سعید مینایی

Determination of organic-carbon-content variation in the field is crucial due to the importance of soil organic carbon content, including its role in increasing soil resistance against wind and water erosion. This study examines the ability of reflectance visible-near infrared (Vis/NIR) spectrometry for measurement and prediction of soil organic carbon content and the effect of the type of spectral preprocessing on the accuracy of multivariable predictive models was studied.

In this research, spectroscopy of soil samples was performed at 7 moisture levels in the interactance measurement mode in the 350-2500 nm spectral range using a contact probe. Spectrophotometry of 5 different sections of each soil sample was carried out and the data were processed and analyzed. Spectral data obtained from the spectrophotometer included unwanted information, background and noise in addition to the information of the samples. In order to arrive at accurate and reliable analytical models, pre-processing of the spectral data was required prior to regression model simulation. Multivariate calibration models of partial least squares (PLS) were developed based on the reference measurements and the information of the preprocessed spectra using a combination of different methods for assessment and prediction of soil organic carbon content. These included: smoothing (moving average (MA), and Savitzky-Golay (SG)); normalizing (multiplicative scatter correction (MSC), standard normal Variate (SNV)); as well as increasing the spectral resolution (first and second derivatives (D1, D2)).

Results showed that NIR spectroscopy is a suitable method for measurement of organic carbon content in soil samples. Prediction utilizing the data analyzed using the PLS model based on SG + MSC, produced the best detection results. Thus, SG+MSC preprocessing (Rc2 =0.81, RMSEC = 0.239, Rp2 = 0.79, RMSEP = 0.252) is suitable for predicting the amount of soil OC with high accuracy (SDR= 3.191). Results showed that reflectance rate diminishes with increasing moisture content reducing the ability of the PLS model to predict organic carbon content. This is true across all the preprocessing methods. In addition, the determined index values and validation criteria showed that prediction of organic carbon content with the PLS model using SG+D1+MSC, SG+MSC, SG+MSC, SG+D1+MSC, SG+SNV and SG+SNV combinations gives the best detection results for the following moisture levels, respectively: 6, 12, 18, 24, 30 and 36%.

Vis/NIR spectroscopy can be used as an alternative to conventional laboratory methods for soil organic-carbon-content determination. Results showed that the use of Vis/NIR spectroscopy for determination of soil organic carbon content can be considered in the site-specific management of fields, which can ultimately lead to saving inputs and reducing the pressure on the environment..

The study of novel extraction methods for natural essential oils and their comparison with conventional methods is one of the research needs of the herbal medicine processing industry. Fennel seed essential oil was extracted using two methods hydro-distillation and supercritical carbon dioxide extraction (pressure of 200 bar, temperature of 40 °C, and extraction time of 1 hour). The obtained essential oils were then analyzed by gas chromatography and gas chromatography-mass spectrometry. Results showed that the overall extraction yield of the essential oil obtained by the two methods of hydro distillation and supercritical extraction was 0.83% and 2.64%, respectively, in 100 grams. This shows an increase of 218.07% in the amount of essential oil obtained using the supercritical approach. This was considered appropriate, taking into account the extraction of the n-hexadecanoic acid (7.19%) compound, which was decomposed or degraded in the hydro-distillation method, and the number of compounds obtained by hydro-distillation compared to supercritical extraction (18 versus 30 compounds). In this research, compare the extraction results were compared based on the ISO standard to ensure the reliability of the results. Comparison of supercritical extraction with hydro-distillation extraction (standard 17412) confirmed the significant difference in the amount of extracted estragole. This study emphasizes the need to focus on the development of new extraction technologies to increase the quantity and quality of the obtained essential oil, which ultimately leads to higher added value compared to traditional methods.

Temperature is a critical factor affecting the quality and shelf life of perishable food products, making the precise and cost-effective monitoring of its levels essential throughout the cold chain. Due to practical limitations in deploying physical sensors at every point of interest, the development of soft (virtual) sensors for temperature estimation has attracted considerable research attention. Soft sensors are generally categorised into model-based and data-driven approaches, with the latter offering superior capability in capturing system dynamics without requiring detailed physical modelling. Among various data-driven methods, artificial neural networks (ANNs) have demonstrated superior performance compared to alternative techniques.The first step in designing a data-driven soft sensor is to collect and prepare training data, which can be either experimental or synthetic. Studies indicate that experimental data lead to more accurate estimations, although they are harder to obtain. A crucial subsequent step involves selecting appropriate input variables corresponding to potential sensor locations. While most previous studies have relied on subjective or heuristic input selection, supervised feature selection methods offer a structured and potentially more optimal alternative; however, such methods have rarely been applied in the context of temperature soft sensors for cold chains. Once inputs and outputs are defined, the modelling process typically employs ANNs, which have shown superior estimation performance over classical models. The present study implements supervised feature selection to optimise both the number and placement of physical sensors and to statistically investigate the effects of key hyperparameters in the time-delay neural network (TDNN) serving as the system's soft sensor estimator.

A cost-effective, Arduino-based data logger was developed to collect real temperature data for training the soft sensor. Temperature distribution data were collected from two peach pallets stored in a 2000-ton cold storage room maintained at 1 °C. The logger simultaneously recorded data from up to 20 DS18B20 sensors at 1-minute intervals. A novel supervised feature selection approach (wrapper method) was applied to identify the most informative sensor positions, thereby minimizing the required number of physical sensors. A time-delay neural network (TDNN) with one hidden layer was employed for temperature estimation. The influence of four key hyperparameters—time delay, number of hidden neurons, activation function, and training algorithm—on model performance metrics (RMSE, R², MAE, BIC) was evaluated. Additionally, a metaheuristic algorithm was used to assess the effectiveness of the feature selection method in reducing the sensor count. Model generalisability was verified using an out-of-sample test set collected under varying temperature scenarios and pallet placements.

Data acquisition for the first pallet lasted five hours, during which the cold storage refrigeration system operated under standard conditions. Table 1 ranks the five most informative sensor locations identified using the FIRE method. Table 3 presents the best model fits obtained with the SIG and ReLU activation functions. These models share a common structure: Levenberg–Marquardt (LM) training and a 20-minute time delay. Comparing activation functions reveals that ReLU yields superior performance metrics (R²mean and RMSEmean), while SIG achieves a lower BIC. Figure 4 illustrates how R²mean and RMSEmean vary as the number of physical sensors is reduced based on FIRE rankings under the optimal estimator configuration (LM2010-ReLU), showing no consistent trend and indicating the robustness of FIRE's variable selection. For the second pallet, data acquisition also spanned five hours; however, the refrigeration system was inactive for defrosting during the first three hours and resumed operation in the final two. Table 2 shows the FIRE-derived variable ranking, and Table 4 lists the best model fits for this dataset. All models for the second pallet employed LM training, a 20-minute delay, and five hidden neurons. In this case, performance metrics (R²mean and RMSEmean) progressively deteriorated as the number of sensors used decreased (Figure 4), indicating a greater sensitivity to sensor reduction under dynamic thermal conditions. Correlation analysis revealed strong relationships between RMSEmean and MAEmean, as well as among MSEtrain, MSEvalidation, and MSEtest; however, R²mean showed little correlation with these variables. BIC exhibited a significant correlation with several metrics. Consequently, MSEtrain, R²mean, and RMSEmean were deemed sufficient for performance evaluation. The influence of estimator hyperparameters (Table 5) indicated that the training method significantly affected performance, favouring LM. Hidden layer size and time delay primarily influenced BIC, while activation function showed no significant effect, consistent with Loisel et al. (2022). Ant Colony Optimisation (ACO) was applied to validate FIRE rankings (Figure 5). ACO results revealed alternative sensor combinations yielding lower RMSEmean than FIRE, suggesting that heuristic methods may offer superior configurations for "one-sensor-per-pallet" setups. Table 6 compares FIRE and ACO outcomes, confirming ACO's advantage in reducing the mean RMSE. Cross-pallet validation demonstrated that the soft sensor trained on one pallet and tested on the other under different thermal scenarios achieved RMSEmean values of 0.8 K and 1.0 K—13–15 times higher than the training RMSEmean, but acceptable given the scenario differences. However, R²mean (~0.4) indicated limited generalisation, implying that future training with diverse scenarios would enhance robustness (Figure 6).

The findings of this study demonstrate the high potential of supervised feature selection as a structured and objective method for identifying the most informative locations for hardware sensor placement in the development of soft sensors. However, to further reduce the required number of hardware sensors, the use of alternative methods, such as metaheuristic algorithms or exhaustive search techniques, appears to be a more prudent approach. In this regard, future research could explore and compare different supervised feature selection techniques to assess their ranking effectiveness and robustness in similar applications. The out-of-sample evaluation of the developed soft sensor in the "one-pallet-one-sensor" configuration yielded RMSE mean values ranging between 0.8 K and 1.0 K. This outcome is considered acceptable given the "single-scenario training" condition. Nevertheless, several factors could influence the accuracy and generalisation performance of the soft sensor, including: (1) the size of the dataset (in terms of duration or number of data points), (2) the temperature scenario or the operational state of the refrigeration system, and (3) the location of the pallets within the cold storage. Therefore, increasing the diversity of data acquisition conditions—such as varying spatial placement or thermal scenarios—is likely to yield valuable information for further improving the soft sensor's performance and predictive accuracy.

The moisture content of sugarcane sheath is a crucial parameter during the crop's growth period, as it plays a key role in understanding water stress and field irrigation management. Traditional methods of measuring crop moisture levels involve time-consuming and expensive processes like obtaining wet and dry weights, followed by calculating moisture content, which are impractical for large areas. Recent advancements in remote sensing technology have enabled the monitoring of plant tissue moisture content in large fields. Remote sensing data have a high capacity to update crop growth monitoring systems.  In this regard, it is possible to use satellite images that provide a wealth of information to users. This research aims to evaluate sugarcane leaf sheath moisture using satellite images and generate moisture maps based on the best model.

The sugarcane fields, which represent the largest agricultural operations in Khuzestan, have an area of over 84,000 hectares. It covers over 9,670 hectares are cultivated by the Amir Kabir Agriculture and Industry company, the focus of this research. The study area is located at a latitude of 31° 00' 20' N and a longitude of 48° 15' 22' E. A total of 18 farms of the sugarcane variety CP69-1062 were utilized for this research. Five points were selected from each farm, and the coordinates of the points were recorded using a GPS device. The study was carried out between July and September. Ground data were collected nearly simultaneously with the Sentinel-2 satellite imaging of the target area. The moisture content of each collected sample was determined gravimetrically in the laboratory. For each image, indices and spectral bands were calculated using QGIS software and the output was saved as Excel and TIF files. The indices and bands obtained from Sentinel-2 satellite images were used to estimate and monitor the moisture status of sugarcane leaf sheath. In the next step, a variance inflation factor (VIF) analysis was implemented to check the collinearity between indices and bands. Finally, the indices of NDVI, EVI, SRWI, Clgreen and single bands B2, B3, B4, B5, B6, B11 and B12 were entered as input to four GRNN, RF, SVR and PLSR models. The Bayes algorithm was employed to optimize the parameters of the model.

The results demonstrated that the SVR model exhibited a superior ability to estimate leaf sheath moisture compared to other models. Additionally, the sensitivity analysis revealed that the SRWI, Clgreen, NDVI, B5, B12, B11, B4, B3, EVI and B2 parameters are effective parameters in the moisture content modelling process. In the final stage, the leaf sheath moisture was classified into five stress classes, namely irrigation time, low moisture, medium moisture, and high moisture, in the order from low to high. The results of the moisture maps and the irrigation schedule for each date indicate that the combined output of B2, B3, B4, B5, B6, B11, B12, NDVI, EVI, SRWI and Clgreen indices and bands has a superior performance. These indices were utilized in the preparation of irrigation plans. This method was employed to assess the potential of S2 MSI spectral indices for the estimation of leaf sheath moisture in the sugarcane growth stage.

Based on sensitivity analysis, the SRWI parameter was found to be the most effective index in the modelling process. Consequently, it can be concluded that a combination of indices and bands of NDVI, EVI, SRWI, Clgreen, B2, B3, B5, B4, B11, and B12 provides a more accurate estimate of sugarcane sheath moisture than any single input. Thus, processing and analysis of Sentinel-2 satellite images can be used to enhance the methodologies employed for the monitoring of sugarcane sheath moisture content in expansive fields.

Stirred tanks have a wide range of uses in food, chemical, and mineral industries. As a result, accurate knowledge of the hydrodynamic behavior of the fluid in these tanks is essential. One of the issues that arises in stirred tanks when working at high speeds is the vortex inside the tank, which inhibits appropriate mixing. In the current numerical study, by attaching vertical baffles to the inner wall of the tank, the flow field and vortex phenomena were evaluated. Computational Fluid Dynamics (CFD) was employed to explore the influence of wall baffles on variations in radial velocity and turbulent kinetic energy. Based on the numerical results, it was discovered that adding baffles to the tank wall enables the radial flow to be extended, which provides for better mixing inside the stirred tank. Moreover, by adding the baffles, vertical flow is improved, enhancing the agitation inside the tank. According to the results, the turbulent kinetic energy for tanks with and without baffles is 0.00957 m2 / m3 and 0.0112 m2 / s3, respectively, while the energy dissipation rates were 0.955 m2 / m3 and 0.805 m2 / s3, respectively. Increasing velocity in the vicinity of the baffle, results in enhanced agitation, providing the energy demand for better mixing. This prevents continuous swirling motion which can reduce agitation quality.

Nowadays, machine vision systems are extensively used in agriculture. The application of this technology in the field can help preserve agricultural resources while reducing manual labor and production costs. In the field of agricultural automation, accurately detecting crop rows is recognized as a crucial and challenging issue for weed identification and the automatic guidance of machines. Therefore, it is necessary to explore practical solutions to optimize this process. Hence, the purpose of this study is the precise identification of basil cultivation rows to enable the automatic navigation of robots in the cultivation field.

In the first stage of this research, six images from each growth period of basil plants (third, fourth, and fifth week) were taken and weeds were removed from the area between the crop rows using three different methods of area opening, dimensional removal, and masking. In the next stage, six images of crop rows without weeds were examined by performing image processing operations and implementing several routing algorithms, namely, Hough transform, wavelet transform, Gabor filter, linear regression, and an additional algorithm proposed in this study. The output of each of these algorithms was compared with the ideal path identified by the user. For this purpose, after capturing an image, green areas were extracted from it by performing the segmentation process. By applying each of the routing algorithms to the image, plant cultivation lines were identified and their equations were determined. Finally, the performance of the designed robot was evaluated using the most appropriate routing algorithm.

Examining the performance of three different methods of weed removal in three periods of plant growth (third, fourth, and fifth week) showed that during this interval, the masking method had the lowest error rate compared to the ideal path and the shortest average operation time of 1.64 seconds, followed by the dimensional removal and the area opening methods. Comparing the routes detected by different routing algorithms with the ideal routes and according to the results of the t-test at 5% probability level, the order of the studied routing methods from the most superior is as follows: the proposed algorithm, Gabor filter, linear regression, Hough transform and wavelet transform algorithm. Overall, the proposed algorithm had the highest rate of adaptation to the ideal path (with an average error of 3.65 pixels) and the shortest operation time (4.79 seconds) and was selected as the most appropriate routing algorithm and the performance of the designed robot was evaluated using it.

A reliable crop row detection algorithm can reduce production costs and preserve the environment. In this study, the masking method was used for removing weeds from the images. The new proposed routing algorithm has superior performance when compared with common routing algorithms such as the Gabor filter, linear regression, Hough transform, and wavelet transform. Additionally, it was shown that the designed robot using the proposed algorithm (with an average error of 3.65 pixels) has the desired performance.

Iran is one of the world's largest and most important raisin-producing countries. Considering the amount and value of raisin exports in Iran, mechanizing this product's collection and maintaining its mechanical quality is one of the most necessary tasks in this field. Therefore, the main purpose of this study is to design and construct a collection head in a Rover for collecting raisin products from the ground and then evaluate the mechanical damage of raisin crops during collection from the ground by the collecting head. After performing the software design, the necessary calculations were performed to select different device parts. The rover was evaluated on raisins spread on the ground at three forward speeds of the rover (1, 2 and 3 km/h) and three heights of the head (2, 5 and 10 mm) from the ground surface. The constructed head with a length of 80 cm was mounted on a rover with dimensions of approximately 70 × 50 cm. The working capacity of this machine at the rotational speed of 25 rpm of the collecting brush is equal to 3.3 kg/min, and it is able to fill the 80 kg container every 15 minutes. The evaluation results showed that the effect of forward speed and head height on mechanical damage was significant (p <0.01), but their interaction was not significant. Also, the lowest mechanical damage (11%) was related to the height of 2 mm from the ground. Mechanical damage of the product was reduced by 8% at the forward speed of 1 km/h compared to the other two speeds.

Pectin, which is made from citrus peel and waste, is one of the most commonly used compounds in the food industry. For large scale production, a combination of membrane-vacuum filtering has been suggested as an alternative to traditional methods of purifying the acidic solution for pectin extraction. This study investigates the main factors regarding membrane filtering system for separation of fibrous materials from an acidic pectin solution under vacuum. These factors which include: filter-aid-particle size, amount of filter-aid (perlite) added to the solution, and the vacuum level, affect production efficiency, degree of esterification, and galacturonic acid content. Pectin extraction efficiency is an important criterion for evaluating the filtration system and test results showed that both perlite particle size and perlite-layer thickness significantly affect this dependent variable. By increasing the perlite particle size from 20 to 100 microns, the extraction efficiency has doubled. This is while increasing the perlite layer thickness from 1 cm to 2 cm cuts the efficiency in half (from 20% to 10%). The highest galacturonic acid content was obtained with 2cm perlite thickness and 20-microns particle diameter. The degree of esterification was affected by the extraction conditions, and results revealed that the extracted pectin samples have an esterification degree of 70±5%. The optimum extraction conditions were determined by the software to be: 2 cm perlite-layer thickness and 56-microns filter-aid particle size at a vacuum level of 0.38 bars. Findings of this study can be utilized in the industrial scale implementation of a biomaterial separation system using vacuum-membrane filtering.

Pectin, which is made from citrus peel and waste, is one of the most commonly used compounds in the food industry. For large scale production, a combination of membrane-vacuum filtering has been suggested as an alternative to traditional methods of purifying the acidic solution for pectin extraction. This study investigates the main factors involved in membrane filtering system for separation of fibrous materials from an acidic pectin solution under vacuum. These factors which include: filter-aid-particle size, amount of filter-aid (perlite) added to the solution, and the vacuum level, affect, separation quality, volumetric flow rate, and energy consumption . A vacuum separation device was developed for this purpose in order to separate the fibrous material dissolved in solution. The independent variables were examined at three levels, the data were analyzed, and the optimum value for each variable was determined using the response surface method (RSM). Results revealed that increasing the vacuum level from 0.2 to 0.4 bar increases the flow-rate 6.5 folds, while, further increase in the vacuum level decreases the flow-rate. This indicates clogging of the paper filter and decreased flow-rate at vacuum level of 0.6 bar and perlite particle size of 100 microns. The evaluation results showed that thickness of the perlite layer has the greatest effect on the separation efficiency and when increased from 1 to 2 cm,  increases the efficiency  2.5 folds. The maximum value of separation efficiency was obtained at a vacuum level of 0.2 bar, particle size of 20 microns and perlite thickness of 2 cm. The energy consumption of 60-micron perlite was 0.74 Wh in the optimal state, and the larger and smaller sizes of perlite had 4.5 times the energy consumption. These findings are applicable in the industrial scale implementation of a biomaterial separation system using vacuum membrane filtering.

Packaging, transportation, and separation of agricultural products are among the processes that cause potential damage, losses, and increased waste, depending on the type of product. Therefore, determining the mechanical strength properties is one of the most important approaches to prevent mechanical damage. Using mechanical tests, such as compression tests, is a common approach to obtain information, but simulation methods can help determine a wider range of information, such as stress and strain distribution patterns in the fruit, at lower cost and higher speed. Quince (Cydonia oblonga), which like other fruits is susceptible to mechanical damage, is rich in various compounds such as flavonoids and phenolic acid, which contribute to anti-cancer, anti-inflammatory, anti-allergic, and antimicrobial properties. In this study, to determine the mechanical properties of quince, compression tests were performed on fruit specimens at a rate of 10 mm/min using a materials testing machine and supplemented by simulation using ANSYS software FEM. The results of the experiments and simulations showed that a viscoelastic model adequately describes the behavior of the fruit under quasi-static loading. The simulation results for loading rates of 5 and 20 mm/min showed that the specimen is subjected to higher shear and normal stresses at a rate of 20 mm/min. The minimum of shear and normal stresses is associated with the rate of 5 mm/min. According to the evaluation results, it is better to perform harvesting and post-harvesting of quinces in such a way that lower loading rates (5 mm/min) are applied to avoid losses as much as possible.

Site-specific agriculture is a subset of precision agriculture that aims to increase productivity as well as the quantity and quality of crops based on measuring spatial variation, soil and plant characteristics, and consumption of inputs as variables in time and space. The first step to fulfill this goal is to locate the agricultural machine in the relevant place so that the desired operation can be performed accordingly. In the current research, a ground positioning device with sensors for measuring the steering angle and the number of rotations of the moving wheel of the tractor has been developed. The system was field-tested with local positioning without needing external servers, and the data were compared with the output values of a GNSS receiver. The experiments were performed on asphalt, plowed and uncultivated fields as well as in sunny and cloudy conditions. The statistical design was based on randomized completeblocks as a factorial test in 2 × 2 × 3 with four replications. According to the obtained results, the X and Y axes data of the GNSS receiver and self-tracking device showed a significant difference at the 1% and 5% levels, respectively. Changes in environmental factors, including sunny/cloudy and the ground surface conditions on both the X and Y axes, did notsignificantly affect positioning by the GNSS receiver and the self-tracker. The accuracy of the tracker system in the X direction was found to be 25 cm and for the GNSS receiver 250 cm, while in the Y direction, this was 50 cm and 140 cm for the GNSS receiver. As a result, the tracker system was more accurate on both the X and Y axes. In addition, path deviation distances obtained with the GNSS receiver and the self-tracking device were significantly different at the 1% probability level. The accuracy of determining the distance in the selftracking system was 60 cm, while with the GNSS receiver, it was 400 cm. In general, the performance of the self-tracking system in finding the optimal trajectory was more accurate than the conventional GNSS receiver (without DC correction).

Sesame oil which is one of the most popular and expensive edible oils, is prone to adulteration. High price of Sesame oil has motivated adulterers to mix the high-quality Sesame oil with low-quality, less expensive vegetable oils. In this study, the fatty-acid profiles of sesame, rapeseed, sunflower oil samples as well as their mixtures (0, 5, 10, 20, 30, 40 and 50% levels) were determined using Gas Chromatography. Also, Machine olfaction system containing 10 MOS sensors was utilized for detection experiments. Sensor response patterns were used for analyzing and recognizing pattern of electronic-nose signals using multivariate data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analyses (LDA), Partial Least Squares (PLS), K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). Results of the SVM with RFB kernel in C-SVM method had the highest classification accuracy. The accuracy of training and validation were 96.34 and 90.56%, respectively, and next were LDA and KNN models with classification accuracies of 92.30% and 89.94%, respectively. In the light of these results, the proposed models along with the measurement system represent excellent tools for the detection of sesame seed oil adulteration with cheaper vegetable oils.

Artificial seed production is a developing technology in plant biotechnology that provides considerable potential for conserving rare, endangered, and threatened species that are difficult to propagate through conventional propagation methods. In the present investigation, Image J software was used to process the digital image of the capsules and determine the volume, sphericity, and artificial seed centrality index. Response surface methodology (RSM) and artificial neural network (MLP and RBF) were utilized to model, predict and optimize the physical properties of the artificial seed of Phalaenopsis orchid. The training and validation data sets of the studied models were compared using regression coefficients (R) and sums of squared errors (SSE). Artificial seeds were obtained through encapsulation of Phalaenopsis orchid protocorm using various levels of sodium alginate concentration (3, 4, and 5%), calcium chloride concentration (100, 125, and 150%), and drop height (1, 1.5, and 2 cm) as input variables. Physical properties of artificial orchid seeds, including (capsule volume, sphericity index (SI), and concentric index (CI)) were considered as output variables. The results showed that image processing is an effective method for determining the physical properties of artificial seeds. According to the regression models, Results showed that interaction effects of the main factors are positively correlated with volume (p< 0.05). The effects of sodium alginate× calcium chloride concentration were significantly correlated with the CI index (P< 0.05). In addition, the sphericity value was positively correlated with sodium alginate concentration. In general, based on R2 and SSE values, the MLP model showed a much more accurate prediction than RSM and RBF models in terms of the values R2 and SSE. The optimum condition for volume, sphericity and CI index values was obtained using MLP 3-10-1 (R= 0.79, SSE= 0.0014), MLP 3-14-1 (R= 0.57, SSE= 0.0031) and MLP 3-14-1 (R=0.67, SSE= 0.0042), respectively. It is concluded that the ANN (MLP) is a desirable tool for the prediction and optimization of the physical properties of Phalaenopsis orchid synthetic seed.

This research includes the design, manufacturing, and evaluation of a live mulch planter unit. In order to address the problems of using agricultural machinery in performing live mulch planting in the furrows or simultaneously with the main crop, a prototype planting unit was designed. In this planter, a seed-drop plate was used to convey the seeds from the metering device to the ground. The result of this project was a prototype of a planter with the ability to plant 19.6 to 163.2 grams per minute of live mulch (hairy vetch) with a tolerance of 0.54 grams along the entire width of a 75 cm furrow. Laboratory and field experiments were conducted to evaluate its performance in actual field conditions, based on planting accuracy and field efficiency. The Laboratory test was performed according to ASAE S341.2 DEC92 standard for Grain Drill evaluation. Results of the initial evaluation of the planter showed that changing the rotational speed of the metering device significantly affected seed output on the drop plate in terms of seeding rate. The position of the outlets did not differ significantly in terms of seed damage. Increasing rotational speed of the metering device significantly increased the tendency of metering mechanism to damage seeds. Increasing rotational speed of the metering device significantly decreased index of non-uniformity in all outlets.Results of the initial evaluation of the planter showed that changing the rotational speed of the metering device significantly affected seed output on the drop plate in terms of seeding rate. The position of the outlets did not differ significantly in terms of seed damage. Increasing rotational speed of the metering device significantly increased the tendency of metering mechanism to damage seeds. Increasing rotational speed of the metering device significantly decreased index of non-uniformity in all outlets.

Utilizing the latest available technologies is essential for food preservation and processing. Consumers increasingly prefer products that have undergone the least change during processing and storage. Among them, pulsed electric field (PEF) is one of the non-thermal methods of food processing and storage. In this study, a Pulsed Electric Field system was designed, fabricated and then evaluated. For this purpose, a Schmidt-Trigger-based pulse generating system system and a semiconductor key (IGBT) were designed and tested using a gate driver with DC output. The input parameters for the tests included: voltage, number and frequency of pulses as well as pulse width. In order to adjust the two parameters, pulse number and excitation frequency, a touch panel and autotransformer were utilized to adjust the voltage. A constant pulse width of 2 microseconds was used. The results of the evaluation were reported in two parts. In the first part, the evaluation of the system function was performed using an oscilloscope and high voltage waves were produced. In the second part, the evaluation of the fish samples was performed in terms of the effect on the value of extracting protein. The Response-Surface method and Box-Bhenken scheme were used for data analysis and process optimization. Results of analyses showed that based on regression coefficients, the effect of the voltage factor and the second voltage factor had the highest influence on Protein extraction increase.

Determining the status of egg fertilization plays a major role in determining the quality of eggs and their products. In this regard, in order to achieve greater productivity and production, egg evaluation is considered necessary and important in terms of spermatogenesis. In this regard, spectroscopy was performed in the range of 0.01900 nm from 130 local egg samples in the direction of the main diameter for 3 days during the storage period. Spectrum data from spectrometers, in addition to sample information, include unwanted information and noise.  For this reason, in order to achieve accurate classification models, it is necessary to process spectral data before developing the appropriate model. In this regard, intelligent neural network classification was developed based on reference measurements and information of pre-processed spectra by combining different methods of smoothing, normalizing and increasing spectral separation power to determine the presence of sperm in the egg.  Classification results on day zero, first, second, warehousing with 72.3% accuracy, 73.1%, 75.5%, and detection, 86.31, 87.1%, 76% and sensitivity, respectively: 83 61%, 79.63% and 73.3% were obtained.

In the processing of vegetables as well as preparation for fresh consumption, the leaf part of the vegetable is separated from the stem manually and non-mechanically. This research was carried out in order to design and development an automatic system for precise cutting of vegetable stems harvested from the field. Machine vision was used to determine the appropriate cutting position. In this way, after placing the product on the conveyor, it is automatically photographed and after identifying the cutting location, a cutting mechanism separates the leaf part of the plant from its stem. The designed cutting system performed the cutting of the samples with an accuracy of about 3 mm. It takes about 4 seconds to identify the cutting location and perform cutting, so the maximum capacity of the machine is 15 cuts per minute. The output of the machine had acceptable quality in cases where the incoming vegetables were evenly and freshly harvested.

In this study, the ability of the near infrared interactance (NIR) spectrometry for nondestructive assessment and prediction of the sugar content of the roots of sugar beet were studied. Additionally, the effect of spectral pre-processing methods on the accuracy of multivariate predictor models was assessed. In this regard, the spectrometry of sugar beet samples was performed in the interactance measurement mode within the spectral range of 350-2500 nm using a contact probe. For this purpose, at first skin spectroscopy was performed in 3 desired areas and then the samples were cut vertically and finally spectroscopy was performed in these three areas. The results show that spectroscopy could be used to measure the amount of sugar in beets. Regions of the main absorbance peaks on NIR spectra of the intact and peeled sugar beets were the same. Therefore, the effect of chemical compounds of sugar beet skin can be ignored to identify internal compounds with nondestructive NIR spectroscopy. Additionally, sugar content of the product can be measured without the need to cut it. Prediction of the sugar content of intact samples with the PLS model based on SG + D2, is the the most accurate prediction method. Thus, SG+D2 preprocessing (rc =0.87, RMSEC = 0.90, rp = 0.95, RMSEP = 0.55) is suitable for predicting the amount of SC with the highes accuracy rate (SDR= 3.20). Finally, a system was designed based on the developed model with the ability to measure the grade of the product in a nondestructive way. This system can be used to process the facilities of sugar beet as well as research on breeding of sugar beet in breeding Institutes.

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.

Greenhouses should provide a controlled environment to produce plants with sufficient sunlight, temperature, and humidity. Better growth conditions in the greenhouses are mainly achieved by maintaining the optimum indoor temperature compared to the outdoor temperature of the greenhouse. The objective of this study is design, construction and evaluation of a fuzzy control system for a research greenhouse with capability of measuring, control and monitoring of greenhouse environmental conditions. Greenhouses control variables are air temperature, ambient relative humidity, light intensity, CO2 levels which are monitored and controlled by operators (heating system, cooling system, carbon dioxide regulation system, ventilation and humidity regulation system). In this study, hydroponic greenhouse was first designed and constructed. Heating and cooling equipment as well as needed sensors were installed. Then, a fuzzy control system was designed. Finally, by considering information on the appropriate environmental conditions of the hydroponic greenhouse of cucumber, the values of temperature, humidity, light and carbon dioxide are considered as fuzzy system inputs and the rules of the fuzzy system were adjusted so that the environmental conditions of the greenhouse were also fuzzy defined according to the input data. The results of the system evaluation showed that fuzzy control can well control the greenhouse environmental conditions.

Study on biometric parameters of trout species in the traditional method (based on human and non-automatic factors) are low-efficient due to serious problems such as disease transmission, stress-induced death, inaccuracy, & time-consuming. To overcome the problems of traditional method, an image-based vision system, including imaging and lighting chambers, was developed in this research. The fish biometric parameters were measured using fish movement videography during passage from the dark chamber. Then the selected images from the video were processed. The length, surface area, weight, amount of food consumed, & growth rate of trout were measured under fully controlled conditions and used as comparison criteria (control). Six mathematical models were used to estimate fish weight through measured parameters and among them the weight/length model was used as the best model for estimating fish weight. The accuracy of the system in estimating fish biometric parameters was above than 90% and the system’s capability to estimate the fish required food during the growth process was 98%.

The objective of this study was to Investigating the role of audit committee attributes in corporate sustainability reporting. The present study is an applied research and its method is causal-post-event. The statistical population of the study is all companies listed on the Tehran Stock Exchange. The sample was selected using systematic exclusion sampling method and imposing conditions of the research variables to 228 firms during 2014-2019. Statistical technique of panel data regression was used to analyze data and test the hypotheses. According to the results, there was a significant positive relationship between Audit Committee Independence, Audit committee financial expertise and Audit Committee Size on corporate sustainability reporting. This is due to the fact that the Audit Committee pays more attention to social responsibility and issues related to sustainable development. The results also indicate that the audit committee, as one of the elements of the company's internal control structure, has taken steps to protect the interests of various groups using the company's accounting information and employ this committee to improve the reporting process as well as provide transparent information and reports. And it is reliable and effective. According to the research results, it is suggested to managers that in order to attract investors, align with environmental development, increase company value and other factors affecting the efficiency and effectiveness of companies, to the independence and financial expertise of the audit committee to increase corporate responsibility. Pay attention and put it in your plan.

​Distillates are one of the most popular consumer products of medicinal plants. High essential oil and low methanol contents have always been considered as two desirable factors by experts in the food and pharmaceutical industries. In order to investigate the effect of harvest height on Hyssop (Hyssopus officinalis L.) distillate quality, an experiment was conducted in a randomized complete block design with three replications. Four harvesting heights of 15, 25, 35 and 45 cm (measured from the highest point of the plant), as well as the remaining stalk, were the treatments in this research. The measured traits were: methanol and essential oil content in the distillates. The results of statistical analysis showed a significant effect of treatments on the studied traits. It can be said that methanol values significantly increased with the harvesting height measured from the top. It varied from 71.64 ± 2.7 mg/l for the height of 15 cm to 219.77 ± 3.52 mg/l for 45 cm. In the remaining stalk, methanol values increased from 142.33 ± 1.34 mg/l for 15 cm height to 393.86±24.65 mg/l for 35 cm height. It should be mentioned that at 45 cm height of cut, there was no remaining stalk. The amount of essential oil in the distillate increased with harvesting height. The findings of this study showed that the harvesting height of 15 cm from the highest part of the plant is recommended for obtaining a higher distillate quality with lower methanol content, and the possibility of increasing the number of harvesting cuts for the production of medicinal and nutritional products.

Iran is the largest producer of saffron and more than 90 percent of Iran's saffron is produced in Iran.Drying is one of the methods commonly used to increase the shelf life of medicinal plants and agricultural products. In this study, drying process of saffron petals with thin layer hot air dryer at five levels at 40, 60, 80, 100 and 120 ° C and three air flow of 0.5, 1 and 1.5 m/s and their impacts of on colored parameter (amounts R, G and B) have been studied. By using vision machine system, color images of the saffron dried petals were taken, and analyzed using image processing algorithms, Features colored (RGB) were also obtained. In addition, the anthocyanin content, (using differential pH method) and L*a*b* characteristics were measured in order to determine the proper drying conditions of the samples. The data were analyzed using factorial experiment based on randomized complete design. The results showed that maximum RGB values were at the temperature range of 80 to 100°C, representing the greatest ratio and intensity of red, green and blue colors. Also in this temperature range, the highest anthocyanin content (482.21mg/l) and lowest color changes (ΔE) were obtained which was a relative desirability of this range for drying saffron petals.

Today, development of vegetable farming is involved with the development of knowledge and equipment for production of grafted plants. This area is classified in the field of biosystems engineering and mechanics of cutting should be investigated as the first steps in this field. In this research, effects of the type of cutting blade, loading rate, oblique angle, and tilt angle were studied on two important parameters in cutting including cutting energy and maximum cutting force of tomato and eggplant seedlings. The results showed that the maximum specific cutting force and the specific cutting energy were in the range of 0.2-5.5 N per millimeter of stem diameter and 0.2-5 mJ per square millimeter of stem cross section, respectively. Statistical analysis of the data revealed that only blade type and oblique angle significantly affected the cutting parameters. Among prevalent blade types in vegetable grafting operations, razor blade requires the minimum cutting force and increasing the blade oblique angle is useful in making a smooth cut.