Mahmoud Omid - Profile on Academia.edu (original) (raw)

Papers by Mahmoud Omid

New spectral absorption photometry methods are introduced to estimate chlorophyll (Chl) content o... more New spectral absorption photometry methods are introduced to estimate chlorophyll (Chl) content of corn leaves by smart phones. The first method acquires light passing through a leaf by smartphone camera, compensating for differences in illumination conditions. In order to improve performance of the method, spectral absorption photometry (SAP) with background illumination has been considered as well. Data were acquired by smartphone camera in Iowa State University maize fields. Various indices were extracted and their correlation with Chl content were examined by Minolta SPAD-502. Hue index in SAP reached R 2 value of 0.59. However, with light-aided SAP (LASAP), R 2 of 0.97 was obtained. Among traits, the vegetation index gave the most accurate indication. We can conclude that the high performance of LASAP method for estimating Chl content, leads to new opportunities offered by smart phones at much lower cost. This is a highly accurate alternative to SPAD meters for estimating Chl content nondestructively.

Computers and Electronics in Agriculture

A new android app for smartphones to estimate chlorophyll content of a corn leaf is presented. Co... more A new android app for smartphones to estimate chlorophyll content of a corn leaf is presented. Contact imaging was used image acquisition from the corn leaves. In this method, the light passing through the leaf is captured directly by a smartphone camera. This approach would eliminate the needs for background segmentation and other pre-processing tasks. To estimate SPAD (Soil Plant Analysis Development) values, various features were extracted from each image. Then, superior features were extracted by stepwise regression and sensitivity analysis. The selected features were finally used use as inputs to the linear (regression) and neural network models. Performance of the models was evaluated using the images taken from a corn field located in West of Ames, IA, USA, with Minolta SPAD 502 Chlorophyll Meter. The R2 and RMSE values for the linear model were 0.74 and 6.2. The corresponding values for the neural network model were 0.82 and 5.10, respectively. Finally, these models were suc...

A b s t r a c t. In this paper, an accurate image processing algorithm for determination of volum... more A b s t r a c t. In this paper, an accurate image processing algorithm for determination of volume and surface area of orange is developed. The proposed machine vision system consists of two CCD cameras, an appropriate lighting system and a personal computer. The cameras are placed at right angle to each other in order to give two perpendicular views of the image of the orange. Initially, the algorithm segments the background and divides the image into a number of frustums of right elliptical cone. The volume and surface area of each frustum are then computed by the segmentation method. The total volume and surface area of the orange is approximated as the sum of all elementary frustums. The difference between the computed volumes and surface areas obtained by the image processing method and measured by water displacement and tape method, respectively, are not statistically significant at the 5% level. The Bland-Altman results show that the orange size has no effect on the accuracy of estimated volume and surface area found by the image processing technique. The regression formula, M=0.68V IP +44.6, between the computed volume and the measured mass of oranges is found to be highly correlated with R 2 =0.93. K e y w o r d s: orange, volume, surface area, mass, image processing, segmentation method

Journal of Cleaner Production, 2013

This study was carried out in Isfahan province, Iran, to assess the environmental impact of green... more This study was carried out in Isfahan province, Iran, to assess the environmental impact of greenhouse cucumber and tomato production using life-cycle assessment (LCA) methodology. In this study a cradle-to-farm-gate approach using data from greenhouse operators and two distinct functional units, one mass-based and the other land-based, were selected to analyze the impact categories. Data for production of inputs were taken from EcoInvent Ò 2.0 database, and SimaPro software was employed for analysis. Ten impact categories including Abiotic Depletion potential, Acidification potential, Eutrophication potential, Global Warming potential for time horizon 100 years, Ozone Depletion potential, Human Toxicity potential, Freshwater and Marine Aquatic Ecotoxicity potential, Terrestrial Ecotoxicity potential, and Photochemical Oxidation potential were selected based on the CML 2 baseline 2000 V2/world, 1990/characterization method. In addition, adaptive neuro-fuzzy inference system (ANFIS) was employed to predict the environmental impact of both crops on the basis of input materials. The results indicated that greenhouse tomato production had a lower environmental impact than cucumber due to less total energy input and correspondingly lower environmental burdens in all impact categories. Almost all impact categories were dominated by natural gas, electricity and nylon (as cover of greenhouses). Furthermore, the results revealed that ANFIS was capable of forecasting the environmental indices of greenhouse production with a high degree of accuracy and minimal error.

Application of tractors in farming is undeniable as a power supply. Therefore, performance model ... more Application of tractors in farming is undeniable as a power supply. Therefore, performance model for evolving parameters of tractors and implements are essential for farm machinery, operators and manufacturers alike. The objective of this study was to assess the predictive capability of several configurations of ANNs for performance evaluating of tractor in parameters of drawbar power, fuel consumption, rolling resistance and tractive efficiency. A conventional tillage system which included a moldboard plow with three furrows was used for collecting data from MF285 Massey Ferguson tractor. To predict performance parameters, ANN models with back-propagation algorithm were developed using the MATLAB software with different topologies and training algorithms. For drawbar power, the best result was obtained by the ANN with 6-7-1 topology and Bayesian regulation training algorithm with R2 of 0.995 and MSE of 0.00024. The ANN model with 6-7-1 structure and Levenberg-Marquardt training algorithm had the best performance with R2 of 0.969 and MSE of 0.13427 for TFC prediction. The 6-8-1 topology shows the best power for prediction of AFC with R2 and MSE of 0.885 and 0.01348, respectively. Also, the 6-10-1 structure yielded the best performance for prediction of SFC with R2 of 0.935 and MSE of 0.012756. The obtained result showed that the 6-7-1 structured ANN with Levenberg-Marquardt training algorithm represents a good prediction of TE with R2 equal to 0.989 and MSE of 0.001327. The obtained results confirmed that the neural network can be able to learn the relationships between the input variables and performance parameters of tractor, very well.

Energy, 2011

This paper examines the energy use patterns and energy inputeoutput analysis of major greenhouse ... more This paper examines the energy use patterns and energy inputeoutput analysis of major greenhouse vegetable productions in Iran. Data from 43 farmers were obtained using a face-to-face questionnaire method. The majority of farmers in the surveyed region were growing cucumber and tomato. Total input energy was found to be 141493.51 and 131634.19 MJ ha À1 for cucumber and tomato productions, respectively. Among input energy sources, diesel fuel and fertilizers contained highest energy with 54.17 e49.02% and 21.64e24.01%, respectively. The energy ratio was found to be 0.69 and 1.48 for cucumber and tomato productions, respectively. Econometric model evaluation showed the impact of human labor for cucumber and chemicals for tomato was significant at 1% levels. Sensitivity analysis indicated that the MPP value of energy inputs were between À5.87 and 7.74. RTS (returns to scale) values for cucumber and tomato yields were found to be 1.29 and 0.76; thus, there prevailed an IRS of cucumber for estimated model. The net return was found positive, as 22651.13 and 78125.08 $ ha À1 for cucumber and tomato, respectively. The benefitecost ratios from cucumber and tomato productions were calculated to be 1.68 and 3.28, respectively. Among the surveyed greenhouses, the result indicated tomato cultivation was more profitable.

In this study, various Artificial Neural Networks (ANNs) were developed to estimate the productio... more In this study, various Artificial Neural Networks (ANNs) were developed to estimate the production yield of greenhouse basil in Iran. For this purpose, the data collected by random method from 26 greenhouses in the region during four periods of plant cultivation in 2009e2010. The total input energy and energy ratio for basil production were 14,308,998 MJ ha À1 and 0.02, respectively. The developed ANN was a multilayer perceptron (MLP) with seven neurons in the input layer, one, two and three hidden layer(s) of various numbers of neurons and one neuron (basil yield) in the output layer. The input energies were human labor, diesel fuel, chemical fertilizers, farm yard manure, chemicals, electricity and transportation. Results showed, the ANN model having 7-20-20-1 topology can predict the yield value with higher accuracy. So, this two hidden layer topology was selected as the best model for estimating basil production of regional greenhouses with similar conditions. For the optimal model, the values of the models outputs correlated well with actual outputs, with coefficient of determination (R 2 ) of 0.976. For this configuration, RMSE and MAE values were 0.046 and 0.035, respectively. Sensitivity analysis revealed that chemical fertilizers are the most significant parameter in the basil production.

The objective of this study is to use a Fuzzy Analytic Hierarchy Process (Fuzzy AHP) and geograph... more The objective of this study is to use a Fuzzy Analytic Hierarchy Process (Fuzzy AHP) and geographical mapping models using Geographical Information System (GIS) to locate the most appropriate sites for solar energy farms in Shodirwan region in Iran. GIS interpolation showed that annual solar insolation in Shodirwan is very good and can be used for potential solar farm locations. The average of solar insolation in the region is 5.12 kWh/m2/day annually. Results showed that 18.25% of the Shodirwan area is exploitable as solar farms. With a conversion efficiency of 10% and area factor of 70%, annual electricity production for the exploitable area is roughly 16100 GWh. Land suitability analysis for solar farms implementation was carried out and overlay results obtained from the analysis of the resultant maps showed that 13.98% and 3.79% of the total land area demonstrate high and good suitability levels, respectively. The total electricity generation potential from both highly and good suitability levels in Shodirwan region was about 15,690 GWh annually.

The incorporation of environmental criteria into the conventional supplier selection practices is... more The incorporation of environmental criteria into the conventional supplier selection practices is essential for organizations seeking to promote green supply chain management. Challenges associated with green supplier selection have been broadly recognized by procurement and supplier management professionals. The development and implementation of practical decision making tools that seek to address these challenges are rapidly evolving. This article contributes to this knowledge area by comparing the application of three popular multi-criteria supplier selection methods in a fuzzy environment. The incorporation of fuzzy set theory into TOPSIS, VIKOR and GRA methods is thoroughly discussed. The methods are then utilized to complete a green supplier evaluation and selection study for an actual company from the agri-food industry. Our comparative analysis for this case study indicates that the three fuzzy methods arrive at identical supplier rankings, yet fuzzy GRA requires less computational complexity to generate the same results. Additional analyses of the numerical results are completed on the normalization functions, distance metrics, and aggregation functions that can be used for each method.

Physical properties of fruits and vegetables are the subject of many researches because of its im... more Physical properties of fruits and vegetables are the subject of many researches because of its importance in designing of agricultural machinery. Banana fruit is one of important fruit. In this study some physical properties of banana fruit (Cavendish variety) were determined. Properties which were measured included weight of whole fruit peel and pulp weight, dimensions, surface area and projected area. The actual surface area and projected area were measured by image processing technique. The calculated attributes were geometric mean diameter, sphericity, radius of curvature, assumed ellipsoidal volume, surface area and projected area. The diameters of fruit varied as quadratic form. High correlation was observed among assumed ellipsoidal attributes and measured properties. The highest correlation was between estimated projected area and measured projected area as R 2 = 0.978. [Mahmoud Soltani et al. Some physical properties of full-ripe banana fruit (Cavendish variety).

Journal of American …, 2011

Image Processing Techniques are being used increasingly in the field of agricultural and food pro... more Image Processing Techniques are being used increasingly in the field of agricultural and food products for quality assurance purpose. The system offers the generation of precise descriptive data and reduction of tedious human involvement. Image segmentation based on color difference between mature fruits and backgrounds under natural illumination condition is a difficult task. By processing images in three color space of RGB, HSI and YC b C r from CCD camera, tomato fruit, stems, leaves and a stem-supporting pole were recognized. Then the processed images were compared in three color spaces in order to identify ripe tomatoes with more than 50% redness. The average of error between actual number of red tomatoes and estimated number in 3 images of each 28 tomato trees was 3.85%.

In this paper, design and testing of a machine vision based raisin sorter is presented. The propo... more In this paper, design and testing of a machine vision based raisin sorter is presented. The proposed MV system consists of electronic, pneumatic and mechanical parts. The hardware is made up of a conveyor belt, eight pneumatic valves, a compressor and a control unit. The controller, which has a microcontroller as its main core, is used for the communication between the PC and the pneumatic valves via RS232 series port. By using the capture card, the camera sends images of raisins to the computer to be processed and have the raisins sorted accordingly. By a suitable combination of length and RGB color values raisins are graded it two classes. The PC sends proper commands, via the microcontroller, to actuators (valves) in order to reject defected raisins. The image processing algorithm has been implemented in Visual Basics environment. The developed program allows the user to easily configure the GUI in order to get high quality sorting results. To evaluate the performance of the sorter under various densities and impurities of raw raisins, as two factors affecting the accuracy of the sorter, some statistical tests were performed. The results of statistical analysis showed that with the existing number of valves, the optimum distance between two consecutive raisins should be 5 mm and the changes in the percentages of impurity does not have a significant effect on the overall performance of the machine on the level of 5%. Therefore, the sorter can provide a 99% pure output with less than 2% of loss.

Olive oil is one of the most important agricultural crops due to its digestive properties and eco... more Olive oil is one of the most important agricultural crops due to its digestive properties and economic status. However , olive oil production is a costly process which causes an expensive price of the final product. The most job-bery ways during olive oil production consist of mixing other oils such as maize, sunflower and soya oil into the olive oil. So, the aim of this study was to develop a dielectric-based system to detect adulteration in olive oil using cylindrical capacitive sensor. For categorizing of fake olive oil by using frequency specification, Linear Discrimi-nant Analysis (LDA) was developed. A set of 15 samples of olive oil, sunflower oil and canola oil which mixed with different ratio of adulteration, were used for calibration and evaluation of developed system. For each sample , 25 iterations were performed. Regarding results, the highest error rate was for a sample containing 60% olive oil-40% canola oil. In general, 7 iterations failed to be properly recognized. Regarding to accuracy indexes, spec-ificity and sensitivity, the system had the minimum error for a mixed sample (60% olive oil-40% canola oil), spec-ificity and sensitivity were obtained as 98% and 100%, respectively and accuracy was obtained as 72%, which was the weakest value. Finally, regarding mean value table for all sample, accuracy reached to 97%. Results showed the developed technique has a good capability of detecting impurities in olive oil. It is concluded from obtained results that the developed system revealed an acceptable adulterated detection in oil production.

The purpose of this study was to quantify the spatial and technological variability in life cycle... more The purpose of this study was to quantify the spatial and technological variability in life cycle greenhouse gas (GHG) emissions, also called the carbon footprint, of durum wheat production in Iran. Methods The calculations were based on information gathered from 90 farms, each with an area ranging from 1 to 150 ha (average 16 ha). The carbon footprint of durum wheat was calculated by quantifying the biogenic GHG emissions of carbon loss from soil and biomass, as well as the GHG emissions from fertilizer application and machinery use, irrigation, transportation, and production of inputs (e.g., fertilizers, seeds, and pesticides). We used Spearman’s rank correlation to quantify the relative influence of technological variability (in crop yields, fossil GHG emissions, and N2O emissions from fertilizer application) and spatial variability (in biogenic GHG emissions) on the variation of the carbon footprint of durum wheat. Results and discussionThe average carbon footprint of 1 kg of durum wheat produced was 1.6 kg CO2-equivalents with a minimum of 0.8 kg and a maximum of 3.0 kg CO2-equivalents. The correlation analysis showed that variation in crop yield and fertilizer application, representing technological variability, accounted for the majority of the variation in the carbon footprint, respectively 76 and 21%. Spatial variation in biogenic GHG emissions, mainly resulting from differences in natural soil carbon stocks, accounted for 3% of the variation in the carbon footprint. We also observed a non-linear relationship between the carbon footprint and the yield of durum wheat that featured a scaling factor of −2/3. This indicates that the carbon footprint of durum wheat production (in kg CO2-eq kg−1) typically decreases by 67% with a 100% increase in yield (in kg ha−1 year−1). Conclusions Various sources of variability, including variation between locations and technologies, can influence the results of life cycle assessments. We demonstrated that technological variability exerts a relatively large influence on the carbon footprint of durum wheat produced in Iran with respect to spatial variability. To increase the durum wheat yield at farms with relatively large carbon footprints, technologies such as site-specific nutrient application, combined tillage, and mechanized irrigation techniques should be promoted.

Better growing conditions are achieved in greenhouses by maintaining a higher internal ambient a... more Better growing conditions are achieved in greenhouses by maintaining a higher internal ambient as compared with external ambient temperature. A computer-based control and monitoring system which provides visualization, control and coordination of temperature and humidity in a greenhouse was recently developed. To validate the system performance, a number of experiments were carried out during the autumn of 2003. In this paper, one of the experimental results conducted from 10 to 12 a.m. on December 7, 2003, in the city of Karaj, is presented and discussed. The system was tested for two modes of operation: the uncontrolled mode of operation and the controlled mode. Four sensors, three for temperature measurements and one for relative humidity measurements, were installed inside and outside. During the first hour and a half the system was tested as a data-acquisition system, ie, only data from the sensors were recorded and monitored on the screen with no operation of fans, sprayer and other installed environmental systems in the greenhouse. For the last 20 min of the experiment, inside air temperature was controlled by the system. The result on temperature measurements shows that external ambient temperature, Tout, is always less than the inside temperature. This is attributed to the solar radiation entering the greenhouse through transparent plastic and being trapped there. We also observed fluctuations on temperature profile inside the greenhouse. This is caused by natural conditions such as surface evaporation within the greenhouse, solar radiation, external ambient temperature and rapid weather changes during the time of the experiment. It was also found that the rate of change of temperature increase in the upper part, Tup, ie near plastic cover, is higher than that of the plants height, Tmid. This rise in vertical temperature gradient is partly due to the different amount of solar incident radiation being received at the locations of sensors. This trend proves the effectiveness of our polytube system, a re- circulating fan with an attached perforated polyethylene tube, in guiding the air toward the plant root zone. For the last 20 min of the experiment, the controller was put into action. The overall per- formance of the system in maintaining the temperature within a given range, around the set point, is found to be satisfactory. The time constant of the fan and heater combination was short, about 10 min, in reaching the desired set point temperature.

A review of macroalgae production, with potential applications in biofuels and bioenergy

This review discusses biofuel and bioenergy production from seaweed, and ranges from cultivation ... more This review discusses biofuel and bioenergy production from seaweed, and ranges from cultivation to final product, and investigates opportunities, problems, advantages, disadvantages and other issues of this emerging industry. High levels of structural polysaccharides and low lignin contents make seaweed attractive feedstocks for production of liquid biofuels via fermentation and biogas production via anaerobic digestion. Since macroalgae can be grown in water (oceans and lakes), they will not compete with land-based crops, and thus will not be in competition with human foods. And biofuel and bioenergy production from macroalgae has some environmental benefits. Electricity produced from biogas derived from macroalgae can be cost-competitive to solar thermal, solar photovoltaic and biomass generated electricity. Biofuel and bioenergy production from macroalgae, however, will entail higher costs than terrestrial biomass feedstocks due to higher costs of cultivation and higher costs to remove harmful content such as sulfur and nitrogen from the resulting fuel or heavy metals from the residues. Economic production of biofuels and bioenergy will be available by increasing the scale and efficiency of production of this emerging resource.

Computers and Electronics in Agriculture, 2012

In this study, quality grading of raisins using image processing and data mining based classifier... more In this study, quality grading of raisins using image processing and data mining based classifiers was investigated. Images from four different classes of raisins (green, green with tail, black, and black with tail) were acquired using a color CCD camera. After pre-processing and segmentation of images, 44 features including 36 color and eight shape features were extracted. Correlation-based feature selection was used to select best features for grading the raisins. Seven features were found superior. To classify raisins, four different data mining-based techniques including artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs) and Bayesian networks (BNs) were investigated. Results of validation stage showed ANN with 7-6-4 topology had the highest classification accuracy, 96.33%. After ANN, SVM with polynomial kernel function (95.67%), DT with J48 algorithm (94.67%) and BN with simulated annealing learning (94.33%) had higher accuracy, respectively. Results of this research can be adapted for developing an efficient raisin sorting system.

Principles and Applications of Light Backscattering Imaging in Quality Evaluation of Agro-food Products: A Review

Food and Bioprocess Technology, 2012

Abstract In recent years, due to the increasing consciousness of quality in the food and health s... more Abstract In recent years, due to the increasing consciousness of quality in the food and health sector, much progress has been made in developing non-invasive techniques for the evaluation or inspection of internal qualitative parameters of fruits, vegetables, and processed foodstuffs considering, eg, moisture content, soluble solid content, acidity, and mechanical properties. This paper reviews the theoretical and technical principles as well as the recent achievements and applications of light backscattering imaging for ...

Data mining-based wavelength selection for monitoring quality of tomato fruit by backscattering and multispectral imaging

International Journal of Food Properties, 2014

ABSTRACT The aim of this research was to predict quality factors of tomato fruit during storage u... more ABSTRACT The aim of this research was to predict quality factors of tomato fruit during storage using backscattering and multispectral imaging techniques. To gather the required information for developing prediction models, batches of 200 tomatoes (cv. Pannovy) harvested at two maturity stages, were stored at standard condition up to four weeks. During storage, the modulus of elasticity, moisture content (MC), soluble solid content (SSC), titratable acidity (TA), hyperspectral data, and backscattering images were acquired on forty tomatoes at regular intervals of one week. After extracting the spectral data from forty points on each sample, they were subjected to preprocessing operations. Several feature selection techniques, including filter (ReliefF, Fisher-Score, and t-Score) and wrapper (genetic algorithm) methods were used to find the sensitive wavelengths for each fruit quality parameter. With the novel strategy used, the wavelengths found by the fusion of genetic algorithm and t-Score techniques showed good prediction performance for all considered qualitative parameters. In order to verify the usefulness of selected wavelengths, backscattering and multispectral imaging techniques were applied. The ANN produced the calibration models which gave a reasonably good correlation for estimating the modulus of elasticity, SSC and TA at 660 nm and MC at 830 nm of tomato from backscattering images. The correlation coefficient between the multispectral and backscattering imaging prediction results and reference measurement results were 0.952 and 0.891 for modulus of elasticity, 0.727 and 0.539 for MC, 0.736 and 0.561 for SSC, and 0.811 and 0.706 for TA, respectively. It can thus be concluded that proposed wavelength selection strategy is potentially useful for assessing quality of horticultural products by multispectral and backscattering imaging techniques.

Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging

Computers and Electronics in Agriculture, 2013

ABSTRACT Light backscattering imaging is an advanced technology applicable as a non-destructive t... more ABSTRACT Light backscattering imaging is an advanced technology applicable as a non-destructive technique for monitoring quality of horticultural products. Because of novelty of this technique, developed algorithms for processing this type of images are in preliminary stage. The present study investigates the feasibility of texture-based analysis and coefficients from space-domain analysis to develop better models for predicting mechanical properties (fruit flesh firmness or elastic modulus) of horticultural products. Images of apple, plum, tomato, and mushroom were acquired using a backscattering imaging setup capturing 660 nm. After segmenting the backscattering regions of images by variable thresholding technique, they were subjected to texture analyses and space domain techniques in order to extract a number of features. Adaptive neuro-fuzzy inference system models were developed for firmness or elasticity prediction using individual types of feature sets and their combinations as input for prediction model applicable in real-time applications. Results showed that fusion of the selected feature sets of image texture analysis and space domain techniques provide an effective means for improving the performance of backscattering imaging systems in predicting mechanical properties of horticultural products. The maximum value of correlation coefficient in the prediction stage was achieved as 0.887, 0.790, 0.919, and 0.896 for apple, plum, tomato, and mushroom products, respectively.

Computers and Electronics in Agriculture

Journal of Cleaner Production, 2013

Energy, 2011

Journal of American …, 2011

A review of macroalgae production, with potential applications in biofuels and bioenergy

Computers and Electronics in Agriculture, 2012

Principles and Applications of Light Backscattering Imaging in Quality Evaluation of Agro-food Products: A Review

Food and Bioprocess Technology, 2012

Data mining-based wavelength selection for monitoring quality of tomato fruit by backscattering and multispectral imaging

International Journal of Food Properties, 2014

Analysis of texture-based features for predicting mechanical properties of horticultural products by laser light backscattering imaging

Computers and Electronics in Agriculture, 2013

Implementation of tractors in agriculture is Substantial as a power supply. Therefore, performanc... more Implementation of tractors in agriculture is Substantial as a power supply. Therefore, performance model for developing parameters of tractors and implements are major for farm machinery, operators and manufacturers alike. The objective of this study was to assess the predictive capability of several configurations of ANNs for performance evaluating of tractor in parameters of drawbar power, rolling resistance and tractive efficiency. A conventional tillage system which included a moldboard plow with three furrows was used for collecting data from MF285 Massey Ferguson tractor. To predict performance parameters, ANN models with back-propagation algorithm were developed using a MATLAB software with different topologies and training algorithms. For drawbar power. The best result was obtained by the ANN with 6-7-1 topology and Bayesian regulation training algorithm with R 2 of 0.995 and MSE of 0.00024. The obtained result showed that the 6-7-1structred ANN with Levenberg-Marquardt training algorithm represents a good prediction of TE with R 2 equal to 0.989 and MSE of 0.001327. The obtained results confirmed that the neural network can be able to learn the relationships between the input variables and performance parameters of tractor, very well.

Due to the ascending significance of energy in the world, prognostication and optimization of Fue... more Due to the ascending significance of energy in the world, prognostication and optimization of Fuel Consumption (FC) in agricultural works is merit to consideration. Therefore, performance model for evolving parameters of tractors and implements are essential for farm machinery, operators and manufacturers alike. A conventional tillage system which included a moldboard plow with three furrows was used for collecting data from MF285 Massey Ferguson tractor. Field experiments were carried out in the experimental farm of Agricultural Engineering Department of Tehran University, Karaj province, Iran, which had loamy soil texture. The objective of this study was to assess the predictive capability of several configurations of ANNs for performance evaluating of tractor in parameter of fuel consumption. To predict performance parameters, ANN models with back-propagation algorithm were developed using a MATLAB software with different topologies and training algorithms. The ANN model with 6-7-1 structure and Levenberg-Marquardt training algorithm had the best performance with R 2 of 0.969 and MSE of 0.13427 for TFC prediction. The 6-8-1 topology shows the best power for prediction of AFC with R 2 and MSE of 0.885 and 0.01348, respectively. Also, the 6-10-1 structure yielded the best performance for prediction of SFC with R 2 of 0.935 and MSE of 0.012756. The obtained results promoted that the neural network can be able to learn the relationships between the input variables and fuel consumption of tractor, reliable.

In this paper, an artificial neural network based system, is presented to separate closed pistach... more In this paper, an artificial neural network based system, is presented to separate closed pistachio nuts from the open ones in the real-time. This intelligent system includes a feeding
part, an acoustical recognition part, and a pneumatic air rejection mechanism. Features of
pistachio nut types are extracted by analysis of sound signal in both time and frequency domains through fast Fourier transform, power spectral density, and principal component
analysis methods. These features are used as input vector to LVQ models, and various LVQ
learning algorithms, including LVQ1, OLVQ, LVQ4.a are evaluated. Further, the performance of the LVQ-based system is compared with those systems using MLP. The best performance is obtained through LVQ4.a algorithm; that is the correct separation
rates for closed shell and open shell ones are 96.5% and 96.83%, respectively and overall 96.67%. The designed system due to its non-destructively, does not cause any damage to the
kernels of open shell pistachios.

This paper has evaluated the ability of ultrasonic sensors in producing guidance signals for gree... more This paper has evaluated the ability of ultrasonic sensors in producing guidance signals for greenhouse applications robots. At first one high quality ultrasonic sensor was selected and some basic experiments were done. Experiments results showed that with predetermined internal parameters, accuracy of selected sensor was good in distances between 15 to 215cm and angles between 0 to 30 degrees. The maximum width of view of each sensor was 17.15cm for flat surfaces and 33.20cm for round surfaces. According to these results, final configuration of sensors around the robot was determined. With designed averaging algorithm it was possible to calculate the averages of orientation and position with high accuracy from ultrasonic sensors outputs. Also, in comparing with reference sensors data, the maximum error and RMS for orientation and position were 11.23 deg, 4.036 deg and 3cm, 0.714cm respectively.

The current study evaluates the potential of hyperspectral imaging combined with artificial neura... more The current study evaluates the potential of hyperspectral imaging combined with artificial
neural networks to predict the moisture content in tomato fruit and to obtain spatial
distribution maps. A total of 192 tomato samples, Solanum lycopersicum 'Pannovy', were
harvested in the third and fourths stage of ripening according to the OECD color chart.
Samples were immediately transmitted to the laboratory and stored at 15°C and 92% rH.
Measurements were carried out after 1, 8, 15, 22, and 30 days of storage. After acquisition of
hyperspectral images of 40 tomatoes on each date, moisture content of samples was
calculated after oven drying (105°C). The electromagnetic spectrum between 400 to 1000
nm was recorded at 495 passbands by a hyperspectral imaging system. After applying
preprocessing operations and removal of data in saturation, valid data sets were collected
manually from the region of interest. Spectral dimensionality was reduced by selecting the
wavelengths in which high correlation exists between the spectral data and fruit moisture
content. A multilayer percepteron neural network has been trained with training dataset to
predict the moisture content of samples. To prepare the spatial prediction maps, tomato
samples were separated from the background. After that, 2D images were unfolded to
vectors and the intensity values of each pixel in the selected wavelengths were fed into the
fully trained neural network. The output matrix, containing the predicted values of moisture
content in every pixel, was folded back to form a 2D matrix with the same spatial dimension
of the hyperspectral images. Finally, the spatial distribution of moisture content was
displayed as a color map, where colors represent different values of predicted attribute. Results proof the feasibility of the method for characterizing the spatial distribution of an attribute in horticultural produce.

Forecasting meteorological behaviors are often needed for solar energy applications, particularly... more Forecasting meteorological behaviors are often needed for solar energy applications, particularly in design methods, in system characterization and in decision making for renewable energy management. In this study, a neuro-fuzzy system called ANFIS is used to forecast mean daily solar radiation ( D R ) in Alborz province of Iran. To design ANFIS models, meteorological data for the year 2008 were collected from the IRIMO data center. Input variables were maximum temperature, relative sunshine duration and extraterrestrial solar radiation. The best result was obtained with triangular membership functions (MF) for the input variables and linear type as output MF. For this model R, RMSE, MAE and MAPE were 0.98, 0.84, 0.69 and 5.3%, respectively. The forecast accuracy which is the measure of how close the actual is to the forecasted D R was 94.7%. Results showed that ANFIS can be successfully used for forecasting D R in the region and may be adopted with minor modification for any other location.

According to the growing population and shortage of fossil energy and the need for utilization of... more According to the growing population and shortage of fossil energy and the need for utilization of alternative energy sources is felt. One of the most accessible and renewable energy is solar energy which can be used as an alternative to fossil fuels to eliminate concerns about the environmental pollution caused by such fuels. Flat plate solar collectors are the major component in a water heating system and thermally optimized operation of the whole system has a considerable impact. One of the important factors determining the performance of a solar collector is the fluid flow rate. Therefore, in this study the performance of flat plate solar collector at three different flow rates of 3, 4 and 5 liters per minute was experimentally evaluated. The most efficient rate at four liters per minute flow rate was equal to 53.5% and at three and five liters per minute were, respectively, 50.46% and 46.35%. The highest received power from by the collectors at the four liters per minute was equ...

Renewable energy has important advantages compared to fossil energy. It produces minor or no poll... more Renewable energy has important advantages compared to fossil energy. It produces minor or no pollutant gases emission. Unlike fossil fuels, renewable energy sources are not limited and are available in all countries in various forms. The availability of renewable energy and solar power is that it can be used in a different form. In this study, received the power and efficiency of flat plate solar collector on the weather sunny, cloudy and overcast rainy examined. Based on the results, the flat plate collector was most efficient on a cloudy rainy day (with an efficiency 61.61%) and had the lowest yield on a sunny day (with an efficiency of %51.66), While the maximum amount of power from the system for a sunny day was 1046.5 W and the lowest power out from the system for a rainy cloudy day was 326.5 W.

Classification is vital for the evaluation of agricultural produce. However, the high costs, subj... more Classification is vital for the evaluation of agricultural produce. However, the high costs, subjectivity,
tediousness, and inconsistency associated with manual sorting have been forcing the post harvest industry
to apply automation in sorting operations. In this study, Fuzzy Logic (FL) was applied as a decision making
support to grade apples. Features such as color and size were measured through webcam. The same set of
apples was graded by both human expert and a fuzzy logic system designed for this purpose. For input and
output variables of the fuzzy logic system, triangular and trapezoidal membership functions were applied.
Totally, 125 rules with logical operator of “AND” and mamdani inference system for decision making and
the centroid (Center of Gravity (COG)) method for defuzzification was applied. For determination the
degree of membership of apples, the trial and error method was done. The algorithm was designed, can
capture an image from apples under the black box, and extract some features and then compare these
features with reference input, and determine the grade of apples. Grading results obtained from fuzzy logic
showed 90.8 % general agreement with the results from the human expert.

The purpose of this study was to evaluate feasibility of near infrared (NIR) spectroscopy with fi... more The purpose of this study was to evaluate feasibility
of near infrared (NIR) spectroscopy with fibre optic probe for
predicting fatty acids profile of Beluga caviar. Measurement was performed on 100 samples of Beluga. The wild caviar samples caught sturgeon comprised Huso huso. NIR calibrations were developed using partial least square regression (PLSR). Selected models for the estimation of fatty acids in this specie of caviar exhibited coefficients of determination for cross validation which ranged 0.81-0.91 % with root mean square errors of (RMSE) between 2.1 and 3.0. This information suggested that in general, NIR interactance spectroscopy could provide an opportunity to measure fatty acids contents of caviars.

Color Feature Extraction by Means of Discriminant Analysis for Weed Segmentation

2004, Ottawa, Canada August 1 - 4, 2004, 2004

Computer Applications in Engineering Education, 2011

In this article, a distributed architecture that allows remote control and monitoring of horticul... more In this article, a distributed architecture that allows remote control and monitoring of horticultural cool storage (HCS) is presented. The various stages in the design and implementation of system for monitoring temperature and relative humidity and controlling HCS environment conditions are presented and discussed. The required hardware include a microcontroller and accompanying electronic circuitry, a server computer, serial port, temperature and relative humidity sensors and two actuators. Microcontroller transfers the sensors data to the server via serial port. Both the client and the server side programs are coded in VB programming language. They use VB MSComm control in order to communicate with the microcontroller. Internet communications is relied on socket programming. Winsock is used for network communications via the TCP/IP protocol. Sockets are configured to listen to a data port or to connect and then transmit to a remote one. Consequently information can be easily and reliably transmitted, monitored and/or controlled by the two machines. The performance of system was evaluated for 2 weeks and the results were quite satisfactory. This system can be easily adapted in other agricultural facilities such as greenhouses and silos. ß

Agriculture sectors as the most momentous food producer sector is known not only energy consumer ... more Agriculture sectors as the most momentous food producer sector is known not only energy consumer but also energy supplier. Energy utilization as a helpful key is considered to analysis and evaluation of sustainability of agriculture. In this research which was done in the western part of Isfahan, energy consumption of potato (Agria type) was determined in three various levels of cultivated areas (a) less than one hectare, one to five hectares (b) and more than five hectares (c). For this purpose, the data were collected randomly from 320 potato farmers by using face -to-face questionnaire method. The results of this research showed that the most part of the input energy which is consumed was related to fertilizer. N fertilizer which is consumed in 80% of these cases had the major role. After that, seeds, fuel consumption and irrigation have respectively the most important role in energy consumption. The least ratio of energy consumption was related to pesticides. The total energy equivalents of inputs were 51.46 GJ/ha, 45.71 GJ/ha and 43.83 GJ/ha respectively for fields classified as "a", "b" and "c" and also energy ratio were determined to be 1.3, 1.75 and 2.08. It seems that as the farm gets bigger and increase the use of technology (increase the level of mechanization and degree of mechanization) in farms, one can increase productivity and efficiency of economy and energy. Also in this research the effects of various type of planting, cultivating and harvesting, also type of tractors were evaluated on energy indexes. Further results indicated that in variable cultivation areas, 88.5% of the total energy was in non-renewable energy forms, and only 11.5% was in renewable forms. Therefore, using such useful pattern (bigger field) which can help us to use our farm and energy in a better way is vital.

In new agriculture, with agricultural mechanization development and available softwares, decision... more In new agriculture, with agricultural mechanization development and available softwares,
decision making systems, intelegent decision making is an easy process for advanced farmer.
Objective of this study is to use analytical hierarchy process, AHP, technique in selecting
appropriate combine type from four common combine type Class, John deere 955, Sahand and
Kordestan Reaper in the harvesting operation in the Yazd province. The AHP supports the group
decision-making process and the use of ergonomic criteria with different and incommensurable
metrics. Criterions of this study included: machine losses, safety and driver’s welfare, the costs of
repairment and maintenance and road traffic. Data analyzed with Expert Choice software version 11. Results indicated from the parameters that Class combine is the most approperiate harvesting machine.

The objective of this paper is to calculate of economic indices of broiler farms and analysis of ... more The objective of this paper is to calculate of economic indices of broiler farms and analysis
of the effects of grower’s literacy and experience on Benefit to Cost Ratio (BCR). Data was obtained
from 44 growers using a face-to-face questionnaire method. Questionnaire was included the effects
of literacy in three levels and experience in four levels, and also the calculation of BCR. The results
indicated that a mean BCR, variable costs and total income were calculated as: 1.38, 3506.29 /1000birdsand4995.49/1000birds and 4995.49 /1000birdsand4995.49/1000birds, respectively. The ANOVA results indicated that the grower
literacy had significant effect on BCR (P<0.01) and level 2 (diploma degree) had the highest BCR.
The Growers’ experience had significant effect at 5% level and level 4 (more than 20 years experience) on the highest BCR, respectively. Growers with more experiences had an effective management with the costs involve and inputs were applied more properly.

The aim of this study was to examine the energy inputs and outputs for the broiler production far... more The aim of this study was to examine the energy inputs and outputs for the broiler
production farms in Alborz province, Iran. A non-parametric data envelopment analysis
(DEA) technique was used to determine the energy efficiency of broiler production farms.
Data used in this study were obtained randomly from 30 poultry production farms using a
face to face questionnaire method during October-December 2013. The results indicated
that total input energy was 189805.48 MJ/(1000 bird), while the output energy was
28151.17 MJ/(1000 bird). Net energy is negative, -161654.31 MJ/(1000 bird), indicating that
in the broiler production, energy is being lost. Also, the energy use efficiency (energy ratio)
was calculated as 0.15, showing the inefficiency use of energy in the broiler production. The
fuel energy (energy content of the fuel) by 58.35% had the highest value of input energy and
the feed energy by 29.71% was next. Two basic input-oriented DEA models, namely, CCR and
BCC, were adopted to optimize the energy inputs in this study. The average values of
technical efficiency, pure technical efficiency and scale efficiency of broiler farms were
computed as 0.90, 0.93 and 0.96, respectively. The analysis of DEA results showed that the farmers could save up to 62% in fuel consumption and 22% in electricity without any reduction in output by adopting the recommendations based on the present study.

Modeling and prediction of environmental indices of potato cultivation with application of adaptive neuro-fuzzy inference system and life cycle assessment

The aim of this research was the automatic spraying of plants in greenhouses. A threewheel differ... more The aim of this research was the automatic spraying of plants in greenhouses. A threewheel differential steering vehicle was designed and built to act as an autonomous greenhouse sprayer robot. Power was transmitted from two DC motors to each wheel through a gearbox. Six ultrasonic sensors were used to produce guidance signals in order to determine the position and orientation of the vehicle. Both fuzzy logic and proportional controllers were developed and tested to control the left and right motors, which navigate the vehicle through the aisle using range information provided by ultrasonic sensors. A series of experiments were performed to evaluate the accuracy of the ultrasonic sensors and determine the best arrangement of the sensors around the chassis of robot. After designing and fabricating, the vehicle was tested on concrete surfaces using two positions of driver wheels and three speeds (15, 25 and 35 cm/sec) inside a greenhouse along a straight aisle with 115 cm width. At first the vehicle performance was evaluated for the driver wheels at front (DWF) mode with two types of controllers and the best controller was determined. After that the vehicle performance was evaluated for the driver wheels at rear (DWR) mode with the best controller, and the best position for the driver wheels was determined. Final tests were conducted on concrete surfaces using the best position of the driver wheels and with the best controller at three speeds inside a greenhouse along a U-shaped path with 98 cm width. Also the spraying, safety and obstacle detection units of the vehicle were evaluated. According to the result of USS3 ultrasonic sensors evaluation tests, the best detected distance ranges of the sensors were 15 to 200 cm. In distances less than 15 cm and angles more than 30 degrees the accuracy was found to be low. In comparing with reference sensors, the maximum error and RMSE for positions were 3 cm and 0.714 cm and for orientation were 11.23 cm and 4.036 cm, respectively. Vehicle evaluation tests showed that the proportional controller performed better than the FLC at all speeds. So the proportional controller was selected as final controller of the vehicle. By increasing the speed, RMSE of the vehicle position increased. The average RMSE of the vehicle position error was between 6.42 and 10.80 cm in the DWF mode but the average RMSE of the vehicle position error was between 6.55 and 7.66 cm in the DWR mode at different speeds. So the DWR mode was selected as the best structure of the robot. Second greenhouse tests showed that the average of RMSE of the vehicle position error was between 4.93 and 6.51 cm in the DWR mode at different speeds with the proportional controller. By increasing the speed, RMSE of the vehicle position error was increased. The performance of safety and central station units of the vehicle were acceptable. The accuracy of spraying unit in "spraying" was 99.47 % and in "not-spaying" was 99.92 % that are acceptable for greenhouse applications.

Greenhouse is a growing business in many countries around the world. However, the amount of energ... more Greenhouse is a growing business in many countries around the world. However, the amount of energy used in greenhouse crop production is very high. The province of Tehran is the main greenhouse production area in Iran. Today, about 34% of greenhouse crops production in Iran is provided from this province. Share of this province in greenhouse vegetable production within Iran was about 16% in 2007 with 642.2 ha greenhouse vegetable growing area. Cucumber and tomato are the major produce in the studied region. Data used in this project were collected from 43 greenhouses in the city of Hashtgerd through a face-to-face questionnaire performed during 2008-2009 cultivation season. Data analysis and evaluation of greenhouses decision making units (DMUs) were done by DEA technique using DEA-Solver software. Both input-oriented CRS and VRS models (known as CCR-I and BCC-I, respectively.), were examined. An attempt was also made to develop a decision support system for automating the evaluation of the producers. The program allows users to input data and do the mentioned DEA analysis on them. This software has been designed with Visual Basic for Application (VBA) which reads the data from Excel and returns the results to worksheet for further investigation. It was found that the total energy inputs for cucumber and tomato were 152908.43 and 130386.72 MJ/ha, respectively. The energy use for the production of one kilogram of cucumber and one kilogram tomato were found 1.57 and 0.7, respectively. The most important inputs in cucumber production were diesel fuel, chemical fertilizer and electricity, and in tomato production were diesel fuel, chemical fertilizer and human power. The results showed that the most energy consuming input for cucumber and tomato productions in the studied greenhouses was diesel fuel. Common factors of energy productivity, net energy, energy intensiveness and energy efficiency were also calculated and reported for both products. From DEA analyses based on CCR-I and BCC-I models it was found, respectively, 6 and 10 cucumber greenhouses were found efficient with technical efficiency of one. In the case of tomato production, 6 and 8 of greenhouses were found efficient. Technical efficiency, pure technical efficiency and scale efficiency for cucumber and tomato production units were (0.87, 0.96 and 0.90) and (0.74, 0.92 and 0.69), respectively. The most efficient cucumber and tomato greenhouses were DMU3 and DMU25 which are referred 7 and 16 times. After determining the input slacks, DMU15 among the cucumber greenhouses and DMU17 among the tomato greenhouses, which were both inefficient, could reduce their energy inputs by 54% and 96.3%, respectively, by adjusting their inputs.

In Grading systems provide many information about fruits such as size, color, shape, defect, and ... more In Grading systems provide many information about fruits such as size, color, shape, defect, and internal quality. Among them, color and size are the most important features for accurate classification and/or sorting of citrus such as oranges, lemons and sweet lemons. Basically two inspection stages of the system can be identified: external fruit inspection and internal fruit inspection. External inspection is accomplished through processing of color CCD images while internal inspection requires special sensors for sugar and acid content. In order to devise a multiproduct inspection system for citrus fruits through machine vision, an efficient algorithm was developed and implemented in Visual Basic environment. The proposed system consists of two CCD cameras, two capture cards, an appropriate lighting system, a personal computer and other mechanical parts. The algorithm initially extracts the fruit image from the background. The samples of any grade of fruits are situated in front of the cameras then calibrated off-line and then the HSI color values and volume are extracted and saved in a database. Next, during grading stage, the online images of fruit in front of cameras are captured and HSI color values and volume of them are determined. By comparing the information during grading phase with available information in the database, the final grade of citrus fruits is determined. To evaluate the accuracy of determined volume by system, obtained values is compared to actual volume of citrus fruits determined by water displacement method using the paired t-test and the Bland-Altman approach. The R 2 values for orange, lemon, sweet lemon and tangerine were 0.985, 0.962, 0.97, and 0.96, respectively. The corresponding Bland-Altman 95% limits of agreement for comparison of volumes with the two methods were (-6.54; 6.84), (-1.62; 1.74), (-7.20; 7.57) and (-4.83; 6.15), respectively. Grading results obtained from the developed machine vision system showed 88.05%, 94.04% and 88.18% accuracy for orange, lemon and sweet lemon, respectively, with the results from the human expert. This system can be easily adapted for grading other axi-symmetric agricultural products such as pear, onion, carrot, etc.

In this research, a feeder unit for feeding pistachio nuts one by one to an acoustic pistachio so... more In this research, a feeder unit for feeding pistachio nuts one by one to an acoustic pistachio sorter was designed, developed and evaluated. This mechanism includes a hopper, cellular conveyor belt and a brush to single pistachio nuts. Pistachio nuts after leaving the hopper and placement in cells of the conveyor belt, move toward the brush. The brush has an opposite direction of rotation to the conveyor belt and push aside extra pistachio nuts. Hence it permits only pistachio nuts that sitting in cells of conveyor belt to pass. The evaluation part of this research has two sections: feeder evaluation and sorter performance evaluation. Feeder evaluation has been done with a factorial experiment in a completely randomized design using 3 levels of conveyor belt speeds (30, 45 and 60 rpm), 3 levels of conveyor slope angles (0, 15 and 30 degree) and 2 levels of brush speeds (75 and 150 rpm). The measured factors were: number of empty cells in conveyor belt, number of cells containing two pistachio nuts and the position of pistachio nuts after dropping. The results showed that when the conveyor belt speed, slope angle and brush speed were 45 rpm, 0 degree and 150 rpm, respectively, the number of empty cell of conveyor belt was least and when they were 30 rpm, 30 degree and 150 rpm, respectively, the number of cells that containing two pistachio nuts were least and when they were 30 or 45 rpm, 15 degree and 150 rpm, respectively, number of pistachio nuts that fall out the sound generation unit were least. The sorter was evaluated using Ahmad Aghaie pistachio nut variety. After data collection by automatic feeder in 3 levels of dropping high (15,25 and 35 cm) and using PCA method, 18 features were extracted for separating pistachio nut type. The optimal model was selected after several evaluation based on minimizing of mean square error (MSE), coefficient of correlation and correct separation rate. The optimal ANN model for this system had a 18-20-2 configuration. The total system accuracy for the pistachio split types (open-shell, closed-shell) were 96.67% and 91.67%, respectively.

In this research, we developed prediction models for describing moisture content and drying rate ... more In this research, we developed prediction models for describing moisture content and drying rate of pistachio nuts using artificial neural network (ANN) method. For this purpose, Akbari variety of pistachio nuts were selected and required experiments were performed using a thinlayer experimental dryer at five drying air temperature (40, 50, 60, 70, and 80 o C) and four air flow velocities (0.5, 1, 1.5, 2 m/s) with three replicates. Initial moisture content for all experiments was about 30 % d.b. Data obtained from the experiments were transferred to artificial neural network medium and analyses were then carried out by using NeuroSolutions V.5. In order to develop ANN models we used error back-propagation with momentum algorithm. First, experimental data were randomly divided into three sets: training, validating and testing sets. The data contained in the three divided sets were 70, 10, and 20%, respectively. The ANN models were designed and trained as two, three, and four layers. The highest coefficient of determination (R 2 ) and least mean squared error (MSE) were considered as criterion for selecting the best network. The network having three layers with a structure of 1-5-8-3 had the best results in predicting moisture content of pistachio nuts. This network has two hidden layers with 8 neurons in the first hidden layer and 5 neurons in the second hidden layer. For this configuration, R 2 and MSE were 0.9989 and 4.2E-6, respectively. Modeling of pistachio's drying rate as dynamically and statically ANNs were also investigated. In the former case, a network of two layers with a structure of 1-16-4 led to the best results. For this configuration, R 2 and MSE were 0.9920 and 9.61E-6, respectively. In the latter case, a network consisting of three layers with a structure of 1-3-7-5 presented the best results. For this configuration, R 2 and MSE were 0.9895 and 9.93E-6, respectively. The models developed in this thesis can be useful in designing the industrial dryers.

In this research, a hybrid separation system, based on acoustic and artificial neural networks (A... more In this research, a hybrid separation system, based on acoustic and artificial neural networks (ANNs) techniques, was developed to separate pistachio nuts with closed shells from those with open shells in real-time. This intelligent system includes a feeding part, an acoustical recognition part, and a pneumatic air rejection mechanism. Features of pistachio nut shell types were extracted from analysis of sound signal in both time and frequency domains by means of fast Fourier transform (FFT), power spectral density (PSD) and principal component analysis (PCA) methods. Altogether seven features were extracted by PCA of amplitude and PSD features. With these features, we could successfully perform the separation task. In developing the ANN models, different ANN architectures, each having different numbers of neurons in hidden layer, were evaluated. The optimal model was selected after several evaluations based on minimizing of mean square error (MSE), correct separation rate (CSR) and coefficient of correlation (r). The optimal ANN model for the sorter was of 7-12-2 configuration. CSR of proposed optimal ANN model for three pistachio split types, closed shell, open shell and thin split were 96.7%, 97.3% and 93.1%, respectively. The developed system because of none destructivity, does not cause damage to kernels in open shell pistachios, and does not cause rejection by the consumer. Hence it can boost the exports. Classifying four different varieties of Iranian pistachio nuts, namely, Kaleghouchi (Ka), Akbari (Ak), Badami (Ba) and Ahmadagaee (Ah) was also performed by the proposed system. Features of pistachio nut varieties were extracted from analysis of sound signal in both time and frequency domains by means of FFT, PSD and PSD methods. Altogether forty features were selected as input vector to ANN models. Selected optimal ANN for classification was of 40-12-4 configuration. CSR of proposed optimal ANN model for four pistachio varieties, Ka, Ak, Ba and Ah were 96.97%, 97.64%, 96.36% and 99.10%, respectively. Net weight average of system accuracy was found to be 97.51%.

In this study, fuzzy logic is applied as a decision support system to grade Golden Delicious appl... more In this study, fuzzy logic is applied as a decision support system to grade Golden Delicious apples. Features such as color and size are measured through a data acquisition system consisted of apple's sorter, illumination chamber, webcam [with 2.1 MP resolution] and a PC [a 2.8GHz Pentium 4 with 768MB of RAM]. A total of 250 apples are investigated. The selected apples were of five different sets or grades ranging from very bad to very good. In order to find the performance of proposed fuzzy inference system (FIS) the same sets were graded by human expert, too. For input (color and size) and output (apple grade) fuzzy linguistic variables of the FIS, triangular and trapezoidal membership functions are selected. Totally, 125 rules with logical AND operator, Mamdani implication, and center of maximum method for defuzzification are employed to develop an efficient fuzzy expert system for decision making about apple grades. The algorithm is implemented in visual basic 6 environment in 1825 lines of program. The developed VB program can automatically capture image of each apple and extracts its RGB color and size features. The software generates all the 125 rules by comparing these features with the reference input. The rules are then exported to MATLAB for further investigation about precision of algorithm. These tests were conducted on two ways s i.e. off-line and on-line. Grading results obtained from our developed FIS scheme shows 91.2% and 95.2% agreement for off-line and online methods, respectively, with the results from the human expert. These show the good correlation between the results obtained from the FIS tests and human expert tests. Therefore, based on these results the automatic apple sorter can be designed and constructed.

Harvesting Wheat by mechanical means using combine is one of farmers important concern. Although ... more Harvesting Wheat by mechanical means using combine is one of farmers important concern. Although many people know combine but only few know how it works. In working with combine, the driver must know basic rule of working with combine, working of different parts, correct adjustments of different sections and how to reduce grain loss and increase harvesting efficiency. Grain loss in the cleaner section is mostly due to low air flow in the downhill and high air flow in the high hill. In this research, a system for automatic adjustment of fan speed according to ground slope was designed and implemented. In this system a magnetic sensor is used to measure fan speed. A noble mechanism for measuring ground slope together with a wire potentiometer is used. A 3 HP electromotor for providing necessary power is selected. An electronic circuit consist of an Op-Amp , relay , contactor ,etc was designed to adjust fan speed according to ground slope .Another circuit in order to display speed and slope is implemented using a 8051 microcontroller . This circuit consists of a microcontroller, an ADC and LCD display. With design and installing this system, in the combine many of the formentioned problems facing combine driver can be avoided.

Rice is one of the most important agricultural products. Because of the importance of rice cracki... more Rice is one of the most important agricultural products. Because of the importance of rice cracking in milling process, precision control of drying condition is important. For control of drying it is necessary with determination of drying kinetics; obtain the moisture change during the drying process. In this thesis, first a thin layer dryer was designed and made. This dryer have a centrifugal fan for blowing air, four electrical heaters for heating drying air and two humidity and temperature sensors for measuring air conditions. An AT89S52 microcontroller used to connect sensors with computer. Microcontroller transfer data to computer via serial port (RS232) and simultaneously it may receive control signals for regulating drying air temperature. A program written in VB6.0 was developed to carry out control and monitoring processes. Drying experiment were conducted at inlet temperature of drying air of 30,40,50,60 and 70°C and air velocity of 0.25, 0.5, 0.75 and 1 m/s and three replications with initial moisture content of %25 db. During the drying the weight of samples measured by a digital balance -that connected to computer via serial port-every 5 seconds. Drying curves obtained from the experimental data were fitted to 9 different empirical thin layer models and compared with 3 statistical parameters. Results shows that Two term model predict moisture change in drying with higher accuracy than other models.

Final quality and maximum time of Duration storing of agricultural materials in a cool storage de... more Final quality and maximum time of Duration storing of agricultural materials in a cool storage depends on their maintaining conditions. The most important control parameters in cool storage are temperature and relative humidity of the cool storage environment. Technological progress and increase in data transferring speed are opened new horizons for use of Internet for monitoring and control of agricultural process. Monitoring and control of processes via Internet not only control the process more accurately but also remove time and place restrictions, decrease human label, decrease costs and consequently increase final quality and efficiency. In this thesis the design and evaluation of a remote monitoring and control system based on microcontroller in agricultural cool storage via Internet is performed. First, temperature and relative humidity data are collected by sensors in cool storage environment. Then the data are transferred to the programmed microcontroller by means of a RS232 serial port. Control commands from the server computer by means of serial port transferred to microcontroller and consequently control a humidifier and the motor of cool storage. In addition, data gathered from sensors and ability of control of cool storage can be done by any client via Internet.

Pages 103 , 2005 JULY , ABBASGHOLIPOUR . M : BY

Boom sprayers are popular in Iran which are used for spraying in fields. Nowadays these sprayers ... more Boom sprayers are popular in Iran which are used for spraying in fields. Nowadays these sprayers are made in various size and dimensions. Boom sprayers all have high volume tank and wide booms and high flow rates performance.Therefore with notice to the importance environmental protection, spray deposit homogeneity, reduce spraying costs, in addition to provision for ease of work, applying new control systems to flow rate control is seem necessary. In this thesis we studied the design and implementation of a monitoring and electronic control system for TF400 model rear tractor mounted boom sprayer. This type of sprayer is used very often throughout Iran for spraying wheat, barley, potato, corn fields and even landscape itself. It has a tank with 440 liters capacity, a pistons pump that produce 20 bar pressure, three boom pieces, having a total of 8 meters length and 16 nozzles and a pressure regulator including three valves for letting/stoping flow to boom sections. In conducting research and analysing the equipment to know the most important parameters effective for optimal operation, we found out the flow rate related to pump specifications, connecting pipes length, pressure control valve, valves and size of nozzles are most important parameters to be considered in the design of controller. Therefore to devise an automatic flow rate proportional control a 0.5 inch valve (instead of conventional valves) was used. In order to design, implement and install an open loop control system on this valve, information and data were collected by a data logger. Equipments and sensors for gathering experimental data were: perssure sensors (Wika), RS232 cable, digital mulltimeter and a especially designed lever for opening/closing or adjusting ball valve. An electronic circuit for gathering data from perssure sensors and sending them to computer was also designed. This data were analyzed with Excel. Flow rate computed in every point of valve opening. Based on above findings, an electronic control and monitoring system was designed and implemented. This system include an AT89S51 microcontroller as centeral processing unit, a stepper motor (Mitsumi M42SP-5), a Ball valve, a four bit DSP display and a buzzer to produce alarm when tank is empty. The program for this system was written in C language by using Keil software. In this system microcontroller senses pulses which are produced by front wheel of tractor and then send necessary commands to the stepper motor in order to adjust shaft and valve shaft according to the set points for flow rate in valve. Volume of liquid in the tank in is also sensed and displayed on DSP LCD and when the tank become empty the buzzer will ring.

Greenhouse automation provides good management to increase quality and quantity of greenhouse pro... more Greenhouse automation provides good management to increase quality and quantity of greenhouse production. Precise environmental control and monitoring are the main parts in greenhouse automation. In this thesis beside the design and development of a prototype greenhouse; design and evaluation of a computer-based control and monitoring system were performed. For optimum temperature and humidity control, CO2 provision and irrigation; suitable control devices were designed and constructed according to prototype greenhouse condition. Microcontroller board receives data about greenhouse environment condition from three temperature sensors and a humidity one. The microcontroller board transfer data to computer via serial port (RS232) and simultaneously it may receive control signal from computer. The microcontroller board according to received control signal changes the state of greenhouse control devices to reach desired condition. A program written in Visual Basic 6.0 was developed to carry out control and monitoring processes. This program monitors and saves received data continuously. Program also executes a complex control algorithm. It compares received data with values that defined in program setting and if necessary it sends control signal to microcontroller board so control devices (i.e, heater, fans, etc.) state changes to reach desired condition. The developed system was tested in autumn season and environmental conditions of inside (i.e, temperature and humidity) and outside (temperature) of greenhouse were investigated for two states of controlled and uncontrolled conditions. Results of uncontrolled condition verify the effect of solar radiation in creating greenhouse effect for designed greenhouse. In controlled condition; Response of system in stabilization of temperature in both heating and cooling states was acceptable and performance of system in humidity control was fairly good. Therefore Overall performance of control system in providing desired condition was good. Results of this study can be used to develop and optimize system performance according to commercial greenhouses requirements.

Supplier selection process is a key operational function to develop sustainable partnerships and ... more Supplier selection process is a key operational function to develop sustainable partnerships and enhance the supply chain performance. This chapter aims to develop an applicable methodology for green supplier selection in food industry. The methodology consists of two phases of classification and ranking of criteria, and the supplier selection phase. In first phase 10 criteria of supplier selection with two dimensions (conventional and green) are identified. Then the criteria are examined and ranked by evaluation factors (frequency in references, adaptation with kind of product, easily understand and easily measurement). The financial, qualitative, service and environmental management system criteria are selected as high ranked criteria. In second phase, potential suppliers are evaluated by high ranked criteria. Group decision making using fuzzy and grey set theories helped to give better results in green supplier selection. At the end of this study in order to demonstrate effective...

EcoProduction, 2014

Green supplier selection (GSS) criteria arise from an organization inclination to respond to any ... more Green supplier selection (GSS) criteria arise from an organization inclination to respond to any existing trends in environmental issues related to business management and processes, so GSS is integrating environmental thinking into conventional supplier selection. This research is designed to determine prevalent general and environmental supplier selection criteria and develop a framework which can help decision makers to determine and prioritize suitable green supplier selection criteria (general and environmental). In this research we considered several parameters (evaluation objectives) to establish suitable criteria for GSS such as their production type, requirements, policy and objectives instead of applying common criteria. At first a comprehensive and deep review on prevalent and green supplier selection literatures performed. Then several evaluation objectives defined to assess the green supplier selection criteria include: frequency, compatibility, quantifiable, easy to understand and assessment. By developed framework suitable criteria can be selected using multi attribute decision making methods. The main contribution of this research is developing a framework to help managers for creating their green supplier criteria list.