Machine learning of fuzzy rules for crop management in protected cultivation
1990
Kurata, K. | Eguchi, N.
A new idea of computer management of the crop was developed based on the concept of machine learning. The system learns the grower's crop management methods (rules) by analyzing the conditions in which the grower takes a specific action such as opening the ventilators, watering the crop, drawing the thermal screens. After learning, the system manages the crop according to the learned rules. In this way, the grower's rules are automatically incorporated in the system's management. The grower's behavior cannot be regarded as accurate as that of machines and, thus, involves fuzziness. To learn the fuzzy rules, we extended our original algorithm based on a concept of "fuzzy region". The extended algorithm was named K1-algorithm. Tests using random numbers showed a sufficient learning power of K1-algorithm. Research topics still left to be investigated for realization of the system we conceive were discussed.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par National Agricultural Library
Découvrez la collection de ce fournisseur de données dans AGRIS