Automated Crop Type Classification using Moth Flame Optimization with Adaptive Neuro Fuzzy Inference Systems

Crop type classification is an important process in the agricultural field. The recent developments of artificial intelligence (AI) approaches enable to design of effective crop type, classification models. At the same time, data pre-processing is essential to transform the raw agricultural data into useful format. This study introduces a novel moth flame optimization (MFO) with adaptive neuro fuzzy inference system (ANFIS) for automated crop type classification. The presented MFO-ANFIS model majorly intends to determine the crop type based on agricultural data. For automated crop type classification, the MFO-ANFIS model follows a three stage process. At the initial stage, min-max normalization is used as a data pre-processing stage to normalize the data into uniform format. Besides, ANFIS model is used to detect and classify the different kinds of crop types. Finally, the MFO algorithm is applied to fine tune the parameters involved in the ANFIS model and thereby improve the crop type classification performance. For ensuring the enhanced outcomes of the MFO-ANFIS model, a wide ranging experimental analysis is performed. The extensive results indicated the better performance of the proposed MFO-ANFIS model interms of different aspects.