An Assessment of Clustering Performance in Neuro-fuzzy system for prediction of Energy Content of Waste-derived Biomass

Optimizing energy harnessed from waste-to-energy system largely depends on accurate prediction of the energetic value of waste biomass. This study develops an evolutionary neuro-fuzzy model to predict the Higher Heating Value of waste biomass. The impact of three prominent clustering techniques of hybrid Adaptive neuro-fuzzy inference system (ANFIS) model and particle swarm optimization (PSO) on their performance was also assessed. The FCM-clustered model outperformed others with Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Mean Absolute Deviation (MAD) values of 1.2031, 8.8464, 0.8286. This outcome revealed the superior capacity of FCM-based ANFIS model for analyzing waste data. This research develops strong and reliable MSW energy prediction models for waste-to-energy and sustainable waste management decision making.