International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Zeolite is widely applied in agriculture due to its high cation-exchange capacity, ability to improve soil fertility, and effectiveness as a slow-release carrier of nutrients. Inaddition, its porous structure allows it to retain and purify water, thereby enhancing soilmoisture balance and reducing nutrient leaching. The present study examines the influence of varying Zeolite concentrations in soil on the germination and subsequent growth dynamics of Cucumber (Cucumis sativus L.) seedlings. Experimental data were subjected to Correlation Analysis, Analysis of Variance (ANOVA), and Statistical Hypothesis testing in order to evaluate the relationship between Zeolite content and plant growth rate. The findings indicate statistically significant effects of Zeolite percentage on both germination and vegetative development, highlighting the potential of Zeolite as a soil amendment for improving Cucumber cultivation practices.

This study presents a correlation-based approach for both detecting sensor malfunctions and identifying redundant sensors in a multi-sensor condition monitoring system. Sensor malfunctions were detected using a threshold-based method that flagged correlation drops, with persistence criteria applied to eliminate false positives. While no persistent malfunctions were observed during the study, the developed algorithm remains suitable for real-time deployment. Correlation analysis also revealed that the 3axis_Y signal exhibited the highest average correlation with others, indicating redundancy. Five machine learning models were trained and evaluated with the Leave-
One-Run-Out strategy to guarantee generalization across acquisition sessions. The findings demonstrated that correlation-driven sensor selection and anomaly detection are effective tools for optimizing predictive maintenance systems, improving model generalization, and simplifying sensor networks without sacrificing reliability.