A computer engineer from Srinakharinwirot University (SWU) has designed a neuro-fuzzy system to predict the Air Quality Index (AQI), blending fuzzy logic with neural networks for more accurate environmental monitoring. The system leverages adaptive neuro-fuzzy inference to model the complex, nonlinear relationships between pollutants and air quality. This approach aims to improve upon traditional forecasting methods by handling uncertainty and imprecision inherent in environmental data.
The research, part of the Computational Intelligence Research Lab (CIRL) at SWU’s Department of Computer Engineering, highlights the growing role of hybrid AI systems in public health and environmental management. The video presentation details the system architecture, training process, and potential applications in real-time AQI forecasting for urban areas.
By integrating fuzzy reasoning with neural learning, the proposed system can adapt to changing pollution patterns, offering a promising tool for policymakers and citizens to take proactive measures against poor air quality.