---

The use of neural networks methodology is not as common in the investigation and pre-diction noise as statistical analysis. The application of artificial neural networks for pre-diction of power tiller noise is set out in the present paper. The sound pressure signals for noise analysis were obtained in a field experiment using a 13-hp power tiller. During measurement and recording of the sound pressure signals of the power tiller, the engine speeds and gear ratios were varied to cover the most normal range of the power tiller op-eration in transportation conditions for the asphalt, dirt rural roads, and grassland. Sig-nals recorded in the time domain were converted to the frequency domain with the help of a specially developed Fast Fourier Transform (FFT) program. The narrow band signals were further processed to obtain overall sound pressure levels in A-weighting. Altogether, 48 patterns were generated for training and evaluation of artificial neural networks. Arti-ficial neural networks were designed based on three neurons in the input layer and one neuron in the output layer. The results showed that multi layer perceptron networks with a training algorithm of back propagation were best for accurate prediction of power tiller overall noise. The minimum RMSE and R2 for the four-layer perceptron network with a sigmoid activation function, Extended Delta-Bar-Delta (Ext. DBD) learning rule with three neurons in the first hidden layer and two neurons in the second hidden layer, were 0.0198 and 0.992, respectively.

---

In this research a new laboratory solar-vacuum dryer was designed and fabricated to study drying behavior of pomegranate arils with heat source of solar energy. Drying of the samples was implemented at the absolute pressures of 10, 20, 40 and 60 kPa. Impact of different absolute pressures on moisture loss trend, effective moisture diffusivity, color and shrinkage of pomegranate arils, dried in solar-vacuum dryer was studied. With regression analysis of the applied models, proved that the Midilli model had supremacy in drying behavior prediction of pomegranate arils. Results indicated that with decreasing absolute pressure, drying time was decreased. Minimum drying time was related to the absolute pressure of 10 kPa. Effective moisture diffusivity of the pomegranate arils was estimated at the ranges of 3.09×10^-10 to 4.13×10^-10 m²/s.Total color changes and shrinkage percent of the pomegranate arils were estimated at the ranges of 17.4 to 22.1 and 67.58% to 74.45%, respectively.    

---

  The purpose of this study was prediction of thermal (effective moisture diffusivity and specific energy consumption), physical (shrinkage and color) and mechanical properties (rupture force) of terebinth fruit in a semi industrial continuous dryer using artificial neural networks (ANNs). Three effective factors on thermal, physical and mechanical properties, were air temperature, air velocity and belt linear speed as independent variables. Experiments were conducted with a semi industrial continuous dryer in temperature levels of 45, 60, 75 °C, air velocity levels of 1, 1.5 and 2 m/s and belt linear speed levels of 2.5, 6.5, 10.5 mm/s. Necessary data were collected using a the semi-industrial continuous dryer. Feed and cascade forward back propagation networks with learning algorithms of Levenberg-Marquardt and the Bayesian regulation were used to train the patterns. To predict the effective moisture diffusivity, feed forward networks with the Bayesian regulation, topology of 3-10-13-1 and 108 training cycles with R²=0.9999 was optimal arrangement. The optimal topology to predict the specific energy consumption was 3-10-1 with feed forward network, Levenberg-Marquardt algorithm, 117 training cycles and R²=0.9961. The best network for shrinkage prediction was feed forward network with the Bayesian regulation algorithm, topology of 3-6-4-1, 101 training cycles and R²=0.9926. To predict the total color change, feed forward networks with the Levenberg-Marquardt algorithm, topology of 3-6-7-1, 24 training cycles and R²=0.9139 was the optimal arrangement. The best network to predict the rupture force was feed forward network trained with the Bayesian regulation, topology of 3-8-6-1, 69 training cycles and R²=0.9990.

---

In this research the effect of different drying conditions of microwave fluidized bed (inlet air temperature, inlet air velocity and microwave power) on drying time, effective moisture diffusivity, shrinkage and total energy consumption of pistachio kernel was studied. Data analysis and optimization of drying process of pistachio were conducted by response surface method and central composite design. Input (independent) parameters were: inlet air temperature, inlet air velocity and microwave power. Dependent (output or response) variables  were: drying time, effective moisture diffusivity, shrinkage and total energy consumption. The primary moisture content of pistachio kernels has been determined 0.569 (d.b.). Drying of the kernels was performed at three levels of air velocity (1.16, 3.32 and 8.48 m/s), three levels of input air temperature (40, 55 and 70°C) and three levels of microwave power (220, 330 and 440W). The obtained effective drying time, moisture diffusivity, shrinkage and total energy consumption of pistachio ranged between 1.2 to 3.83 h, 2.7×10^-10 to 1.32×10^-09 m²/s, 12.01% to 35.43% and 0.337 to 1.63 kWh, respectively. The optimum point occurred at air temperature of 38.48˚C, air velocity of 1.16 m/s and microwave power of 440 W. Response variable values for drying of Akbari cultivar of pistachio with fluidized bed microwave dryer at this point were drying time of 2.677 h, effective moisture diffusivity of 5.179×10^-10, shrinkage percent of 18.41% and total energy consumption of 0.7109 kWh.

---

Short and medium infrared radiation implemented as an energy source in drying process under vacuum conditions. Any comparative study was not carried out between these two energy sources in drying process of agricultural products. In this study, effects of short and medium wave of infrared were evaluated and compared on drying behavior of peach slices under vacuum condition. Drying of the samples was implemented under both the energy sources at the absolute pressures of 20, 40 and 60 kPa and drying temperatures of 50, 60 and 70°C. Drying behavior of peach slices as well as the effect of drying conditions on moisture loss trend, effective diffusion coefficient, color and shrinkage of peach slices, dried in an infrared-vacuum dryer were examined. Effective diffusion coefficient of peach slices under medium wave infrared at different drying conditions was more than short wave infrared in the ranges of 2.6×10^-11 to 1.4×10^-10 m²/s. Total color difference and shrinkage of peach slices under short wave infrared at different drying conditions was less than medium wave infrared in the range of 6.6 to 8.7 and 7.8% to 9.7%, respectively. Minimum total color difference of peach slices under short and medium wave of infrared were obtained 8.2 and 14.8 and minimum shrinkage of peach slices under short and medium wave infrared were achieved 46.7% and 55.9% respectively.  

---

Drying properties of high moisture potato slices with initial moisture content of about 4.06 (db) under thin layer fixed, semi fluidized and fluidized bed conditions were studied. Drying air temperatures of 40, 50, 60 and 70°C were applied in experiments using a laboratory fluidized bed convective dryer. In order to predict the drying behavior of potato slices, seven thin layer drying models were applied from where finally Midilli et al. model was selected as the suitable one, based on comparative indices. Effective moisture diffusivity of the potato slices varied between 4.29×10^-9 and 15.70×10^-9 m² s^-1 for fixed and fluidized bed conditions, respectively. Moisture diffusivity values of the slices were increased as the drying air temperature levels increased. Activation energy values varied between 15.88 and 24.95 kJ mol^-1. Minimum and maximum values of activation energy were obtained at minimum fluidized and fixed bed conditions, respectively. Consumption of specific energy for thin layer drying of high moisture potato slices was obtained between 0.45×10⁵ and 1.64×10⁵ (kJ kg^-1). Increase in the drying air temperature in each bed condition caused increase in energy consumption. The maximum value of energy consumption was obtained at fluidized bed conditions.

---

In this study, hazelnut kernels were dried in an infrared dryer with microwave pretreatment. To determine the optimization conditions of the hazelnut samples, response surface methodology and central composite design were used to investigate the effect of temperature levels (45, 65 and 85 ° C), infrared power levels (500, 1000 and 1500 W) and microwave power levels (270, 450 and 630 W) on drying of hazelnut kernels. The adequacy and accuracy of the fitted models (Lack of Fit and R²) were checked with analysis of variance (ANOVA). Response surfaces and contour plots were created to show the interaction between the independent and the response variables. Based on the experiments, the optimum conditions for the highest values of effective moisture diffusivity and L^* (color index) and the lowest values of consumption energy, shrinkage and a^*, b^* (color indices) were determined at air temperature of 45°C, microwave power of 470.86 W and infrared power of 1316.72 W. The optimum values of the response variables affecting the effective moisture diffusivity, consumption energy, shrinkage, L*, a* and b* were obtained 2.35×10^-9 m² s^-1, 2.65 kWh, 12.94%, 54.10, 14.97 and 16.70, respectively.  

---

Kermanshah province is the main producer of various chickpea cultivars in Iran. In this study a laboratory peg-tooth thresher was employed for chickpea threshing. The effect of cylinder speed (9, 12, 15 m/s), concave clearance (12, 14, 16 mm), feed rate (80, 160, 240 kg/h) and material moisture content (5, 10, 15% w.b.) was studied on percentage of grain damage, threshing efficiency and percentage of seed germination. The experimental plan for optimization was prepared with response surface methodology technique with composite experiment design. The effects of all independent variables on the response variables were significant. The effect of cylinder speed was the most significant and followed by the moisture content. With increasing cylinder speed in the range of 9 to 15 m/s, the grain damage increased from 4.98 to 47.97%, threshing efficiency increased from 96.81 to 99.69% and seed germination decreased from 85.75 to 55.98%. With increasing moisture content, grain damage and threshing efficiency decreased but seed germination increased. With increasing feed rate and concave clearance, grain damage and threshing efficiency decreased while, seed germination increased. The optimized point was determined at the cylinder speed of 10.63 m/s, concave clearance of 13.74 mm, feed rate of 240 kg/h and moisture content of 12% (w.b.). In this condition, the optimum values of grain damage, threshing efficiency and seed germination were 3%, 98.3% and 84.29%, respectively.

---

---

Degradation of nutrients and change in the food quantity occur during the food processing; so, the food quality and retention nutrients are of the most important aspects of food processing. In this research, the effect of tomato slices drying process on the kinetics of vitamin C (ascorbic acid) degradation, color changes (L *, a * and b * ) and the specific energy consumption in order to produce tomato powder was investigated during the hot air drying at 45, 60 and 75 °C.  This tomato powder was used to produce tomato compact tablets.  Also, the effect of tomato dough moisture content (25, 40 and 55 %d.b.) and drying temperature of  wet tomato tablet (30, 40 and 50 °C) on vitamin C concentration (as an indicator for retain nutritional) was investigated during the compression and  convective drying processes. The results showed that the drying temperature and moisture content had a significant effect on the retention of vitamin C concentration (product health) when the fresh tomato processing and the production of compact tablet were going on. Drying under lower temperatures and moisture contents helps to retain quality and nutritional value (less degradation of vitamin C) of tomato tablets.

---

The goal of this study was to predict the moisture content of paddy using machine vision and artificial neural networks (ANNs). The grains were dried as thin layer with air temperatures of 30, 40, 50, 60, 70, and 80°C and air velocities of 0.54, 1.18, 1.56, 2.48 and 3.27 ms^-1. Kinetics of L*a*b* were measured. The air temperature, air velocity, and L*a*b* values were used as ANN inputs. The results showed that with increase in drying time, L* decreased, but a* and b* increased. The effect of air temperature and air velocity on the L*a*b* values were significant (P< 0.01) and not significant (P> 0.05), respectively. Changing of color values at 80°C was more than other temperatures. The optimized ANN topology was found as 5-7-1 with Logsig transfer function in hidden layer and Tansig in output layer. Mean square error, coefficient of determination, and mean absolute error of the optimized ANN were 0.001, 0.9630, and 0.031, respectively. 

---

The aim of this study was optimization of almond kernels drying with infrared-vacuum dryer and microwave pretreatment using Response Surface Methodology (RSM) and Genetic Algorithm (GA). The almond kernels were dried as thin layer with air temperatures of 30, 45 and 75°C vacuum pressures of 20, 40 and 60 kPa and microwave powers of 270, 450, and 630W. Design expert software was used to generate the experimental designs, statistical analysis, and regression models. The results showed that the optimum point for drying of almond kernels under infrared-vacuum dryer and microwave pretreatment with RSM method and considering the minimum value of shrinkage, energy consumption, and total color change as well as the maximum value of effective moisture diffusivity can be achieved at air temperature of 45°C, vacuum pressure of 34.04 kPa, and microwave power of 270W with 68% desirability and optimum point with GA method can be obtained at air temperature of 45°C, vacuum pressure of 34.05 kPa and microwave power of 270W.

---

Lavender leaves, widely used as flavors for foods and beverages, are a rich source of phenol components and antioxidant. Drying method is of vital importance for keeping these compounds. In this study, lavender leaves were dried by means of Atmospheric Freeze (AF), Multi-Stage Semi-Industrial Continuous (MSSIC), and Near Infrared-Vacuum (NIR-Vacuum) dryers and optimized by Response Surface Methodology (RSM) for the highest drying rate, total phenol content, antioxidant capacity, and the lowest color indicators change. Lavender leaves were also dried under natural conditions as the traditional method. Multi-stage drying caused tempering phenomenon and, consequently, drying rate increased obviously. Near infrared-vacuum dryer had suitable performance on keeping the active ingredients of lavender leaves. Optimum point to dry lavender leaves in atmospheric freeze dryer was found to be -5℃. The optimum temperature points in the multi-stage semi-industrial continuous dryer were achieved to be 60, 40, and 60℃ for the first, second, and third stages, respectively. The optimum point in near infrared-vacuum dryer was 60℃ and 20 kPa for air temperature and pressure, respectively. Based on the results, among several drying methods, near infrared-vacuum dryer was the more suitable for drying lavender leaves.
 

---

The present study aimed to develop orange pomace tablets as an additive with nutritional value. Orange pomace powder was converted into tablets by the drying method under the effect of compression force, diameter die, and relaxation force changes. Some of the physicochemical properties (e.g., density, penetration resistance, tensile strength, stability in water, total phenol content, antioxidant capacity, and ascorbic acid) were investigated. The tableting process was optimized by central composite design. The Kawakita and Lüdde model with R²= 0.995 was used to describe the compressibility behavior of orange pomace powder. The effect of diameter die on the minimum tension of deformation changes was insignificant. The results proved that the changes in the value of the active ingredients were insignificant when the orange was dried, ground to powder, and converted to a tablet. Also, the effect of diameter dies changes on all of the responses was significant at 0.01, while the effect of compression force was insignificant just for penetration resistance. Effect of the relaxation force on the mechanical properties was significant (at level of 0.5 for penetration resistance and 0.01 for tensile strength), and on the density and stability in water was insignificant. Finally, the optimum point for tableting from orange pomace was suggested at the compression force of 8.6 kN, diameter die of 10 mm, and relaxation force of 1.14 kN for 1.13×10^-3 g mm^-3 of density, 111 N of penetration resistance, 52.4 MPa of tensile strength, and 51 g.s dl^-1 of stability in water.