Determination of Environmental Humidity and Temperature Prediction in Agriculture Using Mamdani Inference Systems| Chapter 1 | Innovations in Science and Technology Vol. 6

The findings of a humidity and temperature prediction model in the environment for agriculture, which utilised diffuse sets and optimised their parameters using heuristic approaches such as genetic algorithms and exact methods such as Quasi-Newton, are presented in this chapter. It has been discovered that non-specialized users may have difficulty comprehending system dynamics and varied behaviour over time. The purpose of this research is to create models for predicting temperature and humidity values in the environment that are both interpretable and accurate. Because fuzzy logic has a high interpretability rating, using it to present a solution has various advantages. Non-specialized users can have a better grasp of the system dynamics by categorising the obtained values for environment humidity and temperature as high, medium, or low. The humidity and temperature are forecasted using two optimization algorithms used to two separate diffuse sets. Mamdani fuzzy inference systems have been effectively employed for crop prediction, such as crop recommendation based on temperature, humidity, and rain or weather level, using microcontroller-based devices. A Mamdani fuzzy inference system optimised with the Quasi-Newton algorithm, which uses a set of initial values generated during a previous optimization phase using a genetic algorithm, is the best implementation.

Author(s) Details:

Julio Baron Velandia,
Faculty of Engineering, Universidad Distrital “Francisco José de Cáldas”, Colombia.


Jonathan Steven Capera Quintana,
Faculty of Engineering, Universidad Distrital “Francisco José de Cáldas”, Colombia.


Sebastian Camilo Vanegas Ayala,
Faculty of Engineering, Universidad Distrital “Francisco José de Cáldas”, Colombia.

Please see the link here: https://stm.bookpi.org/IST-V6/article/view/6030