View Proposal

Proposer
Aigerim Khairullina
Title
Study Space Intelligence Platform (Smart Library Predictor)
Goal
To create an autonomous IoT and Machine Learning platform that tracks current library occupancy and forecasts upcoming crowd surges to optimize study space utilization.
Description
The hardware layer uses an ESP32 microcontroller wired to two industrial E18-D80NK infrared sensors mounted on a doorway to calculate movement direction (In/Out) based on beam-interruption sequences and stream anonymous counts over Wi-Fi. The backend database aggregates these events into an independent time-series dataset, which a Python-based Machine Learning core processes using regression models (e.g., Random Forest, ARIMA, or XGBoost) to predict peak hours and render a 24-hour forecasting feed via dashboard.
Resources
Background
Url
Difficulty Level
High
Ethical Approval
InterfaceOnly
Number Of Students
1
Supervisor
Aigerim Khairullina
Keywords
machine learning, internet of things, esp32, predictive analytics.
Degrees
Bachelor of Science in Computational Sciences and Software Engineering
Back to List