This study proposes a novel method for identifying grape leaf diseases through RGB image analysis combined with weighted group decision-making. The investigation focused on five disease types, Black Measles, Black Rot, Leaf Blight, Powdery Mildew, and Downy Mildew, along with healthy leaves. Three machine learning classifiers, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN), were employed individually and in a weighted ensemble. Each classifier was assigned a weight based on its accuracy, and the final disease classification was determined using a majority voting strategy. To determine the most discriminative features related to texture, color, and shape, the Relief feature selection algorithm was applied, which identified the top five effective features in diagnosing grape leaf diseases. Experimental results indicated that the classification accuracies of SVM, RF, and k-NN were 88.33%, 80.08%, and 75%, respectively. Furthermore, the proposed weighted group decision-making approach improved the overall classification performance, achieving an accuracy of 91.67%.
The rapid growth of the global population and the increasing demand for energy, coupled with the urgent need for environmental conservation, have prompted researchers to explore renewable energy sources as viable alternatives to non-renewable fossil fuels. This study evaluates the performance enhancement of photovoltaic/thermal (PVT) systems using an immersion cooling method with copper oxide nanofluids. The experimental setup included a glass chamber immersing the panel surface, tested at nanofluid volume ratios of 0.025% and 0.05%, and flow rates of 0.01 and 0.02 L s-1. The immersion height was 5 cm within the glass chamber. The tests were conducted under ambient conditions, which included an ambient temperature of 20.6-31.2 ℃ and an irradiance of 343-924 W m-2. Results demonstrate that copper oxide nanofluids at a 0.05% volume ratio and a 0.02 L s-1 flow rate improved thermal efficiency to 31.87% and reduced panel surface temperature by up to 11.8 °C compared to water cooling. Also, the electrical efficiency of the PVT system exceeded that of the reference panel. The overall efficiency of the PVT system reached 41.89%. These findings highlight the potential of nanofluid-based cooling to optimize PVT system efficiency by enhancing thermal management.
Monitoring the status of machinery is a crucial aspect of production and service units to uphold operational efficiency. Timely changes in engine lubricant significantly contribute to enhanced performance and extended engine lifespan. However, determining the precise replacement time remains a challenge. Oil spectral analysis, while effective, is both expensive and time-intensive. This study aims to introduce an alternative method to engine lubricant spectral analysis. The investigation involves analyzing the results of spectral analysis and dielectric coefficients of 17 engine lubricant samples through statistical methods. The primary objective is to develop models for predicting oil contaminants based on dielectric properties, offering a substitute for spectral analysis. To achieve this, several intermediate goals are pursued. Multilayer perceptron artificial neural networks (MLP-ANN) and support vector machine (SVM) methods are employed for modeling. The performance of the two models is assessed using indicators such as Root Mean Square Error (RMSE), model efficiency, and R-squared (R2). The results indicate that the SVM model consistently demonstrates an efficiency exceeding 0.95 for all predicted indices (Fe, Pb, Cu, Al, Mo, Na, Si, and Vis@100). Consequently, dielectric spectroscopy of lubricant emerges as a viable alternative to traditional oil spectral analysis.
The Dubas bug (Ommatissus lybicus) poses a significant threat to agriculture in the Middle East by weakening palm trees and reducing fruit production. Effective pest control depends on accurate and timely localization of the infestation. However, regular field inspections are difficult and time-consuming, especially for large areas. This research investigates the potential of Sentinel-2 satellite imagery for detecting Dubas bug infestations. The aim is to improve monitoring capabilities, accelerate intervention strategies, and mitigate the associated economic impact. The field trial to assess the infestation occurred in May 2023, coinciding with the peak of the pest outbreak. The severity of the infestation was assessed through pest counts conducted in date palm groves within the urban area of Bam, Iran. Sentinel-2 multispectral images of a specific area were acquired and processed for correction, raw data preparation, and information extraction. The Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) method was used for the atmospheric correction of the acquired images. The Nearest Neighbor Interpolation method was used to resample satellite images, standardizing all bands to a uniform 10-meter resolution. Following the pre-processing phase, the KD-tree-based K-Nearest Neighbor classifier model was selected to develop a model specifically designed for identifying areas infested by the Dubas bug. For training, 70% of the measured field data were used, including uninfested areas and areas with three levels of infestation from light to heavy, as well as other land features such as buildings, roads, etc. The remaining 30% of the data was utilized to evaluate the trained model, using the correct prediction rate as the assessment criterion. The trained classifier, validated against the ground truth data, achieved an accuracy of approximately 83% on the test dataset. This accuracy highlights the ability of Sentinel-2 multispectral imagery and machine learning to detect Dubas bug infestations in date palm groves and can facilitate targeted and sustainable pest management strategies.
Pickering emulsion-based edible biodegradable films have emerged as a promising sustainable alternative to conventional food packaging materials. These films exhibit enhanced mechanical properties, including tensile strength, flexibility, and water vapor barrier performance, which are critical for maintaining food integrity throughout storage and transportation. A key advancement in this field is the incorporation of essential oils into the emulsion matrix, which, despite their hydrophobic nature, significantly improve the functional and mechanical properties of polysaccharide-based films. This review examines the physicomechanical properties of polysaccharide-based edible biodegradable films incorporating Pickering emulsions, with a focus on flexibility, tensile strength, water vapor permeability, and moisture retention capacity. Furthermore, it explores the role of these films in extending food shelf life and analyzes how interactions between essential oils and polysaccharides influence their structural and barrier properties. Findings demonstrate that Pickering emulsions containing essential oils substantially enhance the mechanical and moisture barrier performance of edible biodegradable films. Solid stabilizing particles contribute to increased tensile strength, while essential oils improve flexibility—though excessive concentrations may compromise structural integrity. Additionally, these emulsions reduce water absorption and solubility, thereby improving film stability in humid conditions. Finally, this review examines the current challenges and identifies key research opportunities in the development of essential oil-loaded Pickering emulsion systems for polysaccharide-based biodegradable films, while outlining their potential for scalable industrial applications.
Drying is a vital preservation method in the food industry, reducing moisture content while maintaining product quality and extending shelf life. This process involves complex heat and mass transfer mechanisms, necessitating accurate predictive models. This study compares various modeling approaches, including regression models, semi-empirical, and artificial intelligence (AI)-based methods, to simulate the drying process of potato slices. Experimental drying trials were run at 40°C, 50°C, and 60°C, both with and without phase change materials (PCM) and infrared radiation (IR). AI models (ANN, SVM, and RF) were trained and validated using experimental data. Their performance was evaluated against conventional and semi-empirical models using R2, RMSE, MAE, and MBE. Results indicate that ANN achieved the highest predictive accuracy (R2= 0.998, RMSE= 0.0656 g water g-1 dry matter), outperforming other models. SVM also demonstrated strong predictive capability, while RF performed slightly lower. Among semi-empirical models, the Midilli model provided the best fit but was less accurate than AI-based models. These findings highlight the superiority of AI-driven approaches, particularly ANN, in optimizing drying processes for the food industry.
This research aimed to enhance the design and functionality of an integrated enset processing machine by focusing on key components such as the shaft, cylinder drum, breastplate, and drum blade. Existing enset processing machines suffer from inefficiencies due to component wear, mechanical breakdowns, and suboptimal design, leading to operational challenges. To address these issues, targeted design modifications were planned for the machine’s components. The materials for these components were selected according to ASTM standards. The modified components were rigorously analyzed using the Finite Element Method in the Workbench module of ANSYS 2023 R1 software at Adama Science and Technology University, Adama, Ethiopia. The study reported maximum stresses of 120 MPa, 250 MPa, 400 MPa, and 260 MPa, and minimum stresses of 30 MPa, 70 MPa, 120 MPa, and 80 MPa for the shaft, cylinder drum, blade, and breastplate, respectively. Maximum deformations were found to be 0.15 mm, 0.3 mm, 0.55 mm, and 0.35 mm for these components, with a maximum safety factor of 15 for all. These results indicate that the modifications provide safe working conditions. The design ensures that the drum, drum blade, and breastplate possess sufficient rigidity to withstand operational forces, with minimal deformation (2.39×10⁻⁶ mm for the drum blade), remaining within a safety factor limit of 1.25. Additionally, the machine demonstrated excellent energy dissipation and vibrational response, indicating structural robustness.
Agriculture is the most prominent industry in developing countries and also ranks as one of the most dangerous professions. Tractors and grain combine harvesters are two of the main self-propelled agricultural machines. Agricultural machines, despite their irreplaceable role in increasing productivity, contribute significantly to agricultural accidents. This study was conducted to investigate the current rates and severity of accidents and human casualties related to agricultural tractors and grain combine harvesters in Ilam province, Iran. Evaluations were conducted using data from the years 2019-2023.Over these five years, the accident frequency for agricultural combines and tractors was 61 and 43, respectively, indicating a statistically significant difference. Among the tractor drivers in this research, the most frequent accidents occurred due to the power take-off shaft (P.T.O.), helices, and feeding rollers. Among combine drivers, accidents were most common at the shear points of the machine (cutter bars, gears, etc.). This research evaluated the factors affecting field accidents related to tractors and combines and estimated the accident rates. Accident rates, including AFR (Accident Frequency Rate), ASR (Accident Severity Rate), FIR (Fatal Incident Rate), and FSI (Frequent Severity Index), were calculated. The rates of AFR, ASR, FIR, and FSI were 25.84, 45.82, 1.66, and 1.066% for combine harvesters, and 5.60, 12.63, 4.44, and 0.262% for tractor accidents, respectively. The nonfatal rate for combine harvesters was 6445 per 100,000, and for agricultural tractors, it was 4334 per 100,000. Tractor accidents had a higher fatality rate than combine harvesters, with 445 fatalities per 100,000 for tractors compared to 333 per 100,000 for combine harvesters.
In botanical terms, the classification of plants reveals a multitude of species derived from different sources. The first step for quality control of herbal medicines is to identify their different species and genotypes. The present study investigated the classification of ten different mint genotypes using Gas Chromatography-mass Spectrometry (GC-MS) and an electronic nose (e-nose) system utilizing Metal Oxide Semiconductor (MOS) sensors. Leaf samples were harvested from various mint genotypes, and subsequently, the system sensors' responses to each of these samples were recorded. The classification of plants was performed using biplot diagrams based on GC and GC-MS data, with clustering facilitated by the Ward method. The responses of all e-nose sensors were further analysed through various approaches, including Principal Components Analysis (PCA), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Artificial Neural Network (ANN). The results from the qualitative analysis of essential oils via GC-MS demonstrate that more than 99% of the identified compounds belong to four chemical groups: hydrocarbon and oxygenated monoterpenes, as well as hydrocarbon and oxygenated sesquiterpenes. Also, based on biplot analysis, different mint populations could be generally divided into 8 groups. The results of principal component analysis showed that the first two main components can cover a total of 97% of the data variance. The classification accuracy achieved through e-nose data for LDA, QDA, and ANN was 98.9%, 99.9%, and 96%, respectively. Proper classification of mint genotypes by e-nose system could be used as a sensitive, reliable, and low-cost alternative to traditional methods.
Grain harvesting operations account for approximately 25-30% of total direct energy consumption in crop production systems. Developing appropriate blades for harvesting canola (Brassica napus L.) is crucial due to its distinct characteristics compared to other cereal grains. This study investigated the effects of blade angles (placement angles: 30°, 45°, and 60°; sharpness angles: 30°, 45°, and 60°), reciprocating movement speed (800, 1100, and 1400 courses per minute), and moisture levels (19%, 22%, and 24%) on reducing force, shear stress, and energy consumption during canola harvesting. Results showed that a blade sharpness angle of 30° yielded the lowest shear stress (0.175 N mm-2) compared to 60° (0.303 N mm-2). The 45° blade placement angle demonstrated minimum shear stress (0.177 N mm-2) versus 60° (0.320 N mm-2). Increasing moisture content from 19% to 24% reduced shear stress from 0.256 N mm-2 to 0.200 N mm-2. The highest reciprocating speed (1400 courses per minute) resulted in the lowest shear stress (0.167 N mm-2) compared to 800 courses per minute (0.286 N mm-2). Life cycle assessment revealed that varying blade placement angles (30° to 60°) could increase marine aquatic ecotoxicity by up to 55,762.55 kg dichlorobenzene equivalent, while changes in blade sharpness angles and reciprocating speed could lead to increases of 377,429.87 kg and 143,185.69 kg dichlorobenzene equivalent, respectively. The optimal configuration—comprising a sharpness angle of 30°, a placement angle of 45°, a moisture content of 24%, and a reciprocating speed of 1400 courses per minute—significantly reduced both shear energy and environmental impact.
In this research, the amount of vitamin C, aromatic compounds, and color change of orange powder was measured using chemical methods, an olfactory machine, and a scanner in four dryers at 45℃. These dryer apparatuses included normal atmospheric vacuum, atmospheric control vacuum, convective, and convective-infrared. The highest response of sensors to aromatic compounds in convective and lowest response in control vacuum and normal vacuum dryers was observed. The two main components of principal component analysis (PCA) explained 88% of the data variance. The structure of the artificial neural network (ANN) was 8-5-4. Further, based on loading diagrams of partial least squares (PLS) and principal component regression (PCR) models, the MQ3 and MQ6 sensors were the best to predict the amount of vitamin C and the color change of orange powder. MQ135 sensor can also be removed from the set of electronic nose sensors due to their low accuracy and cost reduction. The multiple linear regression (MLR), compared to PCR and PLS models, proved to be more accurate (i.e., R2= 0.83 and RMSE= 0.144 for vitamin C prediction and R2= 0.94 and RMSE= 0.68 for predicting color change). The highest and lowest values of measured color change was observed in convective dryer and atmospheric control vacuum dryer, respectively. Also, the highest and lowest measured vitamin C was observed in convective-infrared dryer and atmospheric control vacuum dryer, respectively. The best dryer to maintain the quality of the orange powder is the convective-infrared dryer. The results of this article showed that the data obtained from the olfactory machine is able to predict the color change and vitamin C of orange powder. Also, the olfactory machine can be used to identify and classify the type of dryer used to prepare orange powders with the least time and cost, without distorting the sample, and to determine the best dryer for preparing orange powder.
Smallholder maize production in sub-Saharan Africa, crucial for regional food security, grapples with persistent yield gaps driven by labor-intensive planting practices and a critical lack of mechanization specifically designed to accommodate the traits of native plant varieties. This study characterizes three maize varieties (CML-539, Melkassa 3, and Melkassa 6Q) to develop design parameters for adaptive multi-crop planters. Geometric properties including length, width, and thickness were measured using digital calipers, with 100 seeds per variety. Analysis was performed for elongation, geometric and arithmetic mean diameters, surface area, projected area, transverse cross-sectional area, sphericity, flakiness ratio, aspect ratio, shape index, and roundness. Gravimetric properties including bulk and true densities, porosity, thousand seed mass, and angle of repose were systematically analyzed to optimize seed-handling mechanisms in planter design. Physical property analysis revealed distinct varietal requirements: CML-539's irregular morphology (9.42 mm length, 49.30% porosity) necessitates vibration-assisted metering and aerated delivery systems; Melkassa 6Q's uniform properties (71.11± 6.66% sphericity, 811.62 kg m-3 bulk density) permit gravity-fed mechanisms; and Melkassa 3's intermediate characteristics of > 2.3 elongation ratio and 19.31% density variation require adjustable furrow openers of 25-30° rake angles. Geometric variability necessitates the implementation of adaptive solutions, such as curved seed tubes and adjustable furrow openers, to effectively prevent tilt and bridging. The resulting modular planter system, incorporating moisture-responsive metering, adaptive cell sizing, and aerated delivery, aligns with Ethiopia’s agroecological standards of 75 cm row spacing and depth range of 4 to 7 centimeters. This framework offers a scalable, sustainable model for precision smallholder mechanization, transferable to global maize systems.
Introduction One of the most important parts of agricultural operations is tillage, which accounts for about 60% of the total energy consumed. Therefore, reducing tillage energy demand by lowering the number of passes through the development of cost-effective machinery is highly essential in modern farming. One of the main implements that helps farmers achieve this is the disc harrow. As the most important secondary tillage tool, the disc harrow improves soil structure, breaks up clods, and increases the penetration of water and air into the soil. However, its optimal performance is influenced by parameters such as disc diameter, disc edge type (toothed or plain), disc gang angle, and tractor forward speed. Soil bins, as controlled environments for testing tillage tools, serve as an ideal alternative to agricultural lands. They allow accurate simulation of field conditions while minimizing the effects of climate change and variable soil properties. Materials and Methods The present study was conducted with the aim of designing, constructing, and evaluating a disc harrow carrier chassis in the controlled environment of a laboratory soil bin. First, the design phase was carried out using SolidWorks 2020 software, followed by an analysis of the design performance under maximum load using the von Mises method. The next step was the construction of the design. After construction, the evaluation phase was performed by examining the effects of four independent input variables: forward speed (6.43 and 13.15 m min-1), soil moisture content (2.37 and 13.25 percent on a wet basis), disc edge type (plain or toothed), and disc gang angle (0, 15, and 30 degrees), on the dependent output variable, draft force. Each test was replicated three times, resulting in a total of 72 tests. Results and Discussion The results showed that the engineered chassis exhibited sufficient strength during the initial evaluation tests, with all components performing well. The findings indicated that increasing forward speed and disc gang angle led to higher draft force, while higher soil moisture levels reduced draft force. Under low moisture conditions, plain discs generated greater draft force; however, this trend reversed as moisture increased. The highest draft requirement (3.588 N) was observed for plain discs at 2.37% moisture, while the lowest (1.724 N) occurred at 13.25% moisture. At a forward speed of 6.43 m min-1, plain and toothed discs required equal draft, but at 13.15 m min-1, the toothed discs required substantially more draft. Conclusion The experiments showed that there was no significant difference in draft force between disc gang angles of 0 and 15 degrees. However, increasing the angle from 15 to 30 degrees caused a significant rise in draft force. This indicates that the initial increase in gang angle has a smaller effect, but beyond 15 degrees the impact becomes more pronounced. Therefore, selecting an appropriate disc gang angle can help reduce fuel consumption and improve the productivity of agricultural machinery. Both increasing disc gang angle and forward speed raise draft force because soil resistance to disc movement increases. At higher speeds, the disc must exert more force to cut and move the soil, leading to higher energy consumption and greater equipment wear. Conversely, at lower speeds, draft force decreases, but tillage efficiency may be reduced and plowing uniformity may be affected.
IntroductionRemote sensing is considered a key management tool in precision agriculture, particularly for monitoring and identifying plant coverage. Grapes are among the most valuable horticultural crops, with Hamedan province accounting for approximately 7.3 % of Iran's total vineyard area. This study evaluates the accuracy of vineyard identification in Hamedan province using machine learning algorithms including support vector machine (SVM), minimum distance (MD), and random forest (RF) models along with normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) estimated from combined optical and radar images of Sentinel (Sentinel-1 and Sentinel-2). Based on the most accurate vineyard identification map, the maximum time series of NDVI and NDWI of the MODIS satellite in vineyards was estimated between 2007 and 2020, and their correlation with the actual yield of the grape crop was examined.Materials and MethodsIn this research, we first extracted images of pivotal remote sensing vegetation indicators, including NDVI and NDWI, from Sentinel-2 images in Hamedan province in 2020. The approach of addressing speckle noise through median pixels allowed for the acquisition of median radar images from Sentinel-1 over the designated study area. To create high-accurate images, spectral composition was used to combine these images with the NDVI and NDWI from Sentinel-2 images. Using these images, vineyard identification maps were generated through classification algorithms, including support vector machine, random forest, and minimum distance models. Training samples were used to train these algorithms. Samples from six land coverage classes involving vineyards, were collected using a combination of field observations and Google Earth imagery. Of these, 70% were used for training and 30% for testing the classification models. In order to assess the accuracy of the vineyard identification maps, indicators including overall accuracy and kappa coefficient were examined. Subsequently, the vineyard map with the highest assessment indicator was selected. Finally, using this accurate vineyard identification map, the maximum monthly NDVI and NDWI indices estimated from MODIS sensor images in the vineyards were calculated from 2007 to 2020, and their correlation with yields of the grape crop was computed using Pearson correlation.Results and DiscussionBased on the comparison of different classification algorithms for distinguishing vineyards, random forest model along with NDVI and NDWI indices outperformed support vector machine and minimum distance models. With regard to accuracy, however, the random forest along with the NDWI has the best overall accuracy (95%) and kappa coefficient (0.95). The superior performance of NDWI is attributed to the high moisture levels in vineyards resulting from irrigation, as NDWI is particularly sensitive to variations in vegetation water content. The lower accuracy of vineyard identification using SVM and MD models can be linked to shadow effects caused by the canopy structure of grapevines, as well as imbalanced training data used for the support vector machine model. Correlation analysis of real grape yields with NDVI and NDWI of MODIS extracted from the highest accuracy vineyards map indicates NDVI (correlation coefficient 0.81) has a stronger linear relationship with yield than NDWI (correlation coefficient 0.75). This can be explained by NDVI's sensitivity to leaf chlorophyll changes, which results in a strong correlation with yield.ConclusionVineyards can be accurately identified using machine learning algorithms and remote sensing vegetation indices derived from combined radar and optical satellite images. Furthermore, the strong correlation between NDVI and grape yield enable reliable yield prediction based on NDVI time series analysis. The outcomes of this study facilitate the identification of grape cultivation areas, improved water resourse management, the development of optimized irrigation strategies, pre-harvest yield estimation, and the exploration of export options.
IntroductionPlanting rice seedlings in the main field followed by periodic or intermittent irrigation is often considered a form of dry farming. Research suggests that flood irrigation in rice cultivation is primarily favored by farmers for its ability to control weeds and ensure a reliable water supply, rather than necessarily enhancing rice quality or yield. Depending on the rice variety, intermittent irrigation can sometimes improve both the quality and yield per unit area. The transplanting process in this method can be carried out manually without machinery or through mechanized methods using a planter.Materials and MethodsConventional rice transplanters designed for use in flooded land are not suitable for transplanting in dry land farming due to technical constraints. Therefore, it is necessary to develop a specialized rice transplanter tailored for such soil condition. This transplanter encompasses essential components, including a furrow opener, coverer, seedling storage tank or tray, seedling mechanism (distributor), seedling transfer mechanism (seedling transport piston), end separator for seedlings in the soil, power transmission system, depth adjustment shoe, and main and sub chassis. To evaluate the planter's performance, various parameters were assessed, including the percentage of lost plants, the average vertical angle of plant orientation, the average spacing between plants in the crop row, and the average number of seedlings per plant. Moreover, a factorial randomized block design was employed, with three replications for each level of the independent variables. The independent variables were forward speed (X1) at three levels of 0.25, 0.5, and 1 m s-1, planting depth (X2) at three levels of 4, 8, and 12 cm, and the size of the outlet opening of the seedling tray (X3) in three levels of 10, 15, and 20 mm.Results and DiscussionThe developed single-row planter features key specifications, including a working width of 250 mm, a power requirement of 0.57 kW, a theoretical field capacity of 0.06 ha h-1, and a field efficiency of 66.67%. The research findings revealed that forward speed, planting depth, and outlet opening size, along with their interactions, significantly impact the percentage of lost plants at the 99% confidence level. Among the three levels of forward speed (X1), the best speed level is 0.25 m s-1, as it results in the lowest percentage of lost seedlings. As the forward speed increases, the percentage of lost seedlings increases. The lowest percentage of lost plants (Y1) occurs at the planting depth of 8 cm and an outlet opening size of 20 mm. Furthermore, forward speed, planting depth, and their interaction have a noteworthy influence on the vertical angle of plants are established, at the 99% confidence level. With the increase of forward speed and planting depth, the average vertical angle of seedling establishment deviates from the vertical position. The forward speed of 0.25 meters per second and the planting depth of 8 cm show the best results for the establishment of seedlings. The sole factor affecting the spacing between plants in the row is the forward speed. The size of seedling tray’s outlet opening significantly affects the number of seedlings per plant at the 99% confidence level, while planting depth affects it at the 95% confidence level.ConclusionGiven the recent water crisis, adopting the dry rice farming method and using transplanters offers a viable solution for managing and conserving water in agriculture. Implementing dry planting with a custom-made transplanter yields several benefits, including reduced water consumption, lower cultivation costs, improved soil aeration, increased efficiency, and simplified planting processes. Utilizing this transplanter is an effective strategy to decrease both the time and expenses related to transplanting, while also mechanizing rice planting in dry fields.
IntroductionThe increasing demand for automation in agriculture, particularly for repetitive and labor-intensive tasks, has driven the development of robotic harvesting systems. Recent advances in computer vision, deep learning, and the availability of large image datasets have made it possible to create robust object detection models for agricultural applications. Traditional harvesting methods, such as bulk harvesting, often lead to fruit damage and loss owing to non-selective picking. Selective harvesting, particularly with the use of robotic systems, offers a promising alternative by combining the precision of human labor with the efficiency of automation. This study presents a deep learning-based model for detecting cucumber fruits on plants in a real greenhouse environment, which is an essential step towards developing autonomous harvesting robots that selectively pick ripe cucumbers.Materials and MethodsA dedicated image dataset was curated in a commercial greenhouse, comprising 300 images of cucumber plants captured under various lighting conditions (morning, noon, and evening), to ensure robustness against real-world variability. Images were manually labeled to identify the cucumber fruits and their pedicels. To enhance the model training and prevent overfitting, data augmentation techniques were applied to the training set. Several architectures of the YOLO (You Only Look Once) object detection algorithm were evaluated, including the nano-scale versions YOLOv5n and YOLOv8n, and the small-scale YOLOv8s, in addition to the RT-DETR model.The YOLOv8 algorithm is known as one of the state-of-the-art algorithms in computer vision because of its high speed, detection accuracy, and adaptability. The YOLOv8 architecture consists of three main parts: backbone, neck, and head, which are responsible for extracting image features, combining and enriching features, and predicting bounding boxes and object classes, respectively.These models were trained, and their performances were compared based on the detection accuracy and inference time metrics. Training and evaluation were conducted using a suitable computational platform.Results and DiscussionThe performances of different YOLO models and RT-DETR were rigorously evaluated. The results demonstrated that the YOLOv8n model achieved the highest detection accuracy of 87.5%, surpassing the performances of the other tested models. Importantly, the YOLOv8n model also exhibited a favorable balance between the accuracy and inference time, making it suitable for real-time applications. The analysis considered the trade-off between the number of parameters and detection speed, highlighting the efficiency of YOLOv8n.The YOLOv8n model demonstrated superior performance in terms of pedicel detection accuracy compared to YOLOv5n, achieving a fitness score of 91.08% (calculated as a weighted average of mAP@50 and mAP@50-95). While exhibiting strong performance in fruit and pedicel detection (Figure 6), the sensitivity of the model for pedicel detection (88.0%) was comparatively lower than that for fruit detection (96.1%). The highest F1 score (0.89) was observed at a confidence level of 39.5%, indicating the effectiveness of the model in balancing the precision and recall for pedicel detection. Overall, YOLOv8n outperformed the other tested models in identifying the class and location of the fruit pedicel. The superior performance of YOLOv8n can be attributed to its architectural advancements and optimized training processes.ConclusionThis study successfully developed a deep learning-based model for accurate and efficient cucumber fruit detection in a greenhouse environment. The YOLOv8n model demonstrated superior performance compared with the other evaluated architectures, achieving a detection accuracy of 87.5% while maintaining a good processing speed. These findings suggest that the YOLOv8n model has significant potential for integration into autonomous vegetable harvesting robots, contributing to the automation of agricultural processes and increased efficiency in greenhouse operations. Future works should explore further optimization and testing under diverse environmental conditions.
Introduction Tillage of rainfed lands is performed using moldboard plows to a depth of 30 cm. Due to the influence of soil surface roughness and crop residues on moisture absorption and erosion reduction, investigation of the relationship between tillage implements' performance and the aforementioned factors is essential. Therefore, considering the importance of preserving precipitation and preventing soil erosion, this study was conducted to investigate and optimize the effects of forward speed and tillage depth on soil surface roughness and the percentage of buried crop residue using response surface methodology. Materials and Methods This research was conducted in the Khomeyn region, Iran during the 2023-2024 growing season, utilizing a moldboard plow and an MF399 tractor. The objective was to investigate the effects of plowing depth and speed on soil surface roughness and the burial of plant residues. Soil surface roughness was measured using a pin meter, while the percentage of burial of plant residues was determined using image processing techniques and ImageJ software. Wheat straw residue with an initial moisture content of 8-9% was uniformly distributed at a rate of 100 g m-2 along the designated paths. Images were captured before and after the tillage operation for subsequent processing and analysis. To optimize the process, a central composite design (CCD) with three levels of speed (5, 7.5, and 10 km h-1) and three levels of tillage depth (17.5, 22.5, and 27.5 cm) was employed. The objective was to determine the optimal factor levels for maximizing surface roughness and minimizing residue burial. Data were analyzed using a second-order model and Design Expert V11 software. The best model was selected based on statistical criteria. Results and Discussion Modeling soil surface roughness and crop residue incorporation revealed that the second-order regression model, with high coefficients of determination (R2 = 0.983 and 0.96), was capable of accurately predicting these indices. The interaction effects of tillage speed and depth were significant (P < 0.01). In this study, the effect of tillage depth on soil surface roughness was greater than that of tractor speed. The regression model indicated that tillage depth plays a primary role in the amount of crop residue incorporation. Moldboard plowing demonstrated that increasing depth, particularly at high speeds, leads to increased roughness and residue incorporation, whereas increasing speed, especially at shallow depths, reduces roughness and increases incorporation. The maximum roughness was observed at the deepest tillage depth and lowest speed, while the shallowest depth and highest speed resulted in the minimum roughness. Tillage depth and speed influence soil surface roughness and bulk density. Higher speeds decrease furrow depth and ridge height; thus, lower speeds are recommended for creating greater roughness. The highest residue incorporation (85%) was achieved at a depth of 27.5 cm and speeds of 5 and 10 km h-1, while the lowest (70%) occurred at a depth of 17.5 cm and a speed of 5 km h-1. Depth was more influential than speed, and nonlinear models are necessary for more accurate modeling. The developed model, with a desirability of 81%, provides the maximum roughness (10.96 cm) and minimum residue incorporation (69.34%) for a moldboard plow at a speed of 5 km h-1 and a tillage depth of 17.5 cm. Conclusion This study investigated the effects of conventional tillage methods in dry land areas on soil surface roughness and the extent of crop residue burial. The results indicate that increasing tillage depth leads to an increase in both indices, while reducing tractor speed increases roughness and decreases residue burial. The optimization model revealed that at a speed of 5 km h-1 and a depth of 17.5 cm, minimum roughness and maximum residue incorporation can be achieved. To improve regional tillage practices, it is advised to conduct further research into the long-term effects of different tillage systems. This effort will ensure a well-informed selection and implementation of the most effective methods.
IntroductionGlobal challenges threaten food security. In Iran, rice is a staple, with 770,000 ha under cultivation and an annual production of 3.75 million tonnes. The northen provinces of Guilan and Mazandaran dominant rice production, with Guilan only supplying about 50% of the nation’s demand. Advanced computational techniques such as metaheuristic algorithms and artificial intelligence offer powerful tools for problem-solving and modeling inspired by the adaptability of living organisms', and are increasingly applied to support agricultural management and sustainability. However, multi-gene genetic programming (MGP) has not yet been used for rice yield modeling in Iran. This study addresses that gap by evaluating the effectiveness of MGP and exploring its potential to enhance agricultural decision-making.Materials and MethodsThis research examines the yield performance of local rice cultivars, namely Hashemi and Ali Kazemi alongside high-yielding cultivars, including Fajr and Shiroudi in Rasht County, Iran. It utilizes library documents, face-to-face interviews, and MGP analysis. Data were collected from 385 randomly selected farmers and landowners in the region, during the 2020-2024 rice production years. Inputs from the energy sector, including fuel and electricity, water pumping equipment, agricultural machinery, fertilizers, pesticides, organic materials, and the energy output of paddy production, were examined. Energy equivalents were used to convert various types of energy into a common unit. To predict the yield of the two types of paddy cultivars using MGP, the structure of MGP trees was first designed with two objectives: maintaining the model accuracy and avoiding structural complexity. Parameter setting include population, generation and tournament sizes, gene limits, tree depth and size, and probabilities for elitism, crossover, and mutation. Additionally, various mathematical functions were utilized.Results and DiscussionIn examining total energy consumption and production in local and high-yielding cultivar farms, the results indicated a significant difference between the two varieties. In farms producing local varieties, the average energy consumption was 41,081.4 MJ, while the average energy production in these farms reached 23,771.9 MJ. In contrast, the average energy consumption in high-yielding cultivar farms was estimated at 41,118.8 MJ, whereas the average energy production in these farms was 42,220.04 MJ. The energy ratio, energy productivity, and specific energy indices for high-yielding varieties were 76.47%, 76.92%, and 77.70% higher, respectively, compared to local varieties, with the net energy gain index showing an improvement of more than 15 times. The higher energy ratio and energy productivity, along with lower specific energy and net energy gain, indicate that the high-yielding cultivar is more energy-efficient in terms of energy consumption. The MGP model converged after 100 iterations, providing the optimal solution. Changes in the best and mean fitness values indicated that as the iterations increased, the error gradually decreased and eventually stabilized, reflecting continuous improvement of the model during the training process and parameter tuning. Through cross-validation with varying training data set sizes, the findings revealed that the MGP model, when utilizing 65% of the total dataset, generated results that were remarkably similar to those achieved with 80% of the data. Hence, 65% is established as the optimal proportion for the training dataset. The coefficient of determination (R2) for the regression line in the training data set was higher than in the test phase for both varieties. In evaluating the MGP equations to assess the accuracy of the proposed model, the tree depth was increased from 4 to 12. For the local cultivar, the highest coefficient of determination (R2) at a tree depth of 4 was 0.95, while for the high-yielding cultivar, it was 0.94. The simpler structure at depth 4 resulted in a simpler mathematical equation. Finally, the effects of independent variables on the dependent variable, paddy yield, were examined. It was found that organic materials, such as compost, seed, rice straw and husks, were the most significant factors influencing the estimation of paddy yield in both varieties.ConclusionSince modeling focuses on predicting crop yield and making data-driven scientific and practical decisions, the results of this study represent an important step toward advancing sustainable agriculture. It is recommended that farmers seek up to date insights from consultants and participate in workshops to increase their sustainable yields.
Seaweeds are well known for their technological, nutritional, and health values, and their preservation by drying is essential to stabilize and maintain the quality of the product during storage. The research presents the obtaining of mathematical models in polynomial functions using the response surface methodology. The influence of the independent drying variables was studied: load density (1.70-15 kg m-2), incandescent lamp wattage (0-500 W), temperature (30-70 degrees C) and air velocity (0.5-2.5 m s-1) on the response variables: global acceptance (--), total phenolic content (mg GAC/100 gdb) and drying time (min). The study also showed that the conditions of temperature and incandescent lamp wattage during drying significantly affected the total phenolic content. The optimum conditions were: load density 9.13 kg m-2, incandescent lamp wattage 374.5 W, temperature and drying air velocity of 63.3 degrees C and 1.88 m s-1, respectively. The results show that increasing the power of the incandescent lamps leads to a shorter drying time of approximately 40-45%. For these optimized conditions, mathematical models were applied to simulate the drying curve and kinetics of the material studied. Using the Quasi-Newton Simplex method, the models of Midilli et al. and Page in second place, achieved a better performance in the quality of fit of the curves to the experimental data. Under these conditions, the value of the effective diffusivity of water was of the order of 2.03x10-11 m2 s-1, a value very similar to those published for agro-industrial products. The information obtained can be of great help in the use of the obtained parameters and applied techniques for the development of equipment and process control in the drying of red seaweed.
This study investigated the effects of walnut oil incorporation on the physicomechanical and structural properties of sodium carboxymethyl cellulose-based edible films, with a focus on two methods of oil addition: bilayer and composite configurations. For this purpose, firstly walnut oil Pickering emulsion (10% oil) was stabilized using chia seed gum, which was then incorporated into the formulation of bilayer and composite films. SEM revealed that bilayer film exhibited a more cohesive and homogeneous structure compared to the composite film. XRD analysis indicated a semi-crystalline amorphous structure across all films, with bilayer film displaying slightly sharper peaks than composite film. Moisture content and solubility tests highlighted the hydrophobic influence of walnut oil, with bilayer films exhibiting the lowest moisture content and solubility due to their surface-localized oil layer. Thermal analysis using DSC and TGA demonstrated improved thermal stability and reduced weight loss in bilayer film. Mechanical tests showed that the bilayer film had the highest elongation at break (34.3%) and the lowest tensile strength (3.4 MPa). Color analysis revealed significant changes in chromatic indices, with composite films showing higher saturation and total color difference. These findings underscore the potential of walnut oil emulsion stabilized with chia seed gum, particularly in bilayer configurations, to enhance the functional properties of sodium carboxymethyl cellulose-based films.
