Air pollution hotspot management using image processing and machine learning techniques.
My research lies in the nexus of computer vision, low-cost sensors and air quality perception, with an overarching theme of localised and efficient urban air quality management. The goal of my research work is to develop an urban air pollution hotspot management plan using machine learning and a perception-based Air Quality Index.
Urban air pollution is a pressing issue in developing countries and needs immediate action. People's perception of air pollution influences their prophylactic decision-making and behaviour. My research looks to understand the factors influencing people's perception of air pollution and develop an air quality index integrating perception and health impacts. This index can help efficiently communicate information and help people make better decisions. The research also aims to leverage computer vision and develop a deep learning-based model to estimate the particulate matter levels from camera images. Then, we use low-cost sensors and image-based estimation to map and model the pollutants and hotspots in real-time across the city by integrating various data sources (fixed monitoring stations, mobile monitoring stations & low-cost sensors). Finally, we propose management plans after conducting a scenario and cost-benefit analysis.
