Early and reliable detection of plant wilting is crucial for maintaining crop productivity and ensuring sustainable agricultural practices. This study aimed to evaluate the effectiveness of machine learning models in detecting wilting in Vinca rosea plants using simple geometric features extracted from digital images. The extracted features included leaf width, length, area, aspect ratio, and area coverage. Four machine learning classifiers, Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbours (kNN), and Naive Bayes (NB) were trained and validated to classify plants as wilted or healthy. Results showed that SVM achieved the highest performance, with 0.98 accuracy, 0.99 precision, 0.95 recall, 0.97 F1 Score, and 0.99 area under the curve (AUC), outperforming the other models. DT and kNN achieved competitive accuracy (0.97 and 0.95, respectively) but exhibited weaker recall, while NB showed high recall (0.92) but reduced precision (0.87). The findings highlight the robustness of SVM and the potential of simple geometric features combined with machine learning for rapid and reliable wilting detection. Moreover, integrating such image-based wilting detection with irrigation control can optimise water use while sustaining plant health and yield.
Efficient irrigation is vital for crop cultivation, particularly for eggplant (Solanum melongena), which ranks as Malaysia‘s fourth most important vegetable crop. This study evaluates the effectiveness of an Internet of Things (IoT)-based smart irrigation system in enhancing eggplant growth under rain shelter conditions. The system monitored environmental and soil parameters, including air temperature, relative humidity, soil pH, electrical conductivity (EC), and soil moisture and temperature, enabling remote irrigation adjustments to optimise plant health and resource use. Plant growth and environmental data were collected using both manual and IoT-based monitoring systems. IoT sensor measurements were calibrated against manual sensors at specified intervals. Results revealed a 32-day time series of sensor data and calibration curves, with R-squared values ranging from 0.78 to 0.98, indicating strong agreement between manual and IoT measurements. Eggplants irrigated using the IoT system showed significant improvements in plant height, leaf length, leaf diameter, stem thickness and root biomass compared to manual irrigation. The IoT-based monitoring system also produced reliable and consistent measurements, supporting its accuracy and applicability. In conclusion, the IoT-based smart irrigation system enhanced eggplant growth, reduced resource wastage, and improved overall efficiency, highlighting its potential for sustainable agricultural practices.
A variable seed rate system was integrated and evaluated using Trimble technology. Laboratory tests were conducted to assess system performance on a seeder test bench, with seed delivery rates ranging from 180 to 800 seeds per minute. The system was tested using two corn seed plates: a 30-cell Precision Planting plate (PP) and a 40-cell John Deere (JD) plate. The laboratory results showed a cell fill rate of 98.6% for the PP plate and 104.5% for the JD plate. Field performance was evaluated at four sowing densities (100,000; 80,000; 60,000; and 40,000 seeds·ha−1) and three travel speeds (6, 8, and 10 km·h−1). Results showed no significant differences in dosing uniformity due to sowing density otr speed. The system achieved 100% dose uniformity with a coefficient of variation (CV) of just 1.36%, demonstrating high operational reliability. Regarding seed delivery uniformity, an analysis of variance of seed fall timing revealed a significant difference between the plates. The PP plate outperformed the JD plate, with a CV of 10.82% compared to 14.387%, respectively. The system‘s response time to changes in seeding density ranged from 43 milliseconds (from 100,000 to 80,000 seeds·ha−1 at 10 km·h−1) to 232 milliseconds (from 40,000 to 100,000 seeds·ha−1 at 6 km·h−1). In conclusion, the integrated variable seed rate system demonstrated high operational reliability. However, an average variability of 12.5% in planter performance was observed, highlighting an opportunity for further optimisation and system improvement.
Soybean is a key crop due to its nutritional, industrial, and agricultural benefits. Its production performance faces challenges such as improper storage, seed damage, and moisture imbalance. This paper aims to classify soybean seeds into five categories – healthy, damaged, immature, broken, and stained – using image processing and deep learning. Four classifiers DenseNet, MobileNet, ResNet, and EfficientNet were used to classify seeds on a dataset of 5513 soybean seed images. The best performance among the models used was obtained from DenseNet with an accuracy of 96% and an F1-score of 94%. The results also showed that all models achieved an AUC value above 0.99, indicating high performance of the models. This research highlights the potential of machine learning and artificial intelligence in optimising soybean classifiers.
The aim of this study was to analyse long-term changes in diesel engines used in agricultural tractors between 2015 and 2030, with particular attention to displacement, cylinder configuration, power output, power density, efficiency and emission compliance. Technical data from tractor catalogues published in 2015 and 2024 were examined for standard agricultural models representing 33 manufacturers and power ratings from 34 kW to 527 kW. Descriptive statistics, comparative analysis and linear trend modelling were used to identify design tendencies and to forecast changes up to 2030. The results showed a systematic increase in average power and torque, accompanied by a moderate reduction in average displacement and the almost complete standardisation of turbocharging. Downsizing, based on smaller displacement and higher specific output, was most evident up to approximately 2020. Later developments indicate a gradual shift towards rightsizing, in which engine size is better matched to sustained agricultural workloads, thermal robustness and durability requirements. This shift is linked to wider implements, higher working speeds, heavier tractors and the integration of emission-control systems required by Stage V regulations. The findings indicate that modern tractor engine development is moving from aggressive displacement reduction towards balanced optimisation of efficiency, torque stability, durability and emission performance.
