficient in automating

attendance tracking, enhancing access control, and streamlining

payroll processes, enabling a shift from manual to modern methods.

Through hands-on learning, they will gain confidence in

operating and troubleshooting the system while providing valuable

feedback for improvement, adhering to ISO/IEC 25010 standards.

 57

This feedback will support continuous system optimization to meet

user needs effectively.

The training is also expected to improve the barangay’s

operational efficiency by reducing time and errors, freeing up

participants for more strategic tasks. Ultimately, it will establish a

sustainable and technology-driven management approach for the

barangay, ensuring smoother and more secure operations.

Scheme of Implementation

The scheme of implementation on RFID attendance system

with payroll management using machine learning present the

systematized system tutorials and activities of the training plan

 58

Scheme of Implementation

TRAINING PLAN FOR THE USE OF ATTENDANCE SYSTEM

Sourc

Areas of Persons e of Expected Remarks

Concern Objectives Strategies Involved Budget Funds Time outcomes

A. System 1.To secure 1. Sending Brgy. Offcials, 1,000 STF 1 1.Approved

Planning & approved of training Workers, month proposal

Design Proposal from plan Tanod,BHW,Sk 2. Training

1. Formulation the brgy. proposal to officials, and program

of training plan captain on the the brgy. tanod towards the

and proposal use of the Captain system

of the system system (RFID Making of 3. Clear

RFID attendance Well- understandin

attendance system) planned g on the

system) to the training system and

 59

brgy. Workers 2. To secure program, adoptability

users list of and

participants securing

for the final list of

training which participants

is compulsory

to all brgy.

Workers

B. System 1.defining 1. Brgy. Offcials, 1,000 STF anytim 1. Use of the

RFID how the Organizatio Workers, e system with

attendance information n of Tanod,BHW,Sk convenience

System system should programs officials, and and systems

Implementatio be built (i.e., and tanod management

n physical program

1. Software system modules

and Hardware design), (structure

 60

Implementatio 2.ensuring chart)

n that the 2.

1.1. Systems information Processing

design system is logic

Conceptual operational specificatio

design – what and used, n in each

the system 3.ensuring tha module

should do t the (pseudocod

Logical design information e)

– what the system meets

system should quality

look to the standard (i.e.,

user quality

Physical assurance).

design – how

the system
 61

should be built

C. Monitoring 1. To analyse 1.Evaluation Brgy. Offcials, 1,000.0 STF anytim 1. Aware-

and Control evaluation result Workers, 0 e ness on

results analysis Tanod,BHW,Sk which part is

2. To 2. officials, and crucial and

determine Monitoring tanod who needed

whether the more

participants attention.

are using the 2. Adoption

proposed of the

system. upgraded

system RFID

Attendance

system
 62

PROPOSED OUTPUT OF THE STUDY

DEVELOPMENT OF RFID ATTENDANCE SYSTEM WITH PAYROLL

MANAGEMENT USING MACHINE LEARNING

Honey D. Barrida

Cyrus F. Cartagena

Aseneth S. Del Corro

Angeles R. Estremos

Hiljun B. Florentino

John Niño O. Gonzales

Carl Niño B. Lilibios

Zyrill Jay C. Mollaneda

Teresa A. Nulla

Minio Franz M. Vosotros

MAY 2025

Table of contents
 63

DEVELOPMENT OF RFID ATTENDANCE SYSTEM WITH

PAYROLL............................................................................. 59

ATTENDANCE SYSTEM MANUAL ADMINISTRATOR...................61

USER MANUAL..................................................................61

Step 1: Enroll Employee.............................................................61

Step 2: Register New Employee.................................................62

Step 3: Last steps of making employee.....................................62

Step 4: Attendance Records.......................................................63

Step 5: Payroll Management View..............................................63

Step 6: Performance Analysis Dashboard:.................................64

Step 7: Employee Analysis:........................................................65

Step 8: Adjust the settings and System Details.........................65

TRAINING DESIGN ON THE USE OF RFID ATTENDANCE

SYSTEM WITH PAYROLL.......................................................66

MANAGEMENT USING MACHINE LEARNING............................66

TRAINING MATRIX.............................................................68
 64

ATTENDANCE SYSTEM MANUAL ADMINISTRATOR

Welcome to the RFID Attendance System With Payroll

Management Using Machine Learning. It can to make our lives

easier with the help of the system

USER MANUAL

Step 1: Enroll Employee

First Scan the Admin

RFID card to have an

access of the admin, but

take note u can use

another Computer to

access the administrator

 65

Step 2: Register New

Employee

On the

Dashboard Admin Click the “Employee” and

after

that

Click

the

“Add

New

Employee” after typing all Information of a

 66

new Employee click the “Create Employee”.

If the employee is inactive/fired/resign you

can delete it in the sidebar of the name

Step 3: Last steps of making employee

Type all the information of new employee you can use the

picture above for your guide and then click account

 67

Step 4: Attendance

Records
 68

In the attendance record

you can edit the

attendance of the

employee even he/she is

late. Click and type in the

Start date and End date to

see the past attendance

record

Step 5: Payroll

Management View

Payroll

management in the

system you can print

the the payroll or saved

as PDF, this system will

help us to be more

transparent and

accurate in terms of

payroll management
 69

Step 6: Performance

Analysis Dashboard:

By this dashboard you can

train the machine learning

named Performance

Analytics. Click the

“Department Analysis”

you can see the

performance each

department
 70

Step 7: Employee

Analysis:

Scroll down

performance

analysis dashboard

to see this, click the

“analyze” to see the

performance of

each employee

Step 8: Adjust the

settings and

System Details

The setting is the

one control entire

system, you can

edit the works out,

if you want your

work ours start at

7am and end 5pm

you can adjust by

time configuration

settings
 71

TRAINING DESIGN ON THE USE OF RFID ATTENDANCE

SYSTEM WITH PAYROLL

MANAGEMENT USING MACHINE LEARNING

I. Title : Training on the RFID attendance

system

II. Proposed Date : May 2025

III. Proposed Venue : Daan Secante, Tudela,

Ceby

IV. Expected Participants : Brgy. Officials, Workers,

Brgy. Tanod and Sk Officials and IT experts

Rationale : .

The proposed R307 Finger Attendance, and Door Control

System with Payroll Management using Machine Learning

addresses challenges in manual attendance tracking, access

control, and payroll computation. By integrating fingerprint

technology, and machine learning, the system aims to provide

a streamlined, efficient, and secure solution for organizations.

Many current systems face issues such as poor data recording,

weak security, and lengthy payroll processes, often due to a

lack of integration. This proposed solution combines

attendance tracking, door control, and payroll management

with predictive insights and anomaly detection powered by

machine learning.
 72

The system automates administrative tasks, strengthens

access control security, simplifies payroll computation, and

offers intelligent insights for better organizational decision-

making. It’s designed to modernize management processes,

reduce errors, and enhance operational efficiency.

V. Objectives

1. To introduce an integrated R307 Fingerprint Attendance

and Door Control System with Payroll Management using

Machine Learning as a modern solution to address

challenges in attendance tracking, access control, and

payroll computation.

2. To train users on effectively operating the fingerprint

attendance and payroll system for seamless integration

into organizational processes.

3. To demonstrate the system's ability to automate

attendance tracking, enhance security, and streamline

payroll management using machine learning.

4. To provide an efficient and secure solution for attendance

tracking, access control, and payroll management using

machine learning.

5. To gather feedback on the system’s usability and

functionality based on ISO/IEC 25010 standards.

VI. Training Matrix: Please see separate sheet.

 73

VII. Budgetary Requirements:

a. Snacks

b. Lunch

c. Training materials and equipment

d. Miscellaneous

VIII. Training Staff:

Researcher (Trainer)

I. Expected Output:

Impressions

TRAINING MATRIX

Time Activity Description

Day 1

7:30 - Attendance Brgy. Official and

8:00 Workers attendance and

particiapation

8:00 - Opening Program Formal opening and

8:20 introduction to the event

8:20 - Introduction Finger Print Discuss the

9:00 attendance and advancement of system

advancement of system and its use

9:40 - Break Short recess for

10:00 refreshments

10:00 - Fundamental of system Key concepts, tools, and

11:00 methodologies
 74

11:00 - Features of system and Exploring features and

12:00 Admin and user technologies for system

and the admin user and

the user

12:00 - Lunch Break Midday meal break

1:00

1:00 - Build the system and Create the system and

2:00 testing all user will try to test it

2:00 - Implement the system The system is already

3:00 installed in the

workplace
 75

BIBLIOGRAPHY

BIBLIOGRAPHY
Ahmed et al., (2020). Biometric fingerprint access control
system with GSM module. IEEE.
https://ieeexplore.ieee.org/document/9519320
Doe et al., (2021). Challenges in data management and payroll
 76

systems: Issues and solutions. Journal of Business and

Technology,
18(2), 150-165. https://doi.org/10.1080/jbt.2021.18203
Garcia, P. (2019). Enhancing access RFID integration.
International Journal of Security Systems, 12(2), 145-160.
https://doi.org/10.5678/ijss.2019.122
Garcia, P. (2019). RFID-based attendance systems and applications.
Research Gate.
https://www.researchgate.net/publication/340246898_RFID_Ba
sed_Attendance_System_using_IoT
Johnson, M et al,. (2019). Integration of biometric and RFID
technologies for enhanced security and operations.
International Journal of Advanced Computing, 12(3), 210-225.
https://doi.org/10.1016/ijac.2019.03.015
Kashif, I., et al., (2023). IoT-enabled attendance monitoring systems.
arXiv. https://arxiv.org/pdf/2308.02591
Lee, D et al., (2021). Smart office automation with RFID and
biometrics. ScienceDirect.
https://www.sciencedirect.com/science/article/abs/pii/S095741
7421000018
Lee, K et al., (2021). Machine learning algorithms for predictive
analytics and anomaly detection in payroll systems.
International Journal of Artificial Intelligence Research, 25(4),
310-325. https://doi.org/10.1016/ijair.2021.04.018
Lee, K et al.,(2021). Machine learning applications in payroll
management. Robotics and Automation News.
https://roboticsandautomationnews.com/2023/10/13/how-ai-
and-machine-learning-are-transforming-payroll-processing/
72995
Sarma, P et al., 2018). RFID-based attendance system with SMS
notification. AARES.
https://ojs.aaresearchindex.com/index.php/aasgbcpjmra/articl
e/view/12810
Smith, M et al., (2020). The impact of automated systems on
organizational efficiency. Journal of Modern Technologies,
15(4), 123-135. https://doi.org/10.1016/j.jmt.2020.04.005
Smith, M et al.,(2020). RFID technology and its role in automating
attendance tracking. Research Gate.
https://www.researchgate.net/publication/340246898_RFID_Ba
sed_Attendance_System_using_IoT
Tan, D et al., (2022). AI-powered payroll management system.
Academia.
https://www.academia.edu/37131728/RFID_Based_Automatic_
Student_Attendance_and_Parent_SMS_Notification_System
 77

APPENDICES
 78

Appendix A: Transmittal Letter

 79

Appendix B: Advisee and Adviser Agreement Form

80
 81

Appendix C: Certificate of Presentation

 82

Appendix D: System Evaluation Instrument

83
84
85
86
87
88
89
90
91
92
93
 94

Appendix E: Screenshot and Photos

95
 96

Appendix F: Pseudocode

PSEUDOCODE: Attendance and Payroll Management System with RFID

/*

* Main System Components:

* 1. Authentication Module rfid

* 2. Attendance Tracking

* 3. Payroll Processing

* 4. Admin Dashboard

* 5. Performance Analytics

*/

// SYSTEM INITIALIZATION

function initialize_system():

setup_database()

initialize_hardware_connections()

load_configuration()

start_web_server()

display_login_screen()

// HARDWARE CONNECTIONS

function initialize_hardware_connections():

// Initialize RFID Reader

rfid = new RFIDReader()

rfid.connect()

// Initialize Fingerprint Scanner

fingerprint = new FingerprintScanner()

fingerprint.connect()

// Start background scanning threads

start_rfid_polling_thread()

start_fingerprint_polling_thread()

// AUTHENTICATION MODULE

function process_authentication(identity, auth_method):

if auth_method == "rfid":

employee = database.get_employee_by_rfid(identity)

else if auth_method == "fingerprint":

 97

employee = database.get_employee_by_fingerprint(identity)

if employee is None:

// Check if admin RFID

if auth_method == "rfid" and identity == ADMIN_RFID:

return {"success": true, "is_admin": true}

if employee is None:

return {"success": false, "message": "Authentication failed"}

return {"success": true, "employee": employee}

// ATTENDANCE TRACKING

function clock_in(employee_id, auth_method):

now = current_time()

today = current_date()

// Check if already clocked in

existing_record = database.get_attendance_record(employee_id, today)

if existing_record and existing_record.time_in is not None:

return {"success": false, "message": "Already clocked in today"}

// Determine status (on-time or late)

status = "present"

if now > WORKDAY_START + LATE_GRACE_PERIOD:

status = "late"

// Save attendance record

if existing_record:

database.update_attendance(existing_record.id, {

"time_in": now,

"status": status

})

else:

database.create_attendance({

"employee_id": employee_id,

"date": today,

"time_in": now,

"auth_method": auth_method,

"status": status

})
 98

return {

"success": true,

"message": "Clock-in successful",

"status": status,

"timestamp": now

function clock_out(employee_id, auth_method):

now = current_time()

today = current_date()

// Check if already clocked in today

existing_record = database.get_attendance_record(employee_id, today)

if not existing_record:

return {"success": false, "message": "No clock-in record found for today"}

if existing_record.time_out is not None:

return {"success": false, "message": "Already clocked out today"}

// Check minimum work duration

time_diff = now - existing_record.time_in

if time_diff < MIN_WORK_DURATION:

return {

"success": false,

"message": "Minimum work duration not met",

"remaining": MIN_WORK_DURATION - time_diff

// Update attendance record

database.update_attendance(existing_record.id, {

"time_out": now

})

// Calculate hours worked

hours_worked = (now - existing_record.time_in).total_hours()

// Generate daily payroll

generate_daily_payroll(employee_id, today)

return {
 99

"success": true,

"message": "Clock-out successful",

"hours_worked": hours_worked,

"timestamp": now

// PAYROLL PROCESSING

function calculate_payroll(employee_id, start_date, end_date):

// Get employee details

employee = database.get_employee(employee_id)

if not employee:

return {"success": false, "message": "Employee not found"}

// Get attendance records

records = database.get_attendance_records(employee_id, start_date, end_date)

if not records:

return {"success": false, "message": "No attendance records found"}

// Initialize pay categories

regular_hours = 0

overtime_hours = 0

night_diff_hours = 0

weekend_hours = 0

holiday_hours = 0

// Process each attendance record

for record in records:

if record.time_in is None or record.time_out is None:

continue

hours = (record.time_out - record.time_in).total_hours()

date = record.date

// Categorize hours

if is_holiday(date):

holiday_hours += hours

else if is_weekend(date):

weekend_hours += hours

else:

// Regular workday

if hours <= 8:
 100

regular_hours += hours

else:

regular_hours += 8

overtime_hours += (hours - 8)

// Check night differential (10PM - 6AM)

night_diff_hours += calculate_night_differential(record.time_in,
record.time_out)

// Calculate pay based on rates

regular_pay = regular_hours * employee.hourly_rate * REGULAR_RATE

overtime_pay = overtime_hours * employee.hourly_rate * OVERTIME_RATE

night_diff_pay = night_diff_hours * employee.hourly_rate * NIGHT_DIFF_RATE

weekend_pay = weekend_hours * employee.hourly_rate * WEEKEND_RATE

holiday_pay = holiday_hours * employee.hourly_rate * HOLIDAY_RATE

// Calculate gross pay

gross_pay = regular_pay + overtime_pay + night_diff_pay + weekend_pay +

holiday_pay

// Calculate deductions (taxes, benefits, etc.)

deductions = calculate_deductions(employee, gross_pay)

// Calculate net pay

net_pay = gross_pay - deductions

return {

"success": true,

"employee": employee,

"period": {"start": start_date, "end": end_date},

"hours": {

"regular": regular_hours,

"overtime": overtime_hours,

"night_diff": night_diff_hours,

"weekend": weekend_hours,

"holiday": holiday_hours

},

"pay": {

"regular": regular_pay,

"overtime": overtime_pay,

"night_diff": night_diff_pay,

"weekend": weekend_pay,
 101

"holiday": holiday_pay,

"gross": gross_pay,

"deductions": deductions,

"net": net_pay

// ADMIN FUNCTIONS

function generate_payroll_for_all_employees(start_date, end_date, admin_id):

employees = database.get_active_employees()

payroll_records = []

// Check existing payrolls

existing_payrolls = database.get_payrolls(start_date, end_date)

existing_employee_ids = get_unique_employee_ids(existing_payrolls)

// Process each employee

for employee in employees:

if employee.id in existing_employee_ids:

continue // Skip employees with existing payroll

// Calculate payroll

payroll = calculate_payroll(employee.id, start_date, end_date)

if payroll.success:

// Save to database

payroll_id = database.create_payroll({

"employee_id": employee.id,

"period_start": start_date,

"period_end": end_date,

"regular_hours": payroll.hours.regular,

"overtime_hours": payroll.hours.overtime,

"night_diff_hours": payroll.hours.night_diff,

"weekend_hours": payroll.hours.weekend,

"holiday_hours": payroll.hours.holiday,

"regular_pay": payroll.pay.regular,

"overtime_pay": payroll.pay.overtime,

"night_diff_pay": payroll.pay.night_diff,

"weekend_pay": payroll.pay.weekend,

"holiday_pay": payroll.pay.holiday,

"gross_pay": payroll.pay.gross,
 102

"deductions": payroll.pay.deductions,

"net_pay": payroll.pay.net,

"processed_by": admin_id

})

payroll_records.push({

"id": payroll_id,

"employee_name": employee.full_name,

...payroll

})

return payroll_records

// PERFORMANCE ANALYTICS

function analyze_employee_performance(employee_id, start_date, end_date):

// Get employee details

employee = database.get_employee(employee_id)

if not employee:

return {"success": false, "message": "Employee not found"}

// Get attendance records

records = database.get_attendance_records(employee_id, start_date, end_date)

if not records:

return {"success": false, "message": "No attendance records found"}

// Calculate metrics

total_workdays = calculate_working_days(start_date, end_date)

days_present = len(records)

days_late = count_late_days(records)

// Calculate rates

attendance_rate = days_present / total_workdays

punctuality_rate = (days_present - days_late) / days_present

// Calculate work hours and consistency

total_work_hours = calculate_total_work_hours(records)

expected_work_hours = days_present * 8 // 8 hours per day

work_hour_consistency = total_work_hours / expected_work_hours

// Calculate overall performance score

performance_score = (
 103

(attendance_rate * 0.25) + // 25% weight

(punctuality_rate * 0.25) + // 25% weight

(work_hour_consistency * 0.5) // 50% weight

// Determine performance category

performance_category = ""

if performance_score >= 0.85:

performance_category = "Excellent"

else if performance_score >= 0.75:

performance_category = "Good"

else if performance_score >= 0.65:

performance_category = "Average"

else if performance_score >= 0.5:

performance_category = "Needs Improvement"

else:

performance_category = "Poor"

return {

"success": true,

"employee": employee,

"period": {"start": start_date, "end": end_date},

"metrics": {

"attendance_rate": attendance_rate,

"punctuality_rate": punctuality_rate,

"work_hour_consistency": work_hour_consistency,

"days_present": days_present,

"days_late": days_late,

"total_work_hours": total_work_hours

},

"performance_score": performance_score,

"performance_category": performance_category

// USER INTERFACE MODULE (BLACK THEME)

function render_login_screen():

display_header("Attendance & Payroll System", "black")

display_current_time_and_date("white", "black")

display_container("scan-container", {

background: "black",
 104

border: "1px solid #333",

borderRadius: "10px",

padding: "20px",

textAlign: "center",

color: "white"

})

display_text("Place your RFID card or scan fingerprint", {

fontSize: "20px",

fontWeight: "bold",

color: "white"

})

display_toggle_buttons({

"time-in": {

text: "Time In",

active: true,

color: "#00FF00",

background: "#222"

},

"time-out": {

text: "Time Out",

active: false,

color: "#FF0000",

background: "#222"

display_footer("© Attendance & Payroll System", "dark-gray")

// MAIN EXECUTION

function main():

initialize_system()

start_background_polling()

// Main event loop

while system_running:

handle_events()

update_display()

process_queue()

sleep(100) // 100ms interval

 105

Appendix G: Similarity Index Certificate

 106

CURICULUM VITAE
 107

Formal

2x2 Picture

Personal Information

Name : Minio Franz M. Vosotros

Address : Daan Secante, Tudela, Cebu
Date of Birth : May 16, 2004
Place of Birth : Daan Secante, Tudela, Cebu
Civil Status : Single
Email : [email protected]
Contact Number : 09696258033

Educational Background

College : Cebu Technological University

High School : Camotes Hillside Academy
Elementary : Daan Secante Elementary School

Trainings and Seminars Attended

Note: Start from the most recent training program

 108

Formal

2x2 Picture

Personal Information

Name : Angeles R. Estremos

Address : Buenavista, Tudela, Cebu.

Date of Birth : December 28, 2003

Place of Birth : Buenavista, Tudela, Cebu.

Civil Status : Single

Email : [email protected]

Contact Number : 09307848322

Educational Background

College : Cebu Technological University

High School : Tudela National High School

Elementary : Buenavista Elementary School

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
 109

Formal

2x2 Picture

Personal Information

Name Formal
: Zyril J ay C. Mollaneda
2x2 Picture
Address : Consuelo, San Francisco, Cebu

Date of Birth : November 10, 2002

Place of Birth : Cebu City, Cebu

Personal Information
Civil Status : Single
Name :Carl Niño B. L ilibios
Email : [email protected]
Address : Mc-Arthur Tudela, Cebu
Contact Number : 09608211656
Date of Birth : J anuary 18, 2003

Place of Birth : Cebu

Educational City, Cebu
Background
Civil Status
College : Single : Cebu Technological University

Email : lilibioscarlnino@
H igh School : Ronda gmail.com
National H igh School
Contact Number : 09512386680
Elementary : Ronda Central Elementary School

Educational Background
Trainings and Seminars Attended
College : Cebu
Note: Start from Technological
the most recent training University
program

Awards Received
High School : Puertobello National High school
Note: Start from the most recent award
Elementary : Mc-Arthur Elementary School

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
110
 111
Formal

2x2 Picture

Personal Information

Name : J ohn Niño O. Gonzales

Address : General, Tudela, Cebu

Date of Birth : J anuary 19, 2004

Place of Birth : Cebu City, Cebu

Civil Status : Single

Email : [email protected]

Contact Number : 09505438175

Educational Background

College : Cebu Technological University

High School : Tudela National High School

Elementary : Tudela Central School

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
 112
Formal

2x2 Picture

Personal Information

Name : Hiljun B. Florentino

Address : Daan Secante, Tudela, Cebu

Date of Birth : J une 7, 2003

Formal
Place of Birth : Daan Seacante, Tudela, Cebu.
2x2 Picture
Civil Status : Single

Email : [email protected]

Contact Number : 09683306713

Personal Information

Educational Background
Name :Cyrus F. Cartagena

College
Address CebuI sidro
: San Technological University
San Francisco, Cebu

Date
High of Birth
School : September 30,
I mmaculate 2001
Conception I nstitute I NC.

Place of Birth
Elementary : Northern Poblacion
Daan Secante San Francisco,
Elementary School Cebu

Civil Status : Single

Trainings and Seminars Attended
Email : [email protected]
Note: Start from the most recent training program

Contact Number : 09382413963

Awards Received
Note: Start from the most recent award
Educational Background

College : Cebu Technological University

High School : Camotes National High school

Elementary : San I sidro Elementary school

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
113
 114

Formal

2x2 Picture

Personal Information

Name : Honey D. Barrida

Address : Upper Magcarongao Western Poblacion, San Francisco Cebu.

Date of Birth : April 26, 2004

Place of Birth : Upper Magcarongao Western Poblacion, San Francisco Cebu.

Civil Status : Single

Email : [email protected]

Contact Number : 09635946555

Educational Background

College : Cebu Technological University

High School : Informatics College Cebu Inc.- Consolacion

Elementary : San Francisco Central School SPED Center

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
 115

Formal

2x2 Picture

Personal Information

Name : Assenetch S. Del Corro

Address : General, Tudela, Cebu

Date of Birth : October 14, 2003

Place of Birth : General, Tudela, Cebu.

Civil Status : Single

Email : [email protected]

Contact Number : 09106741306

Educational Background

College : Cebu Technological University

High School : Tudela National High School

Elementary : Tudela Central school

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award
 116

Formal

2x2 Picture

Personal Information

Name :Teresa A. Nulla

Address : Esperanza, San Francisco, Cebu

Date of Birth : October 20, 1994

Place of Birth : Esperanza, San Francisco, Cebu

Civil Status : Single

Email :[email protected]

Contact Number : 09544989965

Educational Background

College : Cebu Technological University

High School : L orenzo C. Tanza Memorial National High school

Elementary : Esperanza Elementary school

Trainings and Seminars Attended

Note: Start from the most recent training program

Awards Received
Note: Start from the most recent award