Authors : M. Chiranjeevi; U. Kiran Aditya; J. Naga Leela Krishna; A. Sony; G. Sudheer Kumar; G. Samhitha

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/3m3573rr

Scribd : https://tinyurl.com/mwcjj8zd

DOI : https://doi.org/10.38124/ijisrt/25dec1385

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Students preparing for competitive examinations often rely on multiple disconnected platforms for notes, videos, topic explanations, and mock tests, resulting in a fragmented and inefficient learning experience. This paper presents Smart Preparation, an integrated, AI-driven digital learning platform designed to unify the entire exam preparation workflow into a single, cohesive system. The platform automates syllabus structuring, study-plan creation, and content generation using the Google Gemini API, enabling administrators to instantly produce summaries, flashcards, and topic-wise quizzes. Additionally, the system leverages the YouTube Data API to automatically curate high-quality educational videos, ensuring comprehensive and context-appropriate learning resources. For learners, Smart Preparation offers a guided, topic-wise learning path with real-time progress tracking and performance analytics. A fully featured proctored mock test environment simulates real examination conditions through a countdown timer and academic-integrity mechanisms such as tab-switch detection and full screen exit monitoring. The platform is developed using a modern full-stack architecture—Next.js, Node.js, and SQLite—providing a fast, secure, and scalable user experience. Overall, Smart Preparation addresses the limitations of traditional exam preparation methods by delivering an all-in-one intelligent system that enhances learning efficiency, content accessibility, and assessment reliability.

References :

1. Dickey, E., & Bejarano, A. (2024, October). Gaide: A framework for using generative ai to assist in course content development. In 2024 IEEE Frontiers in Education Conference (FIE) (pp. 1-9). IEEE.Patel, R., & Kumar, S. (2024).
2. Härkki, T. (2020, June). Eye on Collaborative Creativity: Insights From Multiple-Person Mobile Gaze Tracking in the Context of Collaborative Design. In The Interdisciplinarity of the Learning Sciences, 14th International Conference of the Learning Sciences (ICLS) 2020: Proceedings Volume 5 (pp. 2667-2668). ISLS International Society of the Learning Sciences.
3. Jurenka, I., Kunesch, M., McKee, K. R., Gillick, D., Zhu, S., Wiltberger, S., ... & Ibrahim, L. (2024). Towards responsible development of generative AI for education: An evaluation-driven approach. arXiv preprint arXiv:2407.12687.
4. Chelghoum, H., & Chelghoum, A. (2025). Artificial Intelligence in Education: Opportunities, Challenges, and Ethical Concerns. Journal of Studies in Language, Culture and Society (JSLCS), 8(1), 1-14.
5. Naseeb, A. (2024). Artificial Intelligence in Education: Transformative Innovations for 21st-Century Learning. AI EDIFY Journal, 1(1), 37-48.
6. Clay-Williams, R., Baysari, M., Taylor, N., Zalitis, D., Georgiou, A., Robinson, M., ... & Westbrook, J. (2017). Service provider perceptions of transitioning from audio to video capability in a telehealth system: a qualitative evaluation. BMC health services research, 17(1), 558.
7. Kumar, R., Kumar, P., Sobin, C. C., & Subheesh, N. P. (Eds.). (2025). Blockchain and AI in Shaping the Modern Education System. CRC Press.
8. Adeleye, O. O., Eden, C. A., & Adeniyi, I. S. (2024). Innovative teaching methodologies in the era of artificial intelligence: A review of inclusive educational practices. World Journal of Advanced Engineering Technology and Sciences, 11(2), 069-079.
9. Smith, D. (2023). An exploration of the capability of a relational database management system to encompass business and persistence capabilities within architecturally layered software.
10. Kiropoulos, K., Bibi, S., & Ampatzoglou, A. Blockchain in Precision Agriculture: A Comprehensive Survey of Architectures, Applications, and Challenges. Applications, and Challenges.
11. S. R. K. Branavan, K. Narasimhan, and R. Barzilay, “Learning to Assist: AI-Enabled Educational Content Generation,” IEEE Transactions on Learning Technologies, vol. 16, no. 3, pp. 421–434, 2023.
12. X. Liu, J. Chen, and Y. Zheng, “Generative AI for Personalized Education: Opportunities and Risks,” IEEE Access, vol. 12, pp. 8452–8463, 2024.
13. F. Ferreira and T. Ramos, “AI-Enhanced Content Creation in Digital Learning Platforms,” 2023 IEEE International Conference on Advanced Learning Technologies (ICALT), pp. 123–130, IEEE, 2023.
14. R. Mohamed, A. Al-Najjar, and M. K. Hasan, “Learning Analytics for Student Performance Visualization,” IEEE Access, vol. 11, pp. 145322–145338, 2023.
15. G. Siemens and R. Baker, “Learning Analytics and Educational Data Mining: Towards Deep Insights,” Journal of Learning Analytics, vol. 7, no. 2, pp. 1–10, 2020.
16. L. Arora and N. Kumar, “Design of Visualization Dashboards for Student Progress Monitoring in Online Platforms,” 2022 IEEE Conference on Education Technologies, pp. 41–48, IEEE.
17. S. K. Sharma and M. Niranjan, “AI-Powered Remote Proctoring Systems: A Review,” 2023 IEEE International Conference on Smart Education Systems, pp. 89–96, IEEE.
18. T. A. Mohamed, M. A. Ezzat, and H. B. Helmy, “Secure Online Examination with Browser Activity Monitoring,” IEEE Access, vol. 10, pp. 57520–57530, 2022.
19. Sen, K. and Hardt, M., “Preventing Cheating in Online Assessments Using Behavioral and System-Level Monitoring,” ACM Digital Library, 2021.
20. A. Mitrofanova, S. Wiese, and M. Tönnis, “Automatic MCQ Generation for e-Learning Using Transformers,” 2023 IEEE Global Engineering Education Conference (EDUCON), pp. 1647–1654.
21. B. Zou, R. Peng, “Using LLMs for Automated Assessment and Feedback in Higher Education,” Computers & Education: Artificial Intelligence, Elsevier, 2024.