International Research Journal of Engineering and Technology (IRJET) Volume: 12 Issue: 11 | Nov 2025
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
ACE- AI Based Cognitive Education Anirudh Kulkarni1, Darur Eashwar2, Godeshwari3, Aishwarya Hipparagi4, S N Kugali5 1234Student, 5Assistant Professor Department of Information Science and Engineering, Basaveshwar Engineering
College, Bagalkote, India ***
assessments but also enhances learner engagement and performance. by integrating AI-based evaluation, adaptive learning, and automated interview proctoring, this project aims to create a holistic digital learning ecosystem that prepares students for both academic success and professional readiness in an increasingly competitive world.
ABSTRACTThe AI-Based Cognitive Education (ACE) system integrates artificial intelligence and cognitive science to deliver a personalized, adaptive learning experience. It analyzes learners’ performance and behavior to tailor content, provide real-time feedback, and enhance understanding and skill development. ACE transforms admin-uploaded Pd's into a retrieval-augmented study and interview workflow, generating structured learning paths and difficulty-controlled question sets. Using an Ollama-compatible LLM, it evaluates responses with grounded references, while a Fast API vision service employing YOLO face detection and Insight-face embeddings ensures identity verification. Built on a Node.js/Express back-end with MongoDB and Redis, ACE optimizes latency through a cache radius parameter. Evaluation metrics such as Precision, Recall, and F1score assess LLM accuracy. By combining AI driven automation with cognitive principles, ACE advances smart, accessible, and future-ready education.
Fragmented learning makes it hard to progress from materials to mastery and assessment. ACE integrates: - Admin‑driven PDF ingestion to build a domain knowledge store. - Guided study recommendations based on observed mastery. - Retrieval‑augmented interviews and LLM rubric evaluation. - Vision‑based proctoring (YOLO InsightFace verification).
Key Words: AI in Education, Cognitive Learning, Adaptive Learning Systems, Personalized Education, Intelligent Tutoring System, Machine Learning, RAG, guided study, LLM evaluation, proctoring, YOLO, InsightFace, MongoDB, Redis
- A cache “redius” framework to reduce latency under load.
2. OBJECTIVES
1. INTRODUCTION
To build an adaptive learning platform that delivers personalized study paths tailored to individual learners
In today’s digital age, the rapid growth of online education has created vast opportunities for learners, yet it has also introduced challenges such as scattered learning resources, limited practical evaluation, and lack of personalized feedback. Traditional e-learning platforms often focus solely on theoretical knowledge, overlooking the importance of real-world skill assessment and adaptive learning experiences.
To curate and organize learning resources in a structured manner, ensuring accessibility, clarity, and relevance for diverse learners. To enable real-time analytic and personalized feedback to accelerate skill improvement
The AI-Powered E-Learning & Interview Proctor System is designed to bridge this gap by combining artificial intelligence with cognitive learning principles. The system curates high-quality educational content, simulates real-world interview environments, and offers instant, personalized feedback to help learners identify strengths and areas for improvement. Through intelligent monitoring and data-driven analysis, ACE not only ensures academic integrity during
© 2025, IRJET
|
Impact Factor value: 8.315
detection +
To simulate real-world interview environments that help users practice communication, technical, and problem-solving skills effectively. To provide instant, data-driven feedback and analytics for continuous performance improvement and career readiness.
|
ISO 9001:2008 Certified Journal
|
Page 180