Method of Biomass Discrimination for Fast Assessment of Calorific Value

Crop byproducts are alternatives to nonrenewable energy resources. Burning biomass results in lower emission of undesirable nitrogen and sulfur oxides contributes no significant greenhouse effect. There is a diverse range energy-useful biomass, including terms calorific value. This article presents new method discriminating determining its The involves extracting the selected texture features on surface briquette from microscopic image then classifying them using supervised classification methods. fractal dimension, local binary pattern (LBP), Haralick computed classified by linear discrimination analysis (LDA). compared with obtained random forest (RF) deep neural network (DNN) type classifiers. approach superior complexity operating time other methods such as, for instance, calorimetric or chemical composition elements sample. In normal operation mode, our identifies value about 100 s, i.e., 90 times faster than traditional combustion material samples. predicting single sample image, overall average accuracy 95% was achieved all tested authors’ idea use ten input images same majority voting after increases system above 99%.