Using time-series forecasting and real-time data to optimize waste collection systems

This project focuses on analysing scent-detection data for tuberculosis, with the objective of improving detection accuracy and reliability to a level that meets World Health Organization (WHO) verification standards. By applying advanced data analysis and machine learning techniques, the project aims to identify patterns, reduce false positives and negatives, and enhance the overall diagnostic performance of the detection system. Ultimately, the project seeks to support scalable, cost-effective tuberculosis screening solutions that can contribute to earlier diagnosis and improved public health outcomes.