Determination of Environmental Humidity and Temperature Prediction in Agriculture Using Mamdani Inference Systems
Innovations in Science and Technology Vol. 6,
5 March 2022,
Page 1-11
https://doi.org/10.9734/bpi/ist/v6/3475E
This chapter presents the results of a humidity and temperature prediction model in the environment for agriculture, which used diffuse sets and optimised their parameters using heuristic methods like genetic algorithms and exact methods like Quasi-Newton. It has been discovered that non-specialized users may struggle to understand the system dynamics and the behaviour of variables over time. The goal of this study is to develop models with a high level of interpretability and accuracy for predicting temperature and humidity values in the environment. The use of fuzzy logic to present a solution has numerous advantages because this system has a high interpretability rating. Furthermore, by categorising the obtained values for environment humidity and temperature as high, medium, or low, non-specialized users can gain a better understanding of the system dynamics. Two optimization techniques are employed to two different diffuse sets, allowing the humidity and temperature to be predicted. Mamdani fuzzy inference systems have been used successfully for the prediction of variables in crops such as the recommendation of crops based on temperature, humidity and rain or weather level using systems managed by microcontrollers. The best implementation is a Mamdani fuzzy inference system optimised with the Quasi-Newton algorithm, which employs a set of initial values obtained through a previous optimization process with a genetic algorithm.