Journal of Engineering Technology Access (JETA) (Online)

Determination of Clay Content by Applying Machine Learning with Hydrometer Testing and Specific Gravity Analyses

2025-04-22T15:46:21+07:00

This study aims to analyze and compare hydrometer test results with fundamental soil properties while applying Machine Learning (ML), a branch of Artificial Intelligence (AI), to enhance the speed and accuracy of clay content prediction. The study utilized soil samples from Nakhon Phanom and Sakon Nakhon provinces, Thailand. The experimental process included specific gravity and hydrometer analysis. For ML model development, linear regression (LR) and random forest regressor (RFR) were compared to analyzing factors influencing clay content. The data evaluation was based on feature importance analysis and statistical correlation (Correlation Matrix). The application of 10-fold cross-validation ensured that the models did not suffer from overfitting and confirmed the stability of predictions when using hydrometer data from longer test durations. The results indicate that hydrometer readings at longer durations exhibit a strong correlation with clay content and significantly improve the prediction accuracy of LR and RFR. The highest R² values obtained were 0.93 for LR and 0.87 for RFR, demonstrating that longer hydrometer test durations lead to more accurate clay content predictions. ML method combined with the hydrometer readings at 180 minutes, the R² exceeds 0.75. Specifically, LR outperformed RFR at minute 240, suggesting that the linear model better explains data variance at this duration. This research concludes that incorporating ML with hydrometer test data significantly improves the accuracy of clay content predictions. The findings highlight the potential of ML applications in soil property analysis and geotechnical engineering design, leading to more efficient and reliable engineering solutions.

IoT -Based Intelligent Environmental Control for Minimizing Spring Onion Bulb Weight Loss: A Grey-Taguchi Optimization

2025-05-16T08:21:54+07:00

Post-harvest storage of spring onion bulbs is a significant challenge for farmers in Nakhon Phanom, where environmental fluctuations lead to substantial product loss and reduced market value. This research addresses the need for a more efficient and scalable solution by integrating Internet of Things (IoT) technology with the Grey-Taguchi L9 method to optimize storage conditions, including temperature, relative humidity, and light intensity. The experimental methodology involved using nine different combinations of these environmental factors to monitor the weight loss of spring onions over a three-month period. The IoT system enabled real-time adjustments, and the optimization process utilized Grey Relational Analysis (GRA) to identify the most favorable storage conditions. The results indicate that temperature and relative humidity have the most significant effects on minimizing weight loss, with optimal conditions being a temperature of 20°C and a relative humidity of 65%, leading to the least weight loss of 5.2 grams. The model demonstrated a strong fit with a 99.74% R-squared value. Light intensity, however, had a negligible impact on weight loss. This research provides a practical solution for small-scale farmers, contributing to the advancement of post-harvest storage practices and sustainable agriculture. These findings are significant for regions with similar agricultural conditions and have the potential to reduce post-harvest losses, ultimately improving the economic stability of farming communities. Future research could explore applying this IoT-based approach to other crops and integrating predictive analytics for further system improvements.