0% found this document useful (0 votes)
24 views20 pages

Project

Uploaded by

kgpriya2003
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
24 views20 pages

Project

Uploaded by

kgpriya2003
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 20

K.

RAMAKRISHNAN COLLEGE OF
ENGINEERING
Department of Computer Science and Business
Systems
CLOUD BASED E-LEARNING PLATFORM
USING AI TUTOR

Domain: Artificial Intelligence


GUIDED BY: TEAM MEMBERS:
Mrs. B.SATHIYA B.E.,M.Tech., PRIYANKA K
ASSISTANT PROFESSOR SHANMUGAPPRIYA G
DEPARTMENT OF COMPUTER
SUDHARSHANA M
SCIENCE AND BUSINESS
SYSTEMS SUPRIYA K
ABSTRACT

• Objective :Focus on personalized learning experiences to adapt


dynamically to user performance, preferences, and goals. Provide learners
with actionable insights and tailored feedback.

• Approach: Employ AI to recommend learning paths, create quizzes,


analyze user progress. Utilize a combination of cloud infrastructure,
machine learning models, and intuitive user interfaces for scalability and
accessibility.
INTRODUCTION
• AI Integration and Education: AI enables systems to learn from data and
optimize educational experiences. Personalization is crucial for addressing
diverse learner needs.

• Role of AI in Learning: Enhance engagement through tailored


recommendations and real-time analytics. Provide targeted feedback to
improve user outcomes.
Literature Survey
Title and year Author Methods Used Challenges
"Cloud Computing in Smith, J., & Anderson, K. Review of cloud Privacy concerns and data
Education: A Review" infrastructure for scalable e- security issues in cloud-
(2020) learning solutions; hosted educational data
examines benefits like cost remain significant
reduction and flexible challenges.
access.

Adaptive Learning with Johnson, R., & Wang, Y. Uses machine learning Difficulties in training
AI in E-Learning algorithms to personalize models with sparse or
Systems" (2021) learning paths; discusses incomplete student data;
collaborative filtering and risk of over-personalization.
content-based filtering for
recommendations.
Title and year Author Methods Used Challenges
"Real-Time Feedback in Lee, H., & Patel, S. Explores AI-driven real- Ensuring accurate
E-Learning Platforms" time feedback feedback in diverse topics
(2019) mechanisms; adaptive and managing response
quizzes and hint times for real-time
generation are evaluated adaptability.
for improving learning
outcomes.
"Natural Language Gomez, P., & Lu, X. Applies NLP for question NLP can struggle with
Processing for Education" answering and content complex questions,
(2022) recommendations; resulting in inaccurate or
examines sentiment incomplete answers.
analysis for forum
moderation and
automated response
generation.
"Collaborative Learning Nguyen, T., & Roberts, M. Investigates AI Managing nuances in
and AI Moderation" moderation in discussion language can lead to
(2021) forums, focusing on inappropriate moderation
relevance, quality, and or unintentional
sentiment analysis to censorship.
maintain constructive
discussions.
Existing System
• AI-based e-learning platforms analyze student interactions to predict
performance, enabling tailored learning experiences and personalized
content recommendations.
• Machine learning methods such as Artificial Neural Networks (ANNs)
and k-Nearest Neighbors (kNN) are used to forecast student outcomes,
while deep learning automates the creation of quizzes, assignments, and
video summaries.
Disadvantage
• Lack of Human Interaction: Over-reliance on AI may reduce emotional
support and meaningful teacher-student interactions.

• Data Privacy and Security Concerns: Extensive student data collection


risks privacy violations and potential data breaches.

• High Implementation Costs: Developing and maintaining AI systems


require significant investment in infrastructure, skilled personnel, and
updates.
Proposed System

•AI-Driven Personalization: Tailors content and study paths using AI and


reinforcement learning, based on individual user interactions.
•Cloud-Based Infrastructure: Ensures global accessibility, scalability, and
multi-device compatibility for seamless learning anytime, anywhere.
•Interactive Features: Includes dynamic quizzes, real-time feedback, and AI-
moderated forums to boost engagement and foster collaboration.
Advantages

• The proposed system includes interactive quizzes and real-time feedback,

allowing learners to identify areas for improvement immediately.

• This feature supports a global user base, unlike traditional systems that

may struggle with scalability and remote access, especially in high-

demand scenarios.
System Architecture
System Requirements

Hardware Requirements

• Processor: Intel i5 or higher.

• RAM: 8GB for seamless multitasking.

• Storage: 250GB SSD for fast access.

• Additional: Graphics-capable monitor for interactive elements.


System Requirements
Software Requirements

• Frontend: ReactJS for a dynamic and mobile-responsive interface.

• Backend: Node.js with Express.js for robust API and service


management.

• Database: MongoDB for flexible data handling and MySQL for


structured storage.

• AI Tools: TensorFlow, Scikit-learn for model training and integration.


Modules
1. User Module

2. Administration Panel Module

3. Web-Based Panel Module

4. Quiz Generation Module

5. AI Tutor Module using Reinforcement Learning

6. Database (MongoDB) Module

7. Cloud Infrastructure Module (Google Cloud)

8. Final Interface (Frontend using React and Node.js)


Module Description

• User Module: This module handles all aspects of user interaction and
management on the platform. It caters to three main user roles:
students, tutors, and administrators.

• Administration Panel Module: A robust module for seamless


management of platform operations.
Module Description Contd.,
•Web-Based Interface Module: The bridge between users and the
platform’s offerings, emphasizing usability and interaction.

•Quiz Generation Module: Central to the platform’s assessment


capabilities, this module leverages AI for intelligent evaluation.

•AI Tutor Module Using Reinforcement Learning: The brain of the


platform, ensuring adaptability and optimization in learning.
Module Description Contd.,

•Database (MongoDB): High-performance NoSQL database for dynamic data


management.
•Cloud Infrastructure (Google Cloud): Ensures scalability, reliability, and
seamless performance.
•Final Interface (React & Node.js): Interactive and modern interface for a
smooth user experience.
Conclusion
• The Cloud-Based E-Learning Platform with an AI Tutor represents a
transformative step in modern education by integrating advanced AI
technologies to deliver personalized and engaging learning
experiences.

• The integration of AI-powered analytics allows for continuous


performance evaluation, enabling learners to identify and address
weak areas effectively, and fostering a self-driven and informed
approach to education.
References
•Almatrafi, O., & Johri, A. (2018). Systematic review of discussion forums
in massive open online courses (MOOCs). IEEE Transactions on Learning
Technologies, 12(3), 413–428.

• A. Nickow, P. Oreopoulos, and V. Quan, "The impressive effects of


tutoring on prek-12 learning: A systematic review and metaanalysis of the
experimental evidence," 2020.

• R. Luckin, M. Cukurova, C. Kent, and B. du Boulay, "Empowering


educators to be AIready," Artificial Intelligence, Elsevier, 2022.
Thank you

You might also like