Аннотации:
This study presents a hybrid data analysis approach to optimize the growing
conditions for beetroot and tarragon microgreens cultivated in hydroponic systems. Maintaining precise microclimate control is essential, as even minor deviations can significantly
affect the yield and product quality, but traditional monitoring methods fail to adapt
promptly to changing conditions. To overcome this limitation, an automated monitoring
system integrating machine learning methods XGBoost 3.0.0, principal component analysis
(PCA), and fuzzy logic was developed. The model continuously identifies the deviations
in environmental parameters and recommends corrective actions to stabilize the growth
conditions. Experimental evaluation demonstrated superior predictive performance by
using XGBoost, achieving an accuracy and F1-score of 97.88%, ROC-AUC of 99.99%, and
computational efficiency (training completed in 2.3 s), outperforming RandomForest and
GradientBoosting algorithms. Real-time data collection was facilitated through IoT sensors
transmitting readings via Wi-Fi every 5 s to a local server, accumulating approximately
17,280 records per day. The analysis highlighted air humidity, solution humidity, and
temperature as critical influencing factors. This research confirms the developed system’s
effectiveness in intelligent hydroponic monitoring, with future work aimed at integrating
IoT and IIoT technologies for scalable management across diverse crops.
