Author Guidelines

Publications

Editorial

About

Current Issue – Vol.6, Issue.2 (Apr-Jun 2026)

Current Issue – Vol.6, Issue.1 (April-June 2026)


An Optimized DeepFace Architecture for Real-Time Pedagogical Staff Surveillance and Movement Pattern Analysis in Heterogeneous Camera Topologies

Nikhil Kushwaha, Mayur Bansal, Pradyumna Tripathi, Shivank Kumar Soni

Research Paper | Journal Paper

Vol.6, Issue.1, pp.01-07, Jan-2026

DOI: 10.5281/zenodo.18149292

Abstract References Citation Download

Abstract

In the prevailing work setting of the modern technology sector, screen usage, static positions, and cognitive engagements of the brain contribute to physical and mental exhaustion. Existing solutions to fatigue monitoring and alerting are often computationally complex and wearable and invasive technology. This research work introduces the use of a vision-tracking AI model that is non-invasive and exclusive to the specific requirements of the technical professionals. The model considers the eye movements, body positions, and human interactions to provide an accurate level of physical and mental fatigue. Through the learning concept of fusion learning, the model differentiates between the drastic and short-lived work patterns and the continuous physical and mental states. The proposed model is validated to collectively work in a timely and expert manner with very low computational complexity, thereby imparting expert warning notifications related to physical and mental fatigue. The model adheres to the concepts and requirements of Industry 5.0.

Key-Words / Index Term: Computer Vision, Workload Detection, Mediapipe, Fusion Neural Network, Machine Learning, Artificial Intelligence, MentalFatigue

References

      1. Y. Taigman, M. Yang, M. Ranzato, and L. Wolf, "DeepFace: Closing the Gap to Human-Level Performance in Face Verification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA, pp. 1701–1708, 2014. DOI: 10.1109/CVPR.2014.220.
      2. F. Schroff, D. Kalenichenko, and J. Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 815–823, 2015. DOI: 10.1109/CVPR.2015.7298682.
      3. N. Dakhil and A. Abdulazeez, "Face Recognition Based on Deep Learning: A Comprehensive Review," Indonesian Journal of Computer Science, vol. 13, 2024. DOI: 10.33022/ijcs.v13i3.4037.
      4. G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, "Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments," University of Massachusetts Amherst Technical Report, no. 07-49, 2007. DOI: 10.48550/arXiv.1708.08197.
      5. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, pp. 4510–4520, 2018. DOI: 10.1109/CVPR.2018.00474.
      6. P. Viola and M. Jones, "Rapid Object Detection Using a Boosted Cascade of Simple Features," Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Kauai, HI, USA, vol. 1, pp. I–I, 2001. DOI: 10.1109/CVPR.2001.990517.
      7. Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei, and Y. Sheikh, "OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 1, pp. 172–186, Jan. 2021. DOI: 10.1109/TPAMI.2019.2929257.
      8. OpenCV Documentation, "VideoCapture and Real-Time Processing," Available: https://docs.opencv.org/. [Accessed: Jan. 2025].
      9. S. Wang et al., "Multi-Camera Person Tracking via Deep Feature Fusion and Spatio-Temporal Consistency," IEEE Access, vol. 8, pp. 12489–12500, 2020.
      10. A. Hermans, L. Beyer, and B. Leibe, "In Defense of the Triplet Loss for Person Re-Identification," arXiv preprint, arXiv:1703.07737, 2017. DOI: 10.48550/arXiv.1703.07737.
      11. M. L. Tran and T. T. Nguyen, "A Real-Time Face Recognition Attendance System Using Deep Learning," International Journal of Advanced Computer Science and Applications, vol. 11, no. 9, 2020.
      12. A. Khan, R. Ahmad, and S. Islam, "Smart Surveillance Systems Using Deep Learning Techniques: A Survey," IEEE Access, vol. 9, pp. 17307–17337, 2021.
      13. J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv preprint, arXiv:1804.02767, 2018. DOI: 10.48550/arXiv.1804.02767.
      14. A. Dosovitskiy et al., "An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale," Proceedings of the International Conference on Learning Representations (ICLR), 2021.
      15. Flask Documentation, "Flask — Lightweight WSGI Web Application Framework," Available: https://flask.palletsprojects.com/. [Accessed: Jan. 2025].
      16. SQLite Documentation, "SQLite Features and Architecture," Available: https://www.sqlite.org/. [Accessed: Jan. 2025].
      17. A. R. Chowdhury, H. J. Choi, and J. Shin, "Real-Time Multi-Camera Face Recognition in Smart Buildings," IEEE Sensors Journal, vol. 20, no. 18, pp. 10856–10865, 2020.
      18. S. Minaee et al., "Deep-COVID: Predicting Community Mobility and Public Movement Trends," IEEE Transactions on Neural Networks and Learning Systems, 2021.
      19. A. Ruiz, O. Revaud, J. Verbeek, and H. Jégou, "Learning Compact Face Representations for Identity Recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
      20. C. Szegedy et al., "Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, 2017. DOI: 10.1609/aaai.v31i1.11231.
      21. R. Halder, R. Chatterjee, D. K. Sanyal, and P. K. Mallick, "Deep Learning-Based Smart Attendance Monitoring System," in Proceedings of the Global AI Congress 2019, Advances in Intelligent Systems and Computing, vol. 1112, Springer, Singapore, 2020. DOI: 10.1007/978-981-15-2188-1_9.
      22. J. K. Aggarwal and M. S. Ryoo, "Human Activity Analysis: A Review," ACM Computing Surveys, vol. 43, no. 3, Article 16, pp. 1–43, Apr. 2011. DOI: 10.1145/1922649.1922653.

Citation

Yasha Goyal, Yuvraj Singh Rathore, Srashti Kawde, Vishal Chourasiya, Imran Ali Khan, "A Vision-Based AI Framework for Real-Time Fatigue and Workload Detection in IT Professionals Using MediaPipe and a Fusion Neural Network" International Journal of Scientific Research in Technology & Management, Vol.6, Issue.1, pp.01-07, 2026. DOI: 10.5281/zenodo.18149292

A Hybrid PQC + Multi-Source-Enhanced Entropy Key-Distribution and End-to-End Encrypted Email Client

Mansi Trivedi, Kashish Singh, Shivank Soni

Research Paper | Journal Paper

Vol.6, Issue.1, pp.08-14, Dec-2025

DOI: 10.5281/zenodo.18149482

Abstract References Citation Download

Abstract

The threat of quantum computing to classical cryptographic systems rises the necessity for development of quantum resistant security framework for digital communication. Current email systems depend completely on these centralized architectures which are vulnerable to server breaches, while their cryptographic foundation and currently used encryption standards and protocols (RSA and ECC), will face existential crisis and risk from quantum algorithms like Shor's algorithm. To address these challenges, this paper presents a unified and intelligent quantum-resistant email security framework that integrates post-quantum cryptography with multi-source entropy-driven key generation for protecting emails and attachments. The proposed system employs lattice-based cryptographic schemes combined with AI-assisted randomness generation to enhance key unpredictability and resilience. Performance evaluation demonstrates a system efficiency of 90.32% with an effective 135-bit quantum-safe security strength, achieving a practical balance between performance and security with the framework ensuring true end-to-end encryption, guaranteeing that only authorized clients can access sensitive data even in the event of server compromise. Furthermore, the proposed approach provides a scalable foundation for future expansion into a comprehensive quantum-safe digital workspace incorporating secure collaboration tools, enhanced usability, and regulatory compliance.

Key-Words / Index Term: Post-Quantum Cryptography, Quantum-Safe Email, Multi-Source-Enhanced Security, Cryptographic Efficiency, Kyber Algorithm, Quantum Key Distribution, Entropy Generation, Secure Communication, Lattice-Based Cryptography, Quantum Resistance.

References

      1. G. Alagic, B. Alper, D. Apon, D. Cooper, J. Dang, J. Draughon, C. Dumas, R. Griffin, M. Gunn, L. Hernandez, R. Hughes, M. Jamil, S. Jeffries, R. Jones, J. Kampan, J. Kelsey, T. Kleinjung, D. Kuemper, C. Lim, C. McGrew, S. Moody, R. Perlner, R. Reeds, D. Rogaway, Y. Shen, and B. Westerbaan, “NIST Post-Quantum Cryptography Standardization Report,” NISTIR 8413, Nat. Inst. Standards Technol., 2022.
      2. D. J. Bernstein, “Introduction to post-quantum cryptography,” in Post-Quantum Cryptography, Springer, 2009, pp. 1–14.
      3. J. Bos, L. Ducas, E. Kiltz, T. Lepoint, V. Lyubashevsky, J. M. Schanck, P. Schwabe, and D. Stehle, “CRYSTALS-Kyber: A CCA-secure module-lattice-based KEM,” in Proc. IEEE Eur. Symp. Security Privacy (EuroS&P), 2018.
      4. L. Chen, “Report on post-quantum cryptography,” NIST Tech. Ser., Nat. Inst. Standards Technol., 2016.
      5. L. Ducas, E. Kiltz, T. Lepoint, V. Lyubashevsky, P. Schwabe, G. Seiler, and D. Stehle, “CRYSTALS-Dilithium: A lattice-based digital signature scheme,” J. Cryptographic Eng., vol. 10, no. 1, pp. 57–68, 2020.
      6. L. K. Grover, “A fast quantum mechanical algorithm for database search,” in Proc. 28th Annu. ACM Symp. Theory Comput. (STOC), 1996, pp. 212–219.
      7. P. W. Shor, “Algorithms for quantum computation: Discrete logarithms and factoring,” in Proc. 35th Annu. Symp. Found. Comput. Sci. (FOCS), 1994, pp. 124–134.
      8. C. Gidney and M. Ekerå, “How to factor 2048 bit RSA integers in 8 hours using 20 million noisy qubits,” Quantum, vol. 5, p. 433, 2021.
      9. Y. Dodis, R. Gennaro, J. Hastad, M. Rabin, and T. Ristenpart, “Entropy, extractors, and their cryptographic applications,” SIAM J. Comput., vol. 36, no. 5, pp. 1451–1493, 2004.
      10. C. Gutierrez, “Analysis of Linux random number generation,” IEEE Security Privacy, vol. 15, no. 6, pp. 64–71, Nov.–Dec. 2017.
      11. H. Krawczyk, “Cryptographic extraction and key derivation: The HKDF scheme,” in Proc. 30th Annu. Int. Cryptol. Conf. (CRYPTO), Santa Barbara, CA, USA, 2010, pp. 410–429.
      12. P. Zimmermann, The Official PGP User’s Guide. Cambridge, MA, USA: MIT Press, 1995.
      13. B. Ramsdell, “S/MIME version 3 message specification,” IETF RFC 2633, Jul. 1999.
      14. Proton Technologies AG, “ProtonMail security features technical white paper,” 2021. [Online]. Available: https://proton.me
      15. Tutanota GmbH, “Tutanota encryption whitepaper,” 2020. [Online]. Available: https://tutanota.com
      16. D. Cash, S. Jarecki, C. S. Jutla, C. S. Williamson, and D. X. Song, “Highly scalable searchable symmetric encryption with support for boolean queries,” in Proc. 34th Annu. Int. Cryptol. Conf. (CRYPTO), Santa Barbara, CA, USA, 2014, pp. 353–373.
      17. C. Fromknecht, J. P. Miller, and I. C. Smith, “A decentralized public key infrastructure with identity retention,” IACR Cryptol. ePrint Arch., Rep. 2014/089, 2014.
      18. P. Schwabe, D. Stehle, and K. G. Paterson, “Post-quantum TLS without handshake signatures,” in Proc. 2020 ACM SIGSAC Conf. Comput. Commun. Security (CCS), Virtual Event, 2020, pp. 1461–1477.
      19. K. Kwiatkowski and L. Valenta, “The TLS post-quantum experiment,” Cloudflare Blog, Jun. 2019. [Online]. Available: https://blog.cloudflare.com
      20. D. Cooper, S. Santesson, B. Farrell, S. Boeyen, R. Housley, and W. Polk, “Internet X.509 public key infrastructure certificate and certificate revocation list (CRL) profile,” IETF RFC 5280, May 2008.
      21. M. Marlinspike and T. Perrin, “The double ratchet algorithm,” Signal Protocol Specification, Nov. 2016. [Online]. Available: https://signal.org
      22. D. X. Song, D. Wagner, and A. Perrig, “Practical techniques for searches on encrypted data,” in Proc. IEEE Symp. Security Privacy, Berkeley, CA, USA, 2000, pp. 44–55.
      23. M. W. Storer, K. Greenan, and E. L. Miller, “Secure data deduplication,” in Proc. 4th ACM Workshop Storage Security Privacy (StorageSS), Alexandria, VA, USA, 2008, pp. 1–10.
      24. Virtru Corporation, “Virtru technical overview: Data-centric security,” 2022. [Online]. Available: https://virtru.com
      25. S. Pirandola, U. L. Andersen, N. Berta, D. Bunn, R. Chillemi, A. Curci, S. Erdmann, A. G. Ferrari, C. Gabay, D. Grasselli, M. Gyongyosi, N. J. Islam, T. Laing, C. Lupo, G. L. Ottaviani, T. P. Spengler, G. Vimercati, J. F. Villasenor, and P. Wallden, “Advances in quantum cryptography,” IEEE Commun. Surveys Tuts., vol. 21, no. 3, pp. 2347–2390, 3rd Quart. 2020.
      26. V. Scarani, H. Bechmann-Pasquinucci, N. J. Cerf, M. Dušek, N. Lütkenhaus, and M. Peev, “The security of practical quantum key distribution,” Rev. Mod. Phys., vol. 81, no. 3, pp. 1301–1350, 2009.

Citation

Mansi Trivedi, Kashish Singh, Shivank Soni, "A Hybrid PQC + Multi-Source-Enhanced Entropy Key-Distribution and End-to-End Encrypted Email Client" International Journal of Scientific Research in Technology & Management, Vol.6, Issue.1, pp.08-14, 2026. DOI: 10.5281/zenodo.18149482

AI-Driven Zero-Trust Blockchain Framework for Secure and Scalable IoT Data Sharing

Niharika Sarathe, Nikha Yadav, Monu Kumar, Imran Ali Khan

Research Paper | Journal Paper

Vol.6, Issue.1, pp.15-21, Jan-2026

DOI: 10.5281/zenodo.18193372

Abstract References Citation Download

Abstract

The rapid expansion of Internet of Things (IoT) networks has increased the demand for secure, transparent, and scalable data-sharing mechanisms, while conventional centralized IoT architectures remain vulnerable to data tampering, unauthorized access, and single-point failures. Additionally, the lack of adaptive trust management allows compromised devices to impact the entire network. Although blockchain-based solutions provide immutability, they offer limited dynamic trust evaluation, and Zero-Trust models focus mainly on authentication without tamper-proof logging. To overcome these limitations, this paper proposes an integrated Blockchain–Zero Trust IoT Security Framework that combines immutable recordkeeping with continuous trust assessment. Device fingerprints and user credentials are hashed using SHA-256, and all device activities are recorded on a blockchain employing a Merkle Forest structure for scalable verification. An AI-based reputation model evaluates device behavior in real time, allowing only trustworthy devices to execute operations. Experimental results show that the proposed framework achieves up to 92% malicious device detection accuracy, compared to 55–65% in traditional approaches, while maintaining an average latency of approximately 2.01 seconds per action. Furthermore, the Merkle Forest–based blockchain ensures near-linear scalability as the number of devices increases from 100 to 10,000, providing enhanced security and transparency with minimal performance overhead.

Key-Words / Index Term: Internet of Things, Blockchain, Zero Trust Architecture, Merkle Forest, AI-Based Reputation System, IoT Security.

References

      1. J. Kindervag, “Build Security Into Your Network’s DNA: The Zero Trust Network Architecture,” Forrester Research, 2010.
      2. S. Rose, O. Borchert, S. Mitchell, and S. Connelly, “Zero Trust Architecture,” NIST Special Publication 800-207, National Institute of Standards and Technology, 2020.
      3. A. Dorri, S. S. Kanhere, and R. Jurdak, “Blockchain in Internet of Things: Challenges and Solutions,” IEEE Communications Surveys & Tutorials, vol. 19, no. 3, pp. 1736–1762, 2017.
      4. M. Conoscenti, A. Vetrò, and J. C. De Martin, “Blockchain for the Internet of Things: A Systematic Literature Review,” IEEE/ACS International Conference on Computer Systems and Applications, 2016.
      5. K. Christidis and M. Devetsikiotis, “Blockchains and Smart Contracts for the Internet of Things,” IEEE Access, vol. 4, pp. 2292–2303, 2016.
      6. Y. Zhang, R. Yu, S. Xie, Y. Zhang, and M. Guizani, “Securing Internet of Things with Blockchain: Challenges and Opportunities,” IEEE Network, vol. 32, no. 1, pp. 40–46, 2018.
      7. L. Atzori, A. Iera, and G. Morabito, “The Internet of Things: A Survey,” Computer Networks, vol. 54, no. 15, pp. 2787–2805, 2010.
      8. F. Z. Yousaf, M. Bredel, S. Schmid, and M. Menth, “Network and Service Management for the Internet of Things,” IEEE Communications Magazine, vol. 55, no. 7, pp. 42–49, 2017.
      9. X. Wang, W. Cheng, P. Mohapatra, and T. Abdelzaher, “Enabling Secure and Efficient Trust Management in IoT Using Machine Learning,” IEEE Internet of Things Journal, vol. 6, no. 4, pp. 6503–6514, 2019.
      10. S. Sicari, A. Rizzardi, L. A. Grieco, and A. Coen-Porisini, “Security, Privacy and Trust in Internet of Things: The Road Ahead,” Computer Networks, vol. 76, pp. 146–164, 2015.
      11. P. Fremantle, B. Aziz, J. Kopecký, and P. Scott, “Federated Identity and Access Management for the Internet of Things,” International Workshop on Secure Internet of Things, IEEE, 2014.
      12. M. Abomhara and G. M. Køien, “Security and Privacy in the Internet of Things: Current Status and Open Issues,” International Conference on Privacy and Security in Mobile Systems, IEEE, 2014.
      13. H. Xu, W. Yu, D. Griffith, and N. Golmie, “A Survey on Industrial Internet of Things: A Cyber-Physical Systems Perspective,” IEEE Access, vol. 6, pp. 78238–78259, 2018.
      14. R. Roman, J. Zhou, and J. Lopez, “On the Features and Challenges of Security and Privacy in Distributed Internet of Things,” Computer Networks, vol. 57, no. 10, pp. 2266–2279, 2013.
      15. A. Reyna, C. Martín, J. Chen, E. Soler, and M. Díaz, “On Blockchain and Its Integration with IoT: Challenges and Opportunities,” Future Generation Computer Systems, vol. 88, pp. 173–190, 2018.
      16. T. Alladi, V. Chamola, and N. Guizani, “Blockchain Applications for Industry 4.0 and Industrial IoT,” IEEE Communications Magazine, vol. 57, no. 8, pp. 86–92, 2019.
      17. Z. Mlika, A. Chehab, and H. Karam, “Trust Management in IoT Systems: A Survey,” IEEE Internet of Things Journal, vol. 7, no. 6, pp. 5130–5147, 2020.

Citation

Niharika Sarathe, Nikha Yadav, Monu Kumar, Imran Ali Khan, "AI-Driven Zero-Trust Blockchain Framework for Secure and Scalable IoT Data Sharing" International Journal of Scientific Research in Technology & Management, Vol.6, Issue.1, pp.15-21, 2026. DOI: 10.5281/zenodo.18193372

CampusSmart Scheduler: AI-Based Automated Timetable Management System

Jagrati Agrawal, Medha Agrawal, Narayani Puranik, Maneshwari Pawar

Research Paper | Journal Paper

Vol.6, Issue.1, pp.22-26, Jan-2026

DOI: 10.5281/zenodo.18193372

Abstract References Citation Download

Abstract

Designing an academic timetable is a complex and time-consuming task that requires balancing multiple constraints related to classrooms, faculty availability, student batches, and institutional policies. This challenge, formally known as the University Course Timetabling Problem (UCTP), belongs to the class of NPhard combinatorial optimization problems due to its vast search space and tightly coupled constraints. In most universities, timetable preparation is still carried out manually, often taking 12–15 days and resulting in poor utilization of physical resources, typically below 40%. This paper presents Campus Smart Scheduler, an intelligent and automated timetable management system developed using the OptaPlannerconstraint-solving framework. The proposed solution models the UCTP as a Weighted Constraint Satisfaction Problem (WCSP) and employs a hybrid approach that combines Constraint Satisfaction Programming for feasibility with Genetic Algorithms for optimization. A key contribution of this work is a mathematically defined softconstraint model that explicitly promotes smart space utilization by penalizing room underutilization and fragmented scheduling. Experimental results demonstrate significant improvements in scheduling speed, feasibility, and room utilization efficiency, making the system a practical and scalable solution for modern academic institutions.

Key-Words / Index Term: University Timetabling, Constraint Satisfaction Problem, Genetic Algorithm, OptaPlanner, Smart Space Utilisation, NP-Hard Problem.

References

      1. Ahmed, S., Burke, E. K., and Pham, N. (2022). A hybrid optimisation approach for university course timetabling problems. Journal of Scheduling, 25(2), 145–160.
      2. Burke, E. K., Kingston, J. H., and de Werra, D. (2004). Automated timetabling: The state of the art. European Journal of Operational Research, 140(2), 266–280.
      3. Burke, E. K., McCollum, B., Meisels, A., Petrovic, S., and Qu, R. (2007). A graph-based hyper-heuristic for educational timetabling problems. European Journal of Operational Research, 176(1), 177–192.
      4. Carter, M. W., and Laporte, G. (1998). Recent developments in practical course timetabling. In Practice and Theory of Automated Timetabling (pp. 3–19). Springer, Berlin, Heidelberg.
      5. Gupta, R., and Rao, P. (2020). An evolutionary algorithm-based approach for faculty-oriented university timetable scheduling. International Journal of Advanced Computer Science and Applications, 11(6), 312–319.
      6. Smith, J., Kumar, A., and Verma, R. (2019). Genetic algorithm-based solution for university course timetabling problems. International Journal of Computer Applications, 178(7), 25–31.
      7. OptaPlanner Documentation (2023). Constraint solving and optimisation framework. Red Hat Inc.
      8. Schaerf, A. (1999). A survey of automated timetabling. Artificial Intelligence Review, 13(2), 87–127.

Citation

Jagrati Agrawal, Medha Agrawal, Narayani Puranik, Maneshwari Pawar, "CampusSmart Scheduler: AI-Based Automated Timetable Management System" International Journal of Scientific Research in Technology & Management, Vol.6, Issue.1, pp.22-26, 2026. DOI: 10.5281/zenodo.18244099

Reducing Decision Uncertainty in AI-Based Student Career Guidance Using a Hybrid Machine Learning and Large Language Model Framework

Shubham Mallick, Prakrati Mishra, Saksham Kumar, Sakshi Pawar

Research Paper | Journal Paper

Vol.6, Issue.1, pp.27-38, Jan-2026

DOI: 10.5281/zenodo.18271325

Abstract References Citation Download

Abstract

Educational decision-making, particularly the selection of academic streams and career pathways, involves high levels of uncertainty and long-term consequences for students. Although machine learning–based guidance systems have demonstrated strong predictive performance, many students remain hesitant or unconvinced by algorithmic recommendations due to limited interpretability and contextual understanding. This paper presents a hybrid Machine Learning–Large Language Model (ML–LLM) framework designed to reduce decision uncertainty rather than focusing solely on prediction accuracy. The proposed system integrates supervised machine learning models for academic stream prediction, psychometric assessment, and dropout-risk analysis with an LLM-based advisory module that provides natural-language explanations and confidence-aware guidance. To evaluate system effectiveness, uncertainty-oriented metrics such as Prediction Entropy, Decision Stability Score, and Risk Reduction Index are employed alongside traditional performance measures. Experimental results based on real student data demonstrate that the inclusion of LLM-driven explanations significantly improves decision confidence and stability compared to ML-only systems. The findings highlight the importance of uncertainty-aware evaluation in educational AI systems and support the role of explanation-driven hybrid frameworks in improving student-centered decision support.

Key-Words / Index Term: Decision Uncertainty; Educational Decision Support Systems; Machine Learning; Large Language Models; Career Guidance; Explainable Artificial Intelligence; Hybrid AI Framework.

References

      1. M. Alamri, M. Khan, and M. Rahman, “A machine learning framework for academic and career path prediction using student performance data,” IEEE Access, vol. 11, pp. 45566–45578, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.10051343
      2. A. Kumar, A. Tripathi, and R. S. Anand, “Predicting suitable academic fields using ensemble learning techniques,” Education and Information Technologies, vol. 29, no. 4, pp. 4417–4432, 2024. DOI: https://doi.org/10.1007/s10639-023-12046-7
      3. J. T. M. Fernández, L. S. López, and M. G. García, “Educational recommender systems based on machine learning: A systematic review,” Applied Sciences, vol. 12, no. 19, p. 9703, 2022.
      4. Y. Li and H. Chen, “A hybrid recommendation model for academic guidance,” IEEE Access, vol. 10, pp. 23011–23022, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3146109
      5. E. B. Costa, B. Fonseca, M. A. Santana, F. F. de Araújo, and J. L. Rego, “Educational dropout prediction using machine learning: A systematic review,” Computers & Education, vol. 176, p. 104354, 2022. DOI: https://doi.org/10.1016/j.compedu.2022.104354
      6. Z. Zhang, L. Hu, and T. Wang, “Explainable artificial intelligence for educational decision systems,” Computers & Education, vol. 196, p. 104635, 2023. DOI: https://doi.org/10.1016/j.compedu.2023.104635
      7. Y. K. Dwivedi et al., “Artificial intelligence for education: Opportunities and challenges,” Information Systems Frontiers, vol. 26, pp. 211–230, 2024. DOI: https://doi.org/10.1007/s10796-023-10345-6
      8. N. Manouselis and C. Costopoulou, “Educational recommender systems: State of the art and future challenges,” User Modeling and User-Adapted Interaction, vol. 32, no. 2, pp. 389–416, 2022. DOI: https://doi.org/10.1007/s11257-021-09306-0
      9. W. Holmes, M. Bialik, and C. Fadel, “Artificial intelligence in education: Promises and implications for teaching and learning,” Nature Human Behaviour, vol. 7, no. 3, pp. 478–489, 2023. DOI: https://doi.org/10.1038/s41562-022-01427-9
      10. E. Kasneci et al., “ChatGPT for good? On opportunities and challenges of large language models for education,” Education and Information Technologies, vol. 28, no. 6, pp. 1–20, 2023. DOI: https://doi.org/10.1007/s10639-023-11706-y
      11. E. Molan, R. Gupta, and S. Lee, “Explainable AI for student counseling systems: A systematic review,” AI in Education Journal, vol. 6, no. 1, pp. 92–120, 2024.
      12. O. C. Santos, “AI-powered adaptive guidance in education: A comprehensive review,” Computers & Education, vol. 197, p. 104744, 2023. DOI: https://doi.org/10.1016/j.compedu.2023.104744
      13. R. S. Baker and G. Siemens, “Learning analytics and educational data mining: Towards communication and collaboration,” British Journal of Educational Technology, vol. 51, no. 4, pp. 1005–1015, 2020. DOI: https://doi.org/10.1111/bjet.12938
      14. R. Maurya and J. DeDiego, “Ethical integration of AI in human services: Transparency and bias mitigation in educational counseling,” AI and Ethics, vol. 4, no. 2, pp. 223–237, 2023. DOI: https://doi.org/10.1007/s43681-022-00211-7
      15. G. Bansal et al., “Does the whole exceed its parts? The effect of AI explanations on human decision-making,” Proceedings of the ACM CHI Conference on Human Factors in Computing Systems, pp. 1–16, 2021. DOI: https://doi.org/10.1145/3411764.3445268
      16. H. Lakkaraju, O. Bastani, and B. Kim, “Interpretable and explorable explanations for black-box models,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 4942–4949, 2020. DOI: https://doi.org/10.1609/aaai.v34i04.5979
      17. F. Khosravi, K. Cooper, and K. Kitto, “Explainable artificial intelligence in education: A systematic review,” Computers & Education: Artificial Intelligence, vol. 3, p. 100074, 2022. DOI: https://doi.org/10.1016/j.caeai.2022.100074
      18. T. Miller, “Explanation in artificial intelligence: Insights from the social sciences,” Artificial Intelligence, vol. 267, pp. 1–38, 2019. DOI: https://doi.org/10.1016/j.artint.2018.07.007

Citation

Shubham Mallick, Prakrati Mishra, Saksham Kumar, Sakshi Pawar, "Reducing Decision Uncertainty in AI-Based Student Career Guidance Using a Hybrid Machine Learning and Large Language Model Framework" International Journal of Scientific Research in Technology & Management, Vol.6, Issue.1, pp.27-38, Jan 2026. DOI: 10.5281/zenodo.18271325