Journal of Agricultural Machinery

Abstract Non-chemical treatments are an approach for improving seed germination. In order to evaluate the effects of the magnetic field application on onion seed germination and seedling growth indices, a quadrupole magnetic field system was designed and fabricated. It was also compared with a dipole magnetic field system. In the quadrupole system, each coil consisted of three layers and the cores were moved inside the coils. These arrangements make it possible to change the magnetic field intensity in addition to input current setting. The experiments were conducted based on factors including the type of system (bipolar and quadrupole), magnetic flux density (75, 150, 300 and 600 μT) and duration of the field application (15, 30, 60 and 120 min). Germination percentage, germination rate, mean germination time, seedling vigor index, shoot length, root length, fresh weight of shoot and root, fresh weight of seedling, dry weight of shoot and root were measured. The results showed significant effects on seed germination and seedling growth of onion. In most germination characteristics, the quadrupole system had a better impact than the bipolar system. For many traits (except for weights), the increase in field intensity degraded the traits. Quadrupole system that applied the magnetic field of 600 μT for 15 minutes, yielded 63% increase in the total seedling weight. Most of the germination traits were not affected by exposure time. Further investigations are required for shorter exposure times compared to used durations in this study.

Abstract Repetitive and dangerous tasks such as harvesting and spraying have made robots usable in the greenhouses. The mechanical structure and navigation algorithm are two important parameters in the design and fabrication of mobile greenhouse robots. In this study, a four- wheel differential steering mobile robot was designed and constructed to act as a greenhouse robot. Then, the navigation of the robot at different levels and actual greenhouses was evaluated. The robot navigation algorithm was based on the path learning, so that the route was stored in the robot memory using a remote control based on the pulses transmitted from the wheels encoders; then, the robot automatically traversed the path. Robot navigation accuracy was tested at different surfaces (ceramics, concrete, dense soil and loose soil) in a straight path 20 meters long and a square path, 4×4 m. Then, robot navigation accuracy was investigated in a greenhouse. Robot movement deviation value was calculated using root mean square error (RMSE) and standard deviation (SD). The results showed that the RMSE of deviation of autonomous method from manual control method in the straight path to the length of 20 meters in ceramic, concrete, dense  soil and loose soil were 4.3, 2.8, 4.6 and 8 cm, and in the 4×4 m square route were 6.6, 5.5, 13.1 and 47.1 cm, respectively.

Abstract All over the world, farmers choose different implements for tillage, which depend on crop type, soil type, the amount of plant residue from the previous crop, etc. Tillage implement selection is also affected by the availability of implements, power consumption, labor costs, and fund. In this research, the draft force, soil disturbance area, soil cone index, and fuel consumption were considered. The effects of rake angle, forward speed, and soil moisture content on the above-mentioned parameters were investigated. In this research, a comparison between the performance of a Fiber Reinforced Polymer (FRP) composite blade and a conventional steel blade was carried out. Tests were based on the split-split plot in a completely randomized design. The factors of soil moisture content, rake angle, and forward speed were included in three levels. Three levels for the soil moisture content (9.3, 13, 16.7 %), rake angle (20°, 30°, 40°), and forward speed (3, 5, 7 km.h^-1), were considered. The FRP composite blade (on average in the desired range for variables) has reduced the draft force, fuel consumption, and soil cone index, 14.97%, 16.63%, and 35.08%, respectively, than the steel blade. Also, the soil disturbance area created by the FRP composite blade was 4.93% higher than the steel blade. Based on the results of this study, it is clear that the FRP composite blade has better performance rather than the conventional steel blade for the aforementioned test variables. The FRP composite is inexpensive than the steel, this leads to remarkable save money in the production of the FRP composite blade used in the chisel and combined tillage tools that is economical for the farmer and manufacturer.

Abstract In this study a mathematical analysis for estimating the performance rate "RP" of wheel type trenching machine was studied. The mathematical analysis quantifies the analysis and resulted in an equation. This mathematical equation was checked under different operating conditions. The practical study of the performance rate showed that the deviation of the theoretical performance rate from the actual performance rate ranged from 5 to 7% for the 60.4 and 90.5 cm trench depth, respectively. The machine field efficiency also ranged between 43 and 50.1% for 90.5 cm and 60.4 cm trench depth respectively.

Abstract The present study investigated the use of the cyclic voltammetric electrochemical method and the electronic tongue (e-tongue) method for detecting adulteration in lime juice. Since the measurement of citric acid content in lime juice is an accepted indicator of lime juice adulteration in laboratories, at first, attempts were made to determine its concentration using a potentiostat device and the cyclic voltammetry method, which involved various electrodes including glassy carbon, graphite, gold, and carbon nanotube and gold nanoparticle-modified glassy carbon electrodes. Different conditions were considered by testing citric acid at multiple concentrations in buffers with different pH levels. The results showed that the electrochemical behavior of citric acid was weak, so conventional electrochemical methods could not be used to check its behavior. In the second part, a portable electronic tongue system (e-tongue) was evaluated. Eight samples of adulteration levels (from 5% up to 95%) were created in lemon juice (0, 5, 10, 20, 40, 70, 95, and 100% impurity). Unsupervised models including Principal Component Analysis (PCA) and Hierarchical Clustering Analysis (HCA), and supervised models including Multilayer Perceptron (MLP) neural networks and Support Vector Machine (SVM) were used. Based on the results, the PCA fingerprint showed good discrimination between different levels of adulteration, and HCA further confirmed this. The results of the analysis of supervised methods showed that the MLP model outperformed the SVM model in predicting fraud levels with a success rate of 99.33% and high correlation coefficients (R² = 0.9973, RMSE = 0.09). These results show that the proposed system can separate different levels of adulteration in lemon juice and can be used as a taste quality control system.

Abstract Manually picking the flowers of the Damask rose is significantly challenging due to the numerous thorns on its stems. Consequently, the accurate detection of bloomed Damask roses in open fields is crucial for designing a robot capable of automating the harvesting process. Considering the high speed and precise capabilities of deep convolutional neural networks (DCNN), the objective of this study is to investigate the effectiveness of the optimized YOLOv8s model in detecting bloomed Damask roses. To assess the impact of the YOLO model size on network performance, the precision and detection speed of other YOLO network versions, including v5s and v6s, were also examined. Images of Damask roses were taken under two lighting conditions: normal light conditions (from civil twilight to sunrise) and intense light conditions (from sunrise to 10 AM). The outcomes demonstrated that YOLOv8s exhibited the highest performance, with a mean average precision (mAP50) of 98% and a detection speed of 243.9 fps. This outperformed the mAP50 and detection speed of YOLOv5s and YOLOv6s networks by margins of 0.3%, 6.1%, 169.3 fps and 198.6 fps, respectively. Experimental results show that YOLOv8s performs better on images taken in normal lighting than on those taken in intense lighting. A decline of 5.2% in mAP50 and 2.4% in detection speed signifies the adverse influence of intense ambient light on the model's effectiveness. This research indicates that the real-time detector YOLOv8s provides a feasible solution for the identification of Damask rose and provides guidance for the detection of other similar plants.

Abstract The aim of this study is to design, fabricate and evaluate a new type of up-cut rotary tiller and to develop correct formulas to estimate its torque and draft force using the laws of classical mechanics. In order to verify the model, a real-sized prototype of the rotary tiller was tested. It was hypothesized that four processes are involved to create the rotary tiller torque, namely soil cutting, soil lifting, soil-metal friction, and soil velocity. Furthermore, it was assumed that the horizontal components of soil cutting and soil-metal friction forces create the required draft of the machine. Based on these hypothesizes, mathematical formulas were developed to calculate torque, and draft requirements of the machine. To facilitate performing necessary calculations, the developed formulas were entered in a worksheet of the MS Excel software. According to the results of this study, the average experimental draft and torque of the machine tilling a silty clay loam soil were 16.8 N and 12.8 Nm, respectively. Furthermore, the average theoretical draft and torque of the machine were 13 N and 11.8 Nm respectively. These promising results can be considered as the accuracy check of the formulas developed herein.

Abstract The present study aimed to examine the application of accurate and principle-based evaluation of a measuring instrument called the Form Tester in determining and detecting the wear phenomenon in the cylinder liner of agricultural tractors. For this purpose, a cylinder liner of the Perkins 4-248 engine (related to the Massey Ferguson 285 tractor) was manufactured by Keyhan Sanat Ghaem Company was used. The geometric parameters that were measured in this research included roundness, straightness, and concentricity of the cylinder liner. The evaluations on roundness and concentricity of cylinder liner were conducted in 12 circular positions with the same longitudinal distances. The straightness was measured in five lines with the same longitudinal distances in 90° around the cylinder liner environment. The results of the measurements were discussed and analyzed to evaluate the engine status along the functional path of the piston within the cylinder liner. The degree of deviation rate of the parameters indicated significant wear within the cylindrical liner. The wear rate in cross-sections at high and low dead points was significantly greater than that of the same cross-section in the vicinity of the midpoint of the piston movement path inside the cylinder, as well as the cross-sections near the high dead point. The results of this research provide feedbacks for engine designers to apply various changes to the engine and for maintenance and repair engineers to ensure the correct implementation as well as preventive and predictive repair and maintenance strategies.

Abstract In this study, a model was developed for predicting the seeding rate of corn seeds of a typical row-crop planter equipped with a multi-slot feeding device. To this, nine multi-slot rotors (with 4, 5 and 6 slots in three angles of mouth including 23°, 25° and 27°) were designed and manufactured. Tests were carried out at four levels of angular velocity of 40, 52, 62 and 78 rpm on grease belt moving at constant speed of 3.5 km h^-1. Tests were completed in three replications. Discharge flow rate was measured and recorded for each treatment. The data were used to develop a model which can be used for predicting the seeding rate under various numbers of slot, mouth angle and rotor angular velocity. According to the results, angle mouth of slots, number of slots, angular velocity and the dual interaction between them showed increasing effects on weight flow rate of seeds (P-value<0.01). In the next step, raw data were used to develop the two desired models: based on the dimensional analysis technique and response surface methodology (RSM). The models outputs were compared to experimental data. The standard error of estimate for flow rate for dimensional analysis and response surface methodology (RSM) were 68.13 mm³ s^-1 and 475.59 mm³ s^-1, respectively. The dimensional analysis model was closer to experimental data rather than the RSM method. Thus, to predict the volume flow rate of seed, the dimensional analysis model is recommended.

Abstract Despite the development of dairy farm mechanization, milking operations are still associated with heavy workloads which result in human physiological strains. This study investigated the role of gravity force in the linkage between load carriage and workers’ physiological strains in milking work tasks of two major cow milking systems (milking in stanchion barns and tandem parlors). These two milking methods similarly included washing the teats, attaching the cluster, and detaching the cluster. Human energy expenditure (EE) was calculated and load carriage direction in comparison with gravity (LCG) was tracked among twenty-four male workers. The highest heart rate (107 beats min^-1) and EE (35.5 kJ min^-1) were reported for attaching the cluster in the tandem parlor milking method. Tandem parlor milking caused higher human physiological strains and higher proportions of converse LCG compared with stanchion barn milking. By developing dairy farm mechanization from stanchion barn to tandem parlor, cow milking workers are induced to apply higher forces including converse LCG causing higher human physiological strains. Mechanization of dairy farms should be developed not only for improving the rate of work and performance but also for making conditions toward a reduction in the use of human physical forces.

Abstract Correct and timely diagnosis of plant diseases is crucial for improving crop performance. Therefore, developing a precise and reliable intelligent system for managing leaf diseases in trees is very important for farmers. This study aims to develop an artificial intelligence-based solution for detecting leaf diseases in quince trees using a state-of-the-art single-stage object detection model, YOLO (You Only Look Once). Images of diverse leaf diseases affecting this tree were collected from multiple sources, including agricultural research centers in Isfahan Province, Iran, relevant websites, and researchers. In this study, a transfer learning approach was employed to evaluate three well-known YOLO models (YOLOv5m, YOLOv7, and YOLOv8m) based on their detection and identification performance. Statistical metrics, including precision, recall, F1-score, and accuracy, were used to evaluate and compare the performance of the investigated models. The results indicate that the accuracy of the YOLOv5m, YOLOv7, and YOLOv8m models were 78%, 83%, and 87%, respectively. Experimental results revealed that YOLOv8m, trained from scratch on the dataset, demonstrates substantial capability in identifying leaf diseases in quince trees. In addition, a comparison showed that this model outperformed other investigated models with scores of 0.87, 0.66, 0.69, and 0.67 for accuracy, precision, recall, and F1-score, respectively. Based on the overall results of this research, the YOLOv8m model trained in this study can be introduced as a specialized tool for this particular crop. Therefore, the developed model in this study, specifically tailored to quince leaf diseases, can be integrated into diagnostic software for tree leaf diseases. Such software can assist farmers in accurately diagnosing diseases, ultimately reducing economic losses.

Abstract The efficient use of agricultural machinery significantly improves both the quantity and quality of field operations; therefore, it is essential to optimize operational speed and field time. Factors such as field shape complexities and soil surface roughness (SSR) significantly impact seeding performance. The objective of this research was thus to evaluate how these key factors affect seeder performance: (1) field size and shape, and (2) the interaction of seeder speed and SSR. The performance metrics, effective field capacity (F_eff), efficiency (η), and average working speed (v_a), were analyzed using SAS software. The convexity (I_con) and rectangularity (I_R) indices for each plot were calculated using the ArcGIS minimal bounding geometry Data Management tool, while the elevation standard deviation (σ_e) was computed using Python. The resulting values for F_eff, η, and v_a varied widely, with values ranging from 10.2 to 3.1 ha h^-1, 30% to 65.7%, and 5.2 to 17 km h^-1, respectively. A v_a process capability index (C_pk) of 0.22 indicates a significant challenge in meeting the established limits. As the plot run-length increased, the F_eff also increased (R² = 42%), while it decreased with a rising perimeter to area ratio (P/A) (R² = 51%). Additionally, F_eff exhibited an upward trend as the I_con and I_R indices rose, while it experienced a decline with greater compactness (I_com) and square perimeter (I_sp) indices; albeit these relationships were not statistically significant. Higher roughness levels generally resulted in a decline in η. Furthermore, operating the planter at higher speed on uneven terrain led to a significant decrease in efficiency. Hence, redesigning the plots to minimize border complexities, eliminating topographic abnormalities, and implementing tailored plot-specific pre-sowing procedures, will significantly enhance planter performance.

Abstract In this paper, performance of a no-till corn planter in a soil covered with previous wheat residue was evaluated. Three levels of crop residue cover (CRC): 30, 45 and 60%, two planting schemes; on-bed and in-furrow and two forward speed: (4 and 8 km h-1) were considered as treatments. The field was evaluated by ground and air observations. The purpose of this study was to investigate the capability of aerial images captured by an unmanned aerial vehicle (UAV) in identifying the distances between corn seedlings and as a result, assessing the quality of planter performance. Collected data from ground and aerial imagery were used to calculate seed establishment indices including multiple index, miss index, quality of feed index, precision index and also emergence rate index (ERI), for each plot. Images captured from10 m altitude (4.5 mm pixel-1) could give satisfactory results in relation to our objectives. Our results show that acceptable correlations existed between terrestrial and aerial seedlings spacing data sets (0.94<R<0.98) suggesting the aerial imagery is a good choice for evaluating the seed establishment and estimating ERI. Aerial imagery data source underestimated quality of feed and precision indices, overestimated miss index and could not provide processed data range needed for computing multiple index due to low image resolution, weeds presence within crop rows and overlapping of leaves.

Abstract The main purpose of this study was to provide a method for accurately identifying the position of cucumber fruit in digital images of the greenhouse cucumber plant. After balancing the brightness histogram of the desired image, it multiplies the image with a window containing the image of a cucumber fruit, which causes larger coefficients to be obtained in areas with suspected cucumber. By extracting these local maximums, clusters of initial points are obtained as possible windows of cucumber existence. Then, in order to accurately detect the location of the cucumbers, these points and areas around them are referred to a neural network that has been trained using a number of images including cucumber images, non-cucumber images and their optimal responses. The proposed method was implemented in the Simulink toolbox of MATLAB software. The proposed method was then simulated using this network structure and tested on 120 images obtained from a greenhouse by a digital camera. The areas obtained from this network led to the accurate detection of the location of the cucumbers in the image. The proposed method was then simulated and tested on 120 images. The proposed method had a low error and was able to detect high levels of cucumber fruit in the images. This detection took an average of 5.12 seconds for each image. The accuracy of the network in correctly identifying the position of the cucumber fruit in the images was 95.3%. This method had low error and was able to detect a high rate at a good time of cucumber fruits in discover images.

Abstract Several histogram equalization methods for enhancing the color images of Rosa Damascena flowers and some thresholding methods for segmentation of the flowers were examined. Images were taken outdoors at different times of day and light conditions. A factorial experiment in the form of a Completely Randomized Design with two factors of histogram equalization method at 8 levels and thresholding method at 15 levels, was implemented. Histogram equalization methods included: CHE, BBHE, BHEPL-D, DQHEPL, DSIHE, RMSHE, RSIHE, and no histogram equalization (NHE) as the control. Thresholding method levels were: Huang, Intermodes, Isodata, Li, maximum entropy, mean, minimum, moments, Otsu, percentile, Renyi’s entropy, Shanbhag, Yen, constant, and global basic thresholding method. The effect of these factors on the properties of the segmented images such as the Percentage of Incorrectly Segmented Area (PISA), Percentage of Overlapping Area (POA), Percentage of Undetected Area (PUA), and Percentage of Detected Flowers (PDF) was investigated. Results of histogram equalization analysis showed that DQHEPL and NHE have the statistically significant lowest PUA (11.13% and 8.32%, respectively), highest POA (89.35% and 92.07%, respectively), and highest PDF (61.88% and 64.94%, respectively). Thresholding methods had a significant effect on PISA, PUA, POA, and PDF. The highest PDF belonged to constant, minimum, and Intermodes (75.07%, 73.08% and 74.30%, respectively) They also had the lowest PISA (0.35%, 1.29%, and 1.85%, respectively) and PUA (33.72%, 23.09%, and 15.56%, respectively). These methods had the highest POA (80.73%, 76.70%, and 84.67%, respectively). Hence, they are suitable methods for segmentation of Rosa Damascena flowers in color images.

Abstract The main aim of this study was to optimize the design parameters of the fruit shakers for efficient harvesting of Shengy olive. A single-degree-of-freedom spring-mass model was established to determine the natural frequency and damping coefficient of the limb. A tractor-mounted shaker that transmits vibration to limbs and fruits via a reciprocating mechanism was fabricated for field evaluation of the forced vibration modes. A 3×4 factorial experiment with a completely randomized design was conducted to investigate the effects of shaking amplitudes and frequencies on fruit removal. The shaking mode with a frequency of 10 Hz and amplitude of 80 mm transmitted the average power of 92 W to remove 95% of fruits in the field trial. This oscillation characteristic should be used to redesign the fruit shakers to pass human safety standards and efficient harvesting.

Abstract 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 °C) and air velocity (0.5-2.5 m s^-1) on the response variables: global acceptance (--), total phenolic content (mg GAC/100 g_db) 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 °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 2.03×10^-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.

Abstract In the current study, the modeling and optimization of various seedling growth and germination indices for parsley seeds were investigated. A lab-scale quadrupole magnetic field was developed, and experiments were conducted using a completely randomized factorial design with three replications. The factors considered were magnetic field intensity (150, 300, and 450 mT), exposure time (30, 60, and 90 minutes), and culture time (0, 7, and 14 days after applying the magnetic field). The results revealed that the magnetic field significantly affected shoot length, fresh root weight, and fresh shoot weight, while exposure time significantly impacted root length. Sowing day also significantly influenced root length and fresh root weight, along with other factors. Immediate sowings after magnetic field application enhanced root length, while sowing 14 days following the exposure increased shoot length, fresh root weight, and fresh shoot weight. A 30-minute exposure to magnetic field intensities of 150 to 300 mT did not significantly affect seedling growth parameters. However, higher field strengths of 450 mT for 60 to 90 minutes proved beneficial, leading to enhanced shoot length, fresh root weight, fresh shoot weight, germination rate, germination percentage, and reduced mean germination time. The analysis and optimization using Response Surface Methodology revealed that the optimal magnetization condition, with a desirability of 0.682, was achieved at a magnetic field of 450 mT, an exposure time of 60 minutes, and sown 14 days post-exposure. Higher magnetic fields appeared to enhance field durability and significantly impact seedling growth indices.

Abstract Fire Blight (FB) is the most destructive bacterial disease of pome fruit trees around the world. In recent years, spectrometry has been shown to be an accurate and real-time sensing technology for plant disease detection. So, the main objective of this research is early detecting FB of pear trees by using Visible-Near-infrared spectrometry. To get this goal, the reflectance spectra of healthy leaves (ND), non-symptomatic (NS), and symptomatic diseased leaves (SY) were captured in the visible–NIR spectral regions. In order to keep the important information of spectra and reduce the dimension of data, three linear and non-linear manifold-based learning techniques were applied such as, Principal Component Analysis (PCA), Sammon mapping and Multilayer auto-encoder (MAE). The output of manifold-based learning techniques was used as an input of the SIMCA (Soft independent modeling by class analogy) classification model to discriminate NS and ND leaves. Based on the results, the best classification accuracy obtained by using PCA on the 1st derivative spectra, with accuracy of 95.8%, 89.3%, and 91.6% for ND, NS, and SY samples, respectively. These results support the capability of manifold-based learning techniques for early detection of FB via spectrometry method.

Abstract Accurate investigation of kinetics and development of high-precision seed drying models will help better studying the drying process by identifying effective parameters. Present study investigates the application of cold plasma (CP), as a pretreatment process, in air drying of canola seeds. This may bring about some complication into the drying kinetics investigation. Canola seeds with an initial moisture content of 27.5±1% (dry basis) were exposed to CP for 0, 15, 30, and 60 s prior to fluidization by air at temperatures of 40, 50 and 60 °C in a pilot scale fluidized bed heated by a solar panel.  The results showed a decreasing trend in drying time from 40 to 60 ^oC. The shortest drying time corresponds to samples dried at 60 ^oC with no CP pretreatment. The longest period however occurred for samples dried at 40 ^oC with 60 s of CP pretreatment. The greatest effect of CP on reducing the drying time was observed at temperatures of 40 and 50 °C at the CP exposure time of 15 and 60 s, respectively.  A reasonably accurate study of drying kinetics was accomplished using the superposition method. Accordingly, using experimental data, curves correspond to different drying conditions were plotted and in two steps these were shifted to a reference curve to acquire a final drying curve. The curve then was fitted to a second-order equation, and was validated using the experimental data. The correlation coefficients, mean square error and mean absolute error were 0.99, 0.03, and 0.023, respectively.

Abstract The agricultural sector is in need of a rapid transition from traditional and livelihoods to the stage of advanced production and commercialization, in order to provide food security for the community and to play an effective role in strengthening national independence. Mechanization is an approach that allows the agricultural sector to achieve the stage of commercial production. Without mechanization, there is no clear vision of a dynamic and sustainable agriculture that can rectify the food needs sensibly. The development of mechanization in agricultural societies, especially in the rural areas, has been accompanied by problems that the identification of the factors affecting it can help plan to eliminate them. Therefore, in the present study, the effect of the fragmentation of land on the development of agricultural mechanization in the rural districts has been investigated. The research type is applied and descriptive-analytic, survey method has been used and information has been collected through a questionnaire from 420 users in Jiroft city. The data were analyzed using a hierarchical analytical process technique using Expert Choice11 software. The research findings show that the family-social factor in the city of Jiroft was the main deterrent to the lack of development of mechanization and the cultural-communication, educational-technical, lawful-legal, and economic-financial factors were placed in the next priorities. It is proposed to implement the development of mechanization, the modernization of modern technology, education and promotion, building trust, credit and financial facilities for the modernization of agricultural implements.

Abstract Every organization needs an evaluation system in order to be aware of the level of performance and desirability of its units. It is more important for agricultural companies, including agro-industries. In this study, 20 sugarcane harvesting units were selected. After modeling based on input-oriented CCR and BCC models, efficiency values for sugarcane harvesting units were calculated and the CART decision tree was used to extract rules to predict the efficiency of these units. The results of a study of 20 sugarcane harvesting units in the CCR model showed that 6 units had an efficient score and 14 units had an inefficient score, and their technical efficiency score was in the range of 0.73-0.95. The results of the BCC model study also showed that out of a total of 20 sugarcane harvesting units, 8 units had efficient scores. As can be seen, in the BCC model, more units are introduced as efficient units and there is less dispersion between inefficient units. Also, the distribution of efficient units in the BCC model is less than the CCR model. The average technical efficiency, pure technical efficiency, and scale efficiency were 93%, 88%, and 93%, respectively. Also, the accuracy of the decision tree model for technical efficiency and pure technical efficiency was 86% and 93%, respectively.

Abstract The Soil and Plant Analysis Development (SPAD) value is a significant parameter indicating chlorophyll content, particularly in the green parts of plants. Conventional SPAD meters determine this value by measuring the transmission and absorption of red and infrared radiation at a single point (2×3 mm² sensor size). However, obtaining a comprehensive value for an entire leaf requires multiple measurements, increasing processing time. In this study, a non-destructive method for predicting SPAD values was developed using image processing techniques to determine dominant wavelength values from leaf photographs. A custom-designed photo box with controlled 6000 lux white LED lighting was used to capture images at a fixed distance of 15 cm. Images were processed using Color Picker (2024) software, where green components of the leaf were analyzed to extract dominant wavelength values. The results demonstrated that SPAD values could be accurately predicted using dominant wavelength data, with a 98.33% accuracy for the linear model (RMSE: 1.308) and 98.43% for the polynomial model (RMSE: 5.467). The findings indicate that a linear model provides a more precise correlation. This novel approach enhances the efficiency of SPAD measurement and offers a rapid, non-destructive alternative to conventional methods.

Abstract In the context of plant diseases, the selection of appropriate preventive measures, such as correct pesticide application, is only possible when plant diseases have been diagnosed quickly and accurately. In this study, a transfer learning model based on the pre-trained EfficientNet model was implemented to detect and classify some diseases in tomato crops, using an augmented training dataset of 2340 images of tomato plants. The study's findings indicate that during the model's validation phase, the rate of image categorization was roughly 5 fps (frames per second), which makes sense for a deep learning model operating on a laptop computer equipped with a standard CPU. Furthermore, the model was learned well because increasing the number of epochs no longer improved its accuracy. After all, the curves of the train and test accuracies, as well as the losses versus epoch numbers, remained largely horizontal for epoch numbers greater than 20. Notably, the highest coefficient of variation across these four cases was only 7%. Furthermore, the cells of the primary diagonal of the confusion matrix were filled with larger numbers in comparison with the values of the other cells; precisely, 88.8%, 7.7%, and 3.3% of the remaining cells of the matrix (cells of the primary diagonal excluded) were filled with 0, 1, and 2, respectively. The model's performance metrics are: sensitivity 85%, specificity 98%, precision 86%, F1-score 84%, and accuracy 85%.

Abstract The overall objective of this research is to check the abilities of two non-destructive techniques, the digital imaging (DI) and laser light backscattering imaging (LLBI), on detection of α-solanine toxicant in potatoes. Potato samples were classified in healthy and toxic categories based on the amount of α-solanine. For quantifying α-solanine in potato tubers, high-performance liquid chromatography (HPLC) has been used. The results of classification showed that single layer perceptron neural networks can classify potatoes with the accuracies of 94.28% and 98.66% by DI and LLBI systems (Donald cultivar), respectively. It can be said that LLBI systems might take precedent over DI systems due to their high accuracy, rapidity, and industrial capability.