Precision agriculture: On the accuracy of multilevel and clustered ANFIS models for sugarcane yield categorization

Sugarcane is one of the profit-making crops cultivated in India. Sugarcane cultivation plays a major role in rural development by means of creating employment opportunities. Detection of problems associated with sugarcane yield at an early stage helps the decision makers to decide import and export policies. In this work, a multilevel adaptive neuro fuzzy inference system (ANFIS) based on hybrid learning for sugarcane yield classification is proposed. In addition, clustering ANFIS parameters based on the optimization approaches Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Imperialist Competitive Algorithm (ICA) is also incorporated in order to enhance the accuracy of the system under study. The performance of the proposed multi level approach is compared with clustered GA, PSO and ICA. Experimental results show the superiority of the PSO approach in sugarcane yield classification.