Comparison of the Performance of Fuzzy Tsukamoto and Fuzzy Mamdani in an Internet of Things Based Grape Greenhouse Control System

Rusadi, Athirah
Ula, Munirul
Daud, Muhammad
Nurdin, Nurdin
Hasibuan, Arnawan

Journal Of Artificial Intelligence And Software Engineering
Vol 5, No 2 (2025): Juni On-Progress

The application of Internet of Things in agriculture, particularly in grape greenhouses, enables automated environmental control to enhance efficiency and crop yield. This study compares the performance of two fuzzy logic methods, Fuzzy Mamdani and Fuzzy Tsukamoto, in a temperature and humidity control system based on IoT using the DHT22 sensor. The system is designed to automate irrigation via actuators based on sensor data. Performance evaluation was conducted using RMSE, MAE, and standard deviation metrics. The results show that the Tsukamoto method achieved lower RMSE 2.6928, MAE 2.2625, and standard deviation 1.1080 compared to the Mamdani method, which recorded RMSE of 2.9039, MAE of 2.3947, and standard deviation of 1.9268. However, a paired t-test yielded a p-value of 0.0690 0.05, indicating no statistically significant performance difference. Thus, while Fuzzy Tsukamoto appears superior in metrics, both methods are considered equally effective for controlling environmental conditions in grape greenhouses.The application of Internet of Things in agriculture, particularly in grape greenhouses, enables automated environmental control to enhance efficiency and crop yield. This study compares the performance of two fuzzy logic methods, Fuzzy Mamdani and Fuzzy Tsukamoto, in a temperature and humidity control system based on IoT using the DHT22 sensor. The system is designed to automate irrigation via actuators based on sensor data. Performance evaluation was conducted using RMSE, MAE, and standard deviation metrics. The results show that the Tsukamoto method achieved lower RMSE 2.6928, MAE 2.2625, and standard deviation 1.1080 compared to the Mamdani method, which recorded RMSE of 2.9039, MAE of 2.3947, and standard deviation of 1.9268. However, a paired t-test yielded a p-value of 0.0690 0.05, indicating no statistically significant performance difference. Thus, while Fuzzy Tsukamoto appears superior in metrics, both methods are considered equally effective for controlling environmental conditions in grape greenhouses.