Plant diseases affect the availability and safety of plants for human and animal consumption and threaten food safety, thus reducing food availability and access, as well as reducing crop yield and quality. There is a need for novel disease detection methods that can be used to reduce plant losses due to disease. Thus, this study aims to diagnose tomato leaf diseases by classifying healthy and unhealthy tomato leaf images using two pre-trained convolutional neural networks (CNNs): Inception V3 and Inception ResNet V2. The two models were trained using an open-source database (PlantVillage) and field-recorded images with a total of 5225 images. The models were investigated with dropout rates of 5%, 10%, 15%, 20%, 25%, 30%, 40%, and 50%. The most important results showed that the Inception V3 model with a 50% dropout rate and the Inception ResNet V2 model with a 15% dropout rate, as they gave the best performance with an accuracy of 99.22% and a loss of 0.03. The high-performance rate shows the possibility of utilizing CNNs models for diagnosing tomato diseases under field and laboratory conditions. It is also an approach that can be expanded to support an integrated system for diagnosing various plant diseases.

This study analyzes the possibility of utilizing artificial neural networks (ANNs) to characterize the drying kinetics of linden leaf samples during infrared drying (IRD) at different temperatures (50, 60, and 70 °C) with sample thicknesses between 0.210 mm and 0.230 mm. The statistical parameters were constructed using several thin-layer models and ANN techniques. The coefficient of determination (R²) and root mean square error (RMSE) were utilized to evaluate the appropriateness of the models. The effective moisture diffusivity ranged from 4.13 × 10⁻¹² m²/s to 5.89 × 10⁻¹² m²/s, and the activation energy was 16.339 kJ/mol. The applied Page, Midilli et al., Henderson and Pabis, logarithmic, and Newton models could sufficiently describe the kinetics of linden leaf samples, with R² values of >0.9900 and RMSE values of <0.0025. The ANN model displayed R² and RMSE values of 0.9986 and 0.0210, respectively. In addition, the ANN model made significantly accurate predictions of the chemical properties of linden of total phenolic content (TPC), total flavonoid content (TFC), DPPH, and FRAP, with values of R² of 0.9975, 0.9891, 0.9980, and 0.9854, respectively. The validation of the findings showed a high degree of agreement between the anticipated values generated using the ANN model and the experimental moisture ratio data. The results of this study suggested that ANNs could potentially be applied to characterize the drying process of linden leaves and make predictions of their chemical contents.

Agricultural production can achieve sustainability by appropriately applying agricultural mechanization, especially in developing countries where smallholding farmers lack sufficient agricultural machinery for their farming operations. This paper aimed to study the extent to which small-, medium-, and large-scale farms in the Delta of Egypt use agricultural mechanization in their wheat crop farming operations. K-means clustering was used to aggregate and analyze the scenarios implemented by farmers for wheat cultivation so as to suggest guidelines for each cluster of farmers on how to mechanize their indoor wheat agricultural operations to maximize production. The study is divided into two parts: Firstly, data were collected regarding the percentage of small, medium, and large farms; the cultivated area of wheat crops in small-, medium-, and large-scale farms; and the size of tractors, as an indicator of the mechanization available in the governorates of Egypt’s Delta. Secondly, data were collected through a questionnaire survey of 2652 smallholding farmers, 328 medium-holding farmers, and 354 large-holding farmers from Egypt’s Delta governorates. Based on the surveyed data, 14, 14, and 12 scenarios (indexes) were established for small-, medium-, and large-scale farms, respectively, related to various agricultural operations involved in wheat crop production. These scenarios were analyzed based on the centroids using K-means clustering. The identified scenarios were divided into three clusters for the three levels of farms. The data obtained showed the need for smallholding farmers to implement mechanization, which could be achieved through renting services. These findings, if implemented, would have huge social and economic effects on farmers’ lives, in addition to increasing production, saving time and effort, and reducing dependence on labor.

Gluten-free foods continue to be a hot topic and trend in the food market because more people are being diagnosed with gluten intolerance. Whey is a by- or co-product of the dairy industry and is considered a waste stream. In this study, whey protein concentrate (WPC), one of the whey products, was added at 8, 9, 10, 11 and 12% levels to sorghum and corn flours to make gluten-free products in the form of cookies. Mixograph and subjective evaluation showed that optimal water absorption (corn: 50–55%; sorghum: 55–60%) increased with increasing WPC level in both sorghum and corn flour dough systems. Increasing WPC from 8 to 12% resulted in a decrease in storage modulus (G’) and loss modulus (G’’) for both sorghum and corn doughs. Corn dough rheological properties were less affected by WPC addition as compared to sorghum. The diameter of gluten-free sorghum and corn cookies significantly increased with the fortification of WPC. The color of sorghum and corn cookies became darker as the WPC level increased. Cookies prepared with 10% WPC addition showed the most hardness and brittleness, probably due to the gelling property of WPC. This study contributes to the sustainable utilization of whey product and helps understand the performance of WPC during the processing of gluten-free products and its potential for making food snacks such as cookies in food manufacturing.

The global palm oil industry is targeting an increased oil extraction rate in oil palm milling to meet global demand. This can be achieved through the certification of mills and adherence to bunch grading as part of ensuring that only high-quality and ripe fresh fruit bunches are accepted and processed at all mills. However, the current grading process requires the analysis of oil palm bunches, which is laborious and tedious or prone to error due to human subjectivity. This paper introduces a non-destructive technique to predict the moisture and oil content in oil palm fruitlets using electrical impedance spectroscopy. In total, 90 samples of oil palm fruitlets at different stages of ripeness were acquired. Electrical impedance measurement of each fruitlet was done using electrocardiogram (ECG) electrodes connected to an LCR meter at frequencies of 1 kHz, 10 kHz, 20 kHz, and 100 kHz. The actual oil content in the fruitlets was determined using the Soxhlet extraction method, while the actual moisture content was determined using a standard oven-drying method. The variation of electrical impedance values at each frequency was analyzed. At 100 kHz, the correlation coefficients relating the electrical impedance to the moisture and oil content were around −0.84 and 0.80, respectively. Predictions of the moisture and oil content using linear regression of the impedance measurements at 100 kHz gave RMSE values of 5.85% and 5.71%, respectively. This information is useful for oil palm fruit grading and oil yield production estimation in the palm oil industry.