A User-Centric Smart Library IoT & ML System (MDPI Publication)
About Project
Scientific research project published in MDPI Applied Sciences journal. Employs IoT sensors, machine learning algorithms (KNN, XGBoost), and Fog-Cloud computing to monitor and optimize library environmental conditions.
Other Projects
Distant Learning Management System (LMS) — NDU
Design, development, and deployment of a unified Distance Education Management System (LMS) for Nakhchivan State University faculty and students. Fully integrated with the Student Information Management System (SIMS / TMİS) via Single Sign-On (SSO). The platform handles live online lectures via LiveKit, course material distribution, attendance tracking, video archiving, and academic management. Officially protected by registered State Patent and Copyright Certificates. Key Features: • Full integration with SIMS (TMİS); • Single Sign-On (SSO) authentication; • Dedicated student and lecturer control panels; • LiveKit-driven live online class orchestration & management; • Course material library and video archiving; • Secure data exchange & high-throughput database architecture.
Webinar Portal — NDU
Architected and developed the University Webinar System to manage online academic conferences, lectures, and departmental webinars across all university faculties. Provides real-time video broadcasting, session registration, live moderation, and automated video archiving. Key Features: • Live webinar broadcasting & streaming; • Webinar registration & video archiving; • Faculty and department level administration; • Granular user role & permission management; • Centralized video storage library.
Comparative Analysis of Computational Efficiency of Machine Learning Models and Interpretation of Sensor Importance in IoT-Based Smart Library Environments
Scientific research paper published in Scientific Works of Nakhchivan State University (2026, Vol 2(135), pp. 206-217). Evaluates sensor feature importance and computational efficiency across 7 machine learning models (KNN, Random Forest, Decision Tree, SVM, XGBoost, Naive Bayes). Key Highlights: • Comparative evaluation of 7 machine learning algorithms; • Assessment of IoT sensor features on computational complexity; • Environmental parameter optimization models.