Interpretable fuzzy inference systems for cooperation of expert knowledge and data in agricultural applications using FisPro

Fuzzy inference systems (FIS) can either be designed from expert knowledge or learnt from data. The main interest of using FIS is their interpretability. An open source software called FisPro has been designed to answer precisely the needs of interpretable FIS design and learning. This work presents FisPro and illustrates through three real world applications how to cope with the different types of information while preserving interpretability, whatever the respective contributions of expertise and data in the FIS design.