Professional Documents
Culture Documents
Final Document
Final Document
Technology: Python
CONTENT PAGE NO
Abstract
1.INTRODUCTION
1.1 Motivation
1.4 Scope
2.LITERATURE SURVEY
3. SYSTEM ANALYSIS
3.2 Disadvantages
3.4 Advantages
4. REQUIREMENT ANALYSIS
4.4 Architecture
5. SYSTEM DESIGN
6.1 Modules
8. 8. CONCLUSION
9. FUTURE ENHANCEMENT
10. REFERENCES
ABSTRACT:
In the rapidly evolving landscape of remote and online learning, the ability to monitor and assess
students' engagement and productivity has become increasingly vital. This paper presents a
pioneering approach to address this challenge through "Privacy-Preserving On-Screen Activity
Tracking and Classification in E-Learning Using Federated Learning." Our innovative solution
combines the benefits of real-time user monitoring with stringent privacy protection, aiming to
distinguish whether students are effectively utilizing their time for knowledge development or,
regrettably, wasting it. E-learning platforms have gained immense popularity, especially in light
of global events necessitating remote education. However, ensuring that students are actively
engaged and focused during online sessions remains a significant concern. Our approach
leverages Federated Learning, a decentralized machine learning paradigm, to safeguard user
privacy while accurately classifying on-screen activities. By employing this technique, we
address the dual challenge of preserving user privacy and providing valuable insights into the
efficiency of online learning. Federated Learning empowers our system to train machine learning
models collaboratively across multiple user devices, eliminating the need to centralize sensitive
data on a single server. This ensures that individual user data, including screen recordings and
interactions, remains on their devices, preserving user privacy and complying with stringent data
protection regulations such as GDPR and HIPAA. This decentralized approach sets our solution
apart from traditional methods that risk privacy breaches and data security concerns.Our system's
classification capabilities are built upon deep learning models that analyze on-screen activities in
real-time. By considering various factors such as user interactions, screen content, and time
management patterns, our system can effectively differentiate between productive knowledge
development and unproductive behavior, such as distractions or disengagement. This information
empowers educators and institutions to take timely corrective actions, thereby enhancing the
overall effectiveness of online education. "Privacy-Preserving On-Screen Activity Tracking and
Classification in E-Learning Using Federated Learning" represents a groundbreaking
contribution to the field of e-learning monitoring. By integrating Federated Learning with
advanced classification models, we strike a delicate balance between user privacy and
educational effectiveness. This innovative approach enables educators to make informed
decisions, fosters student engagement, and ultimately ensures that time spent in e-learning
environments is optimized for knowledge development rather than wasted. As the landscape of
education continues to evolve, our system provides a robust foundation for privacy-preserving,
data-driven, and effective e-learning practices.
1. INTRODUCTION
1.1 Motivation:
In the digital age, safeguarding user privacy is paramount, especially in the realm of e-learning.
Our project, "Privacy-Preserving On-Screen Activity Tracking and Classification in E-learning
Using Federated Learning," aims to revolutionize educational technology by employing
federated learning. By prioritizing user privacy, we empower learners with a secure and
personalized educational experience. This innovative approach ensures that sensitive on-screen
activities are tracked and classified without compromising individual privacy, fostering a
trustworthy and adaptive e-learning environment for all.
The rise of e-learning platforms has created a need for monitoring user activities to distinguish
between productive engagement and time-wasting behavior. Traditional methods lack privacy
protection and may compromise sensitive user data. This project aims to tackle this problem by
employing Federated Learning techniques, which allow the classification of user activities
without compromising individual privacy.
The main objective of this project is to develop a privacy-preserving system that leverages
Federated Learning to track and classify on-screen activities in e-learning environments
accurately. Specifically, it aims to:
1.4 Scope:
This project's scope encompasses the development of a privacy-preserving system for on-screen
activity tracking and classification in e-learning environments. It targets students and users of
online learning platforms. The system employs Federated Learning to ensure data privacy while
assessing user engagement. It aims to differentiate between productive learning and time-wasting
activities, ultimately providing insights to enhance e-learning experiences.
In the dynamic landscape of e-learning, the demand for personalized and adaptive learning
experiences has grown exponentially. As educational platforms incorporate sophisticated
technologies to enhance user engagement and tailor content delivery, concerns about user
privacy have become increasingly prominent. Traditional on-screen activity tracking methods
often compromise user privacy, raising ethical and legal issues. This project introduces a
groundbreaking solution — Privacy-Preserving On-Screen Activity Tracking and Classification
in E-Learning using Federated Learning. The primary goal of this project is to develop a robust
system that seamlessly integrates on-screen activity tracking and classification mechanisms into
e-learning platforms while prioritizing user privacy through the implementation of federated
learning. Federated learning is a decentralized machine learning approach that enables model
training across multiple devices or servers without exchanging raw data. By adopting this
paradigm, our system ensures that sensitive user information remains localized and secure on
individual devices.
The proposed system leverages advanced machine learning algorithms to analyze on-screen
activities, including mouse movements, keyboard inputs, and other relevant metrics, to
understand user engagement and learning patterns. Through federated learning, these algorithms
are trained collectively without exposing individual data points, preserving the privacy of each
learner. This innovative approach not only enhances the adaptability of e-learning content but
Web: www.takeoffprojects.com Phone: 08772261612
Email: info@takeoffprojects.com +91-9030333433
Domain: Application
Technology: Python
also addresses the critical concerns surrounding data privacy in educational technology. The
project aims to contribute to the broader discourse on the responsible integration of technology in
education by providing a privacy-centric solution for on-screen activity tracking. In doing so, it
seeks to strike a balance between the benefits of personalized learning experiences and the
imperative to protect user privacy. As the educational landscape continues to evolve, this
research initiative holds the promise of shaping the future of e-learning, making it more secure,
adaptive, and respectful of individual privacy.
2. LITERATURE SURVEY
[1] M. Xu, J. M. David, and S. H. Kim, ‘‘The fourth industrial revolution: Opportunities
and challenges,’’ Int. J. Financial Res., vol. 9, no. 2, pp. 90–95, 2018.
The article by M. Xu, J. M. David, and S. H. Kim explores the opportunities and challenges
associated with the fourth industrial revolution (4IR). Published in the International Journal of
Financial Research in 2018, the authors delve into the transformative impact of emerging
technologies on various industries. They discuss the potential advantages of the 4IR, such as
increased efficiency and innovation, while also acknowledging the challenges, including
concerns related to job displacement and ethical considerations. The literature survey highlights
the complex landscape of the 4IR, offering insights into the multifaceted implications of
technological advancements on the financial domain and beyond.
[2] J. Goet, ‘‘Impact of social media on academic performance of students,’’ KIC Int. J.
Social Sci. Manage., vol. 1, no. 1, pp. 35–42, Dec. 2022.
The study conducted by J. Goet investigates the influence of social media on students' academic
performance. Published in the KIC International Journal of Social Sciences and Management in
December 2022, the research explores the complex relationship between social media usage and
academic outcomes. Goet delves into the potential impacts of social media on students,
examining factors such as time management, distractions, and information assimilation. The
findings contribute to the ongoing discourse on the intersection of technology and education,
offering insights into the challenges and opportunities posed by social media in the academic
context. This research serves as a valuable resource for educators, policymakers, and researchers
seeking a nuanced understanding of the implications of social media on student learning.
[2] Alberto, T. C., Lochter, J. V., & Almeida, T. A. (2015, December). Tubespam: Comment spam
filtering on youtube. In Machine Learning and Applications (ICMLA), 2015 IEEE 14th International
The profitability
Conference on (pp. 138-143). IEEE. In this paper,
interested in understanding the challenges and opportunities associated with the intersection of
students' digital lives and academic success.
[4] C. Li and F. Lalani, The COVID-19 Pandemic has Changed Education Forever. This is
How, vol. 29. Geneva, Switzerland: World Economic Forum, 2020
In their seminal work, "The COVID-19 Pandemic has Changed Education Forever. This is
How," C. Li and F. Lalani underscore the transformative impact of the global pandemic on
education. Published in the World Economic Forum's volume 29, the authors delve into the
profound shifts induced by the pandemic in educational paradigms. They explore the accelerated
adoption of digital learning tools, the challenges posed to traditional classroom structures, and
the emergence of remote and hybrid learning models. The literature survey highlights the
pandemic's lasting imprint on education, emphasizing the imperative for innovative solutions and
adaptive strategies to navigate the evolving landscape shaped by unprecedented disruptions.
The cited literature by A. Aristovnik et al. (2020) explores the global repercussions of the
COVID-19 pandemic on higher education students. The study delves into the multifaceted
impacts, shedding light on the challenges faced by students worldwide. It scrutinizes the
transformative effects on academic, social, and psychological aspects, offering a comprehensive
understanding of the pandemic's profound influence. The research emphasizes the need for
adaptable educational strategies and support systems to mitigate the adverse effects on students'
lives. By providing a global perspective, the study contributes valuable insights for
policymakers, educators, and institutions grappling with the unprecedented challenges posed by
the pandemic in sustaining a resilient and effective higher education environment.
[6] I. E. Allen and J. Seaman, ‘‘Digital learning compass: Distance education enrollment
report,’’ Babson Survey Res. Group, Wellesley, MA, USA, Tech. Rep. 2017-1, 2017.
Web: www.takeoffprojects.com Phone: 08772261612
Email: info@takeoffprojects.com +91-9030333433
Domain: Application
Technology: Python
The literature survey conducted by I. E. Allen and J. Seaman, titled "Digital Learning Compass:
Distance Education Enrollment Report," published by the Babson Survey Research Group in
2017, provides a comprehensive analysis of distance education enrollment trends. The report
offers insights into the evolving landscape of digital learning, highlighting the increasing
prevalence of online education. It explores factors influencing enrollment, such as institutional
policies, student demographics, and emerging technologies. The findings contribute valuable
data for understanding the dynamics of distance education, aiding educators, policymakers, and
institutions in adapting to the changing educational paradigm. This research serves as a crucial
resource for stakeholders seeking to navigate and optimize digital learning environments.
3. SYSTEM ANALYSIS
The existing method for on-screen activity classification relies on Stochastic Gradient Descent
(SGD), a widely used optimization algorithm in machine learning. However, while SGD has
been effective in various applications, it presents several limitations when applied to the task of
on-screen activity classification in e-learning environments.
3.2 Disadvantages:
Privacy Concerns: SGD requires centralized data, posing a significant privacy risk as user data
is stored and processed on a central server.
Scalability Issues: It may not scale well for large-scale e-learning platforms with numerous
users and diverse activities.
Data Imbalance: SGD may struggle to handle imbalanced datasets, affecting the accuracy of
classification.
3.4 Advantages:
Privacy-Preserving: Federated Learning ensures that user data remains on local devices,
preserving individual privacy.
Accuracy: CNN excels at feature extraction from on-screen activities, while Decision Trees and
Linear Discriminant Analysis enhance classification accuracy.
Scalability: The combination of these algorithms allows the system to scale effectively,
accommodating a large number of users and diverse learning activities.
4. REQUIREMENT ANALYSIS
Requirement’s analysis is very critical process that enables the success of a system or software
project to be assessed. Requirements are generally split into two types: Functional and non-
functional requirements.
Functional Requirements: These are the requirements that the end user specifically
demands as basic facilities that the system should offer. All these functionalities need to be
necessarily incorporated into the system as a part of the contract. These are represented or
stated in the form of input to be given to the system, the operation performed and the output
expected. They are basically the requirements stated by the user which one can see directly in
the final product, unlike the non-functional requirements.
Examples of functional requirements:
1) Authentication of user whenever he/she logs into the system
2) System shutdown in Medical Insurance Cost.
3) A verification email is sent to user whenever he/she register for the first time on some
software system.
Non-functional requirements: These are basically the quality constraints that the
system must satisfy according to the project contract. The priority or extent to which these
factors are implemented varies from one project to other. They are also called non-behavioral
requirements.
They basically deal with issues like:
Portability
Security
Maintainability
Reliability
Scalability
Performance
Reusability
Flexibility
Examples of non-functional requirements:
1) Emails should be sent with a latency of no greater than 12 hours from such an activity.
2) The processing of each request should be done within 10 seconds
3) The site should load in 3 seconds whenever of simultaneous users are > 10000
4.2 Hardware Requirements
Processor - I3/Intel Processor
Hard Disk - 160GB
Web: www.takeoffprojects.com Phone: 08772261612
Email: info@takeoffprojects.com +91-9030333433
Domain: Application
Technology: Python
4.4 Architecture:
5. SYSTEM DESIGN
In an information system, input is the raw data that is processed to produce output. During the
input design, the developers must consider the input devices such as PC, MICR, OMR, etc.
Therefore, the quality of system input determines the quality of system output. Well-designed
input forms and screens have following properties −
It should serve specific purpose effectively such as storing, recording, and retrieving the
information.
It ensures proper completion with accuracy.
It should be easy to fill and straightforward.
It should focus on user’s attention, consistency, and simplicity.
All these objectives are obtained using the knowledge of basic design principles
regarding −
o What are the inputs needed for the system?
o How end users respond to different elements of forms and screens.
Output Design:
The design of output is the most important task of any system. During output design, developers
identify the type of outputs needed, and consider the necessary output controls and prototype
report layouts.
To develop output design that serves the intended purpose and eliminates the production
of unwanted output.
To develop the output design that meets the end user’s requirements.
To deliver the appropriate quantity of output.
To form the output in appropriate format and direct it to the right person.
To make the output available on time for making good decisions.
GOALS:
The Primary goals in the design of the UML are as follows:
1. Provide users a ready-to-use, expressive visual modelling Language so that they can
develop and exchange meaningful models.
2. Provide extendibility and specialization mechanisms to extend the core concepts.
3. Be independent of particular programming languages and development process.
4. Provide a formal basis for understanding the modelling language.
5. Encourage the growth of OO tools market.
6. Support higher level development concepts such as collaborations, frameworks, patterns
and components.
7. Integrate best practices.
A use case diagram in the Unified Modeling Language (UML) is a type of behavioral
diagram defined by and created from a Use-case analysis.
The main purpose of a use case diagram is to show what system functions are performed
for which actor. Roles of the actors in the system can be depicted.
CLASS DIAGRAM
In software engineering, a class diagram in the Unified Modeling Language (UML) is a type of
static structure diagram that describes the structure of a system by showing the system's classes,
their attributes, operations (or methods), and the relationships among the classes. It explains
which class contains information
SEQUENCE DIAGRAM
COLLABORATION DIAGRAM:
In collaboration diagram the method call sequence is indicated by some numbering technique as
shown below. The number indicates how the methods are called one after another. We have
taken the same order management system to describe the collaboration diagram. The method
calls are similar to that of a sequence diagram. But the difference is that the sequence diagram
does not describe the object organization whereas the collaboration diagram shows the object
organization.
DEPLOYMENT DIAGRAM
Deployment diagram represents the deployment view of a system. It is related to the component
diagram. Because the components are deployed using the deployment diagrams. A deployment
diagram consists of nodes. Nodes are nothing but physical hardware’s used to deploy the
application.
ACTIVITY DIAGRAM:
Activity diagrams are graphical representations of workflows of stepwise activities and actions
with support for choice, iteration and concurrency. In the Unified Modeling Language, activity
diagrams can be used to describe the business and operational step-by-step workflows of
components in a system. An activity diagram shows the overall flow of control.
COMPONENT DIAGRAM:
A component diagram, also known as a UML component diagram, describes the organization
and wiring of the physical components in a system. Component diagrams are often drawn to help
model implementation details and double-check that every aspect of the system's required
function is covered by planned development.
ER DIAGRAM:
An Entity–relationship model (ER model) describes the structure of a database with the help of a
diagram, which is known as Entity Relationship Diagram (ER Diagram). An ER model is a
design or blueprint of a database that can later be implemented as a database. The main
components of E-R model are: entity set and relationship set.
An ER diagram shows the relationship among entity sets. An entity set is a group of similar
entities and these entities can have attributes. In terms of DBMS, an entity is a table or attribute
of a table in database, so by showing relationship among tables and their attributes, ER diagram
shows the complete logical structure of a database. Let’s have a look at a simple ER diagram to
understand this concept.
DFD DIAGRAM:
A Data Flow Diagram (DFD) is a traditional way to visualize the information flows within a
system. A neat and clear DFD can depict a good amount of the system requirements graphically.
It can be manual, automated, or a combination of both. It shows how information enters and
leaves the system, what changes the information and where information is stored. The purpose of
a DFD is to show the scope and boundaries of a system as a whole. It may be used as a
communications tool between a systems analyst and any person who plays a part in the system
that acts as the starting point for redesigning a system.
Contrast Level:
Level 1:
Level 2:
User:
1. Data Upload Module: Users can securely upload their e-learning activity data to the system
for analysis and classification, ensuring their privacy.
2. Data Preprocessing Module: Users' data is cleaned, anonymized and features are extracted,
safeguarding their personal information while enhancing classification accuracy.
3. Algorithm Implementation Module: Users benefit from the system's advanced machine
learning algorithms, including CNN, Decision Trees, and Linear Discriminant Analysis, which
classify their activities effectively, providing insights into their learning habits.
4. Model Evaluation Module: Users can assess the performance and accuracy of the
classification models, gaining a deeper understanding of the system's effectiveness.
5. Prediction Module: Users receive predictions about their engagement levels in e-learning,
helping them understand whether they are effectively utilizing their time or potentially wasting
it, ultimately improving their learning experience.
For System:
1. Data Upload Module: This module securely collects user-generated data from various e-
learning platforms and stores it for further processing within the system.
2. Data Preprocessing Module: Data is processed by cleaning it, removing personally
identifiable information, and extracting relevant features, ensuring data quality for subsequent
classification.
3. Algorithm Implementation Module: The system deploys state-of-the-art machine learning
algorithms like CNN, Decision Trees, and Linear Discriminant Analysis to classify user
activities based on preprocessed data, ensuring accurate categorization.
4. Model Evaluation Module: This module rigorously evaluates the accuracy and effectiveness
of the classification models, ensuring the reliability of the system's predictions.
5. Prediction Module: Based on classified activities, this module predicts user engagement
levels, providing valuable insights for educational institutions and administrators to optimize e-
learning experiences and resource allocation.
ALGORITHMS
Decision Tree: A decision tree classifier is a popular machine learning algorithm used for both
classification and regression tasks. It operates by recursively partitioning the input data into
subsets based on the most influential features, creating a tree-like structure of decision nodes.
Each node represents a decision based on a specific feature, leading to a sequence of decisions
that culminate in a final prediction or classification. Decision trees are interpretable, easy to
visualize, and effective in capturing complex relationships within the data. They are widely
employed in diverse fields for their ability to handle both categorical and numerical data, making
them a versatile tool in predictive modeling.
CNN: Convolutional Neural Networks (CNNs) are a class of deep learning algorithms designed
for image and pattern recognition. Inspired by the visual processing in the human brain, CNNs
excel in extracting hierarchical features from input data. Comprising convolutional layers,
pooling layers, and fully connected layers, CNNs automatically learn spatial hierarchies of
features, enabling them to recognize complex patterns and structures in images. Widely
employed in computer vision tasks, such as image classification and object detection, CNNs
have revolutionized fields like image processing and have applications in various domains,
including healthcare, autonomous vehicles, and facial recognition technology.
Login page: Here the user will login with his credentials.
Model Selection: Here we are selecting model for training/testing based on dataset.
Prediction: User need to enter input based on selecting model, it will predict whether it
Knowledge Development or not.
Software system meets its requirements and user expectations and does not fail in an
unacceptable manner. There are various types of test. Each test type addresses a specific testing
requirement.
internal code flow should be validated. It is the testing of individual software units of the
application .it is done after the completion of an individual unit before integration. This is a
structural testing, that relies on knowledge of its construction and is invasive. Unit tests perform
basic tests at component level and test a specific business process, application, and/or system
configuration. Unit tests ensure that each unique path of a business process performs accurately
to the documented specifications and contains clearly defined inputs and expected results.
Integration tests are designed to test integrated software components to determine if they actually
run as one program. Testing is event driven and is more concerned with the basic outcome of
screens or fields. Integration tests demonstrate that although the components were individually
satisfaction, as shown by successfully unit testing, the combination of components is correct and
consistent. Integration testing is specifically aimed at exposing the problems that arise from the
combination of components.
Software integration testing is the incremental integration testing of two or more integrated
software components on a single platform to produce failures caused by interface defects.
The task of the integration test is to check that components or software applications, e.g.
components in a software system or – one step up – software applications at the company level –
interact without error.
Test Results: All the test cases mentioned above passed successfully. No defects encountered.
Acceptance Testing
User Acceptance Testing is a critical phase of any project and requires significant participation
by the end user. It also ensures that the system meets the functional requirements.
Test Results: All the test cases mentioned above passed successfully. No defects encountered.
Functional tests provide systematic demonstrations that functions tested are available as
specified by the business and technical requirements, system documentation, and user manuals.
White Box Testing is a testing in which in which the software tester has knowledge of the inner
workings, structure and language of the software, or at least its purpose. It is purpose. It is used
to test areas that cannot be reached from a black box level.
Black Box Testing is testing the software without any knowledge of the inner workings, structure
or language of the module being tested. Black box tests, as most other kinds of tests, must be
written from a definitive source document, such as specification or requirements document, such
as specification or requirements document. It is a testing in which the software under test is
treated, as a black box. you cannot “see” into it. The test provides inputs and responds to outputs
without considering how the software works.
Test objectives
Features to be tested
8.CONCLUSION
9. FUTURE ENHANCEMENT
10.REFERANCES
[1] M. Xu, J. M. David, and S. H. Kim, ‘‘The fourth industrial revolution: Opportunities and
challenges,’’ Int. J. Financial Res., vol. 9, no. 2, pp. 90–95, 2018.
[2] A. Sun and X. Chen, ‘‘Online education and its effective practice: A research review,’’ J. Inf.
Technol. Educ., Res., vol. 15, pp. 157–190, May 2016.
[3] I. E. Allen and J. Seaman, ‘‘Digital learning compass: Distance education enrollment
report,’’ Babson Survey Res. Group, Wellesley, MA, USA, Tech. Rep. 2017-1, 2017.
[4] S. I. U. Rehman, H. S. Ullah, and A. Akhtar, ‘‘Consumption of social media and academic
performance: A cross-sectional survey of perception of students in KP universities,’’ Global
Mass Commun. Rev., vol. 4, pp. 57–71, 2020.
[5] I. K. Sohail and N. A. Nabaz, ‘‘The influence of social media on student’s academic
performance: A case study of Lebanese French University,’’ Mod. Manag. Theory Pract., vol.
25, no. 2, pp. 117–127, 2019.
[6] J. Goet, ‘‘Impact of social media on academic performance of students,’’ KIC Int. J. Social
Sci. Manage., vol. 1, no. 1, pp. 35–42, Dec. 2022.
[7] S. I. U. Rehman, H. S. Ullah, and A. Akhtar, ‘‘Consumption of social media and academic
performance: A cross-sectional survey of perception of students in KP universities,’’ Global
Mass Commun. Rev., vol. 5, no. 4, pp. 57–71, Dec. 2020.
[8] C. Li and F. Lalani, The COVID-19 Pandemic has Changed Education Forever. This is How,
vol. 29. Geneva, Switzerland: World Economic Forum, 2020.
[9] A. Aristovnik, D. Keržič, D. Ravšelj, N. Tomaževič, and L. Umek, ‘‘Impacts of the COVID-
19 pandemic on life of higher education students: A global perspective,’’ Sustainability, vol. 12,
no. 20, p. 8438, Oct. 2020.
[10] M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang,
‘‘Deep learning with differential privacy,’’ in Proc. ACM SIGSAC Conf