PREDICTION OF QUALITY CHANGES DURING OSMO-CONVECTIVE DRYING OF BLUEBERRIES USING NEURAL NETWORK MODELS FOR PROCESS OPTIMIZATION

Artificial neural network (ANN) models were used for predicting quality changes during osmo-convective drying of blueberries for process optimization. Osmotic drying usually involves treatment of fruits in an osmotic solution of predetermined concentration, temperature and time, and generally affects several associated quality factors such as color, texture, rehydration ratio as well as the finish drying time in a subsequent drier (usually air drying). Multi-layer neural network models with 3 inputs (concentration, osmotic temperature and contact time) were developed to predict 5 outputs: air drying time, color, texture, and rehydration ratio as well as a defined comprehensive index. The optimal configuration of neural network model was obtained by varying the main parameters of ANN: transfer function, learning rule, number of neurons and layers, and learning runs. The predictability of ANN models was compared with that of multiple regression models, confirming that ANN models had much better performance than conventional mathematical models. The prediction matrices and corresponding response curves for main processing properties under various osmotic dehydration conditions were used for searching the optimal processing conditions. The results indicated that it is feasible to use ANN for prediction and optimization of osmo-convective drying for blueberries.     

QUALITY EVALUATION OF OSMO-CONVECTIVE DRIED BLUEBERRIES

Abstract

The color, texture and rehydration ratios of two-stage osmo-convective dried blueberries were evaluated. The parameters analyzed for color were the total color difference (ΔE) and the red-blue (a/b) ratio. The textural parameters of hardness and stickiness of the osmo-convective dried blueberries were evaluated. The results were compared with those of conventionally air-dried blueberries (worst case scenario) and freeze-dried blueberries (best case scenario). The results showed that osmotic dehydration for a short contact time minimized color losses during convective air-drying. The osmo-convective dried blueberries were not significantly harder (p > 0.05) than the conventional air-dried blueberries. The rehydration ratios of the osmo-convective dried blueberries were lower than the rehydration ratios of freeze-dried and air-dried blueberries. The best osmotic dehydration condition under which the osmo-convective dried blueberries had better color and texture and, a shorter drying time than the conventional air-dried blueberries was 50°C – 55°Brix for 4.5 h.     

Influence of vacuum impregnation pretreatment combined with IR drying on quince quality with shrinkage modeling by ANN

The effects of infrared power on drying behavior of quince slice were investigated. The samples were pretreated under vacuum impregnation (VI) and atmospheric pressure with sucrose sirup. The quality attributes measured included moisture content, bulk density rehydration, water loss, solid gain, texture, porosity, color, non-enzymatic browning, and effective moisture diffusivity. In addition, the modeling of shrinkage by ANN. VI increased the effective moisture diffusivity, bulk density, and softening of the dried fruit tissues while decreasing the time of drying (p?<?0.05). The highest porosity was observed for the control samples treated under VI and dried at 1200?W. The desired color was achieved in the osmotic samples treated under atmospheric conditions and dried at 800?W. The rate of rehydration was reduced in the osmotic samples under vacuum. MLP neural network was used to model the shrinkage of the best topology 3-3-1 by LM learning algorithm and threshold function of Tangent sigmoid function, with a correlation coefficient of 0.9963 and the error MSE of 0.000340.     

OSMO-CONVECTIVE DRYING OF GRAPES

In order to reduce browning of grapes during drying, a special drying method was developed and evaluated using a laboratory scale fluidized bed dryer. Fresh Thompson seedless grapes were initially dried by immersion in a fluidized bed of sugar. The mass ratio of grapes to sugar was 1:1. The flow rate of hot air (at 45 and 60^°C) was sufficient to fluidize the sugar bed, while grapes placed on the screen, 3 cm above the drying air distributor, remained generally stationary.

Due to the simultaneous osmotic and convection drying effects, the drying time was reduced by factor ∼1.5 as compared to drying under the similar conditions without added sugar. A special pre-treatment of dipping of grapes in ethyl oleate (2% solution in 0.5% sodium hydroxide) at 80†deg; C for 30 s further reduced the drying time by factor 2 in both cases. The color of osmo-convective dried grapes were comparable to that of sulfur dioxide treated grapes. The texture of osmo-convective dried grapes was more pliable (softer) than convective dried samples. The major problem associated with die osmo-convective drying of grapes on a sugar bed was the stickiness, caused by sugar, on the fruit surface. This was reduced by partially substituting sugar with semolina (maintaining a 1:1 ratio) to create fluidized bed.     

OSMO-CONVECTIVE DRYING OF GRAPES

ABSTRACT

In order to reduce browning of grapes during drying, a special drying method was developed and evaluated using a laboratory scale fluidized bed dryer. Fresh Thompson seedless grapes were initially dried by immersion in a fluidized bed of sugar. The mass ratio of grapes to sugar was 1:1. The flow rate of hot air (at 45 and 60^°C) was sufficient to fluidize the sugar bed, while grapes placed on the screen, 3 cm above the drying air distributor, remained generally stationary.

Due to the simultaneous osmotic and convection drying effects, the drying time was reduced by factor ～1.5 as compared to drying under the similar conditions without added sugar. A special pre-treatment of dipping of grapes in ethyl oleate (2% solution in 0.5% sodium hydroxide) at 80?deg; C for 30 s further reduced the drying time by factor 2 in both cases. The color of osmo-convective dried grapes were comparable to that of sulfur dioxide treated grapes. The texture of osmo-convective dried grapes was more pliable (softer) than convective dried samples. The major problem associated with die osmo-convective drying of grapes on a sugar bed was the stickiness, caused by sugar, on the fruit surface. This was reduced by partially substituting sugar with semolina (maintaining a 1:1 ratio) to create fluidized bed.     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

Prediction of Timber Kiln Drying Rates by Neural Networks

The purpose of this exploratory work was to apply artificial neural network (ANN) modeling to the prediction of timber kiln drying rates based on species and basic density information for the hem-fir mix that grows along the local coastal areas. The ANN models with three inputs (initial moisture content, basic density, and drying time) were developed to predict one output, namely, average final moisture content. The back-propagation algorithm, the most common neural network learning method, was implemented for testing, training, and validation. Optimal configuration of the network model was obtained by varying its main parameters, such as transfer function, learning rule, number of neurons and layers, and learning runs. Accurate prediction of the experimental drying rate data by the ANN model was achieved with a mean absolute relative error less than 2%, thus supporting the powerful predictive capacity of this modeling method.     

Color prediction of mushroom slices during drying using Bayesian extreme learning machine

Abstract

Color is an important appearance attribute of fruits and vegetables during drying processing, as it influences consumer’s preference and acceptability. Establishing color change kinetics model is an effective way for better understanding the quality changes and optimization of drying process. However, it is difficult to quickly and accurately predict color change kinetics during drying as it is highly nonlinear, complex, dynamic, and multivariable. To alleviate this problem, a new model based on extreme learning machine integrated Bayesian methods (BELM) has been developed for the prediction of color changes of mushroom slices during drying process. The effects of drying temperature (55, 60, 65, 70, and 75?°C) and air velocity (3, 6, 9, and 12?m/s) on color change kinetics of mushroom slices during hot air impingement drying were firstly explored and the experimental results indicated that both drying temperature and air velocity significantly affected the color attributes. Then, to validate the robustness and effectiveness of BELM, the basic extreme learning machine (ELM) and traditional back-propagation neural network (BPNN) models have also been employed to predict the color quality. In terms of prediction accuracy and execution time, BELM could achieve least similar or even better performance than ELM and BPNN. It overcame the overfitting problems of ELM. The test results of optimal BELM model by two new cases revealed that the lowest R² and highest RMSE of BELM model were 0.9725 and 0.0563, respectively. The absolute values of relative errors between the actual and predicted values were lower than 8.5%.     

Evaluation of the air-borne ultrasound on fluidized bed drying of shelled corn: Effectiveness,grain quality,and energy consumption

The objective of the study was to investigate the influence of high power ultrasound on a laboratory-scale fluidized bed shelled corn dryer. The drying time, moisture content variation, specific energy consumption, and quality parameters including ultimate compressive strength, toughness, shrinkage and color of corn kernels were investigated. Furthermore, artificial neural network (ANN) simulation models were developed for predicting the drying variables. Machine vision techniques were used to determine color and shrinkage as qualitative indices. Results showed that the lower frequencies had better penetrations at lower temperatures and cause a significant reduction in drying time. In addition, the ultrasound application led to reduction of ultimate compressive strength and toughness of the dried samples although ultrasound has nonthermal character as the subsidiary factor, it plays an important role in shrinkage and color specification. Based on error analysis results, the prediction capability of ANN model is found to be reasonable for the developed models. Application of ultrasound significantly decreased the specific energy consumption of drying process at the optimal drying condition.     

Ultrasound-assisted osmotic process on quality of microwave vacuum drying sweet potato

The effects of pretreatment before microwave vacuum drying (MVD) on texture, color, expansion, rehydration, drying rate, microstructure, sensory evaluation, and other properties of sweet potato were investigated in this study. The pretreatment consisted in five processing conditions, using blanching; osmotic dehydration at 35°Brix of sucrose (OD); ultrasound in distilled water (US); ultrasound in distilled water before osmotic dehydration (US?+?OD), and ultrasound-assisted osmotic dehydration (USOD). Pretreatments of sweet potato before MVD have shown success in reducing drying time with US treatment relatively more effective regarding drying time than other treatments. Compared with other treatments, US showed the highest rehydration ratio values. The osmotic group pretreatment exhibited a pronounced effect on water loss and solid gain, improved the color, aroma, and taste of dried sweet potato, whereas sucrose impregnation resulted in a hard texture observed with OD sample. USOD samples had a higher expansion ratio, lower hardness and color difference values, appeared less cell damaged, and recorded better overall quality than the other samples. There was a slight difference between USOD and US?+?OD samples. Combining osmotic dehydration with ultrasound as a pretreatment can significantly accelerate the heat transfer rate, reducing the dried time accordingly and increasing energy efficiency.     

Comparison of two alternatives of combined drying to process blueberries (O'Neal): Evaluation of the final quality

In this work, we examined and compared two combined alternatives for the drying of blueberries (O’Neal). Pretreatments of osmotic dehydration (60°Brix sucrose solution at 40°C for 6 h) and hot air drying (HAD) (60°C, 2.5 m/s for 90 min) were performed to reach the same water content. Pretreated blueberries were then dried by microwave at different microwave output power values: 562.5, 622.5, and 750 W. The combined drying processes were also compared with HAD alone (control). The effects of the processes over blueberries were studied in terms of decrease in water content, drying rate (DR), mechanical properties (firmness and stiffness), optical properties (L*, a*, and hue angle (h)), antioxidant capacity, and rehydration capacity. The hot air–microwave drying decreased the process time and presented a high drying rate compared with the osmotic dehydration–microwave processes and the control drying. In terms of quality, the antioxidant and rehydration capacities were the most affected. The results showed that the best drying method to obtain the desired final product was the hot air–microwave drying (750 W).     

Modeling and optimization of the process parameters in vacuum drying of culinary banana (Musa ABB) slices by application of artificial neural network and genetic algorithm

The influence of drying temperature, sample slice thickness, and pretreatment on quality attributes like rehydration ratio, scavenging activity, color (in terms of nonenzymatic browning), and texture (in terms of hardness) of culinary banana (Musa ABB) has been evaluated in the present study. A comparative approach was made between artificial neural network (ANN) and response surface methodology (RSM) to predict various parameters for vacuum drying of culinary banana. The effect of process variables on responses during dehydration were investigated using general factorial experimental design. This design was used to train feed-forward back-propagation ANN. The predictive capabilities of these two methodologies for optimization of process parameters were compared in terms of relative deviation (R_d). Results revealed that a properly trained ANN model is found to be more accurate in prediction as compared to RSM. The optimum condition selected from ANN/GA responses on the basis of highest fitness value revealed that culinary banana slices of 6 mm thickness pretreated with 1% citric acid and dried at 76°C resulted in a maximum rehydration ratio of 6.20, scavenging activity of 48.63% with minimum nonenzymatic browning of 25%, and hardness of 43.63 N. Results further revealed that, in the case of rehydration ratio, temperature and pretreatment showed a positive effect while thickness had a negative effect. On the contrary, for scavenging activity, temperature showed the highest negative effect followed by slice thickness and positive effect with pretreatment. For nonenzymatic browning, thickness showed the highest negative effect but temperature and pretreatment showed a positive effect. Similarly, for hardness, all three parameters showed a negative effect.     

Study on quality attributes and drying kinetics of instant parboiled rice fortified with turmeric using hot air and microwave-assisted hot air drying

Abstract

This study investigated the quality and drying kinetics of instant parboiled rice fortified with turmeric (IPRFT) by using hot air (HA) and microwave-assisted hot air (MWHA) drying. The cooked long grain parboiled rice (LGPR) fortified with turmeric was dried with HA at temperatures of 65, 80, 95, and 110?°C. The microwave power density of 0.588 Wg^?1 was incorporated for drying with MWHA. Drying was performed until the dried IPRFT reached 16% (d.b.) of moisture content. The quality of the dried IPRFT was evaluated in terms of color, total phenolics content (TPC), total antioxidant capacity (TAC), rehydration ratio, volume expansion ratio, texture and microstructure. The results showed that the incorporation of microwave power with HA drying helped to reduce the drying time by 50% compared to conventional HA drying. A prediction of the moisture ratio by using the Page model provided the best R² and RMSE in drying kinetics. The drying conditions had small effects on the color, TPC, TAC, and microstructure of the dried IPFRT. The rehydration ratio, volume expansion ratio and texture of the rehydrated IPFRT showed minimal variations from changes in the drying conditions. The TPC and TAC of the dried IPRFT clearly increased compared to the TPC and TAC of the initial LGPR.     

DEVELOPMENT OF ANN MODEL FOR NON-LINEAR DRYING PROCESS

ABSTRACT

This paper presents an application of artificial neural network (ANN) technique to develop a model representing the non-linear drying process. The air heat plant (AHP), an important component in drying process is fabricated and used for building the ANN model. An optimal feed forward neural network topology is identified for the air heating system set-up. The training sets are obtained from experimental data. Back propogation algorithm with momentum factor is used for training. The results show that the back propogation ANN can learn the functional mapping between input and output. The advantages of ANN model developed for AHP is highlighted. The developed model can be used for control purposes.     

Use of Artificial Neural Network and Image Analysis to Predict Physical Properties of Osmotically Dehydrated Pumpkin

The objectives of this research were to predict, using neural networks, the color intensity (ΔE), percentage of shrinkage as well as the Heywood shape factor, which is the representative of deformation, of osmotically dehydrated and air dried pumpkin pieces. Several osmotic solutions were used including 50% (w/w) sorbitol solution, 50% (w/w) glucose solution, and 50% (w/w) sucrose solution. Optimum artificial neural network (ANN) models were developed based on one to two hidden layers and 10–20 neurons per hidden layer. The ANN models were then tested against an independent data set. The measured values of the color intensity, percentage of shrinkage, and the Heywood shape factor were predicted with R² > 0.90 in all cases, except when all the drying methods were combined in one data set.     

Comparison of Three New Drying Methods for Drying Characteristics and Quality of Shiitake Mushroom (Lentinus edodes)

This articles provides results of an experimental investigation of three hybrid drying technologies on the drying characteristics and key quality parameters of shiitake mushroom (Lentinus edodes). The drying techniques tested at the laboratory scale are mid-infrared-assisted convection drying (MIRCD), hot air coupled with radio frequency drying (HCRFD), and hot air coupled with microwave drying (HCMD). For comparison, the standard drying technique using hot air was also tested. The quality parameters include texture, color, rehydration rate, shrinkage, nutrient retention, microstructure, etc. These four drying tests were conducted at fixed air temperature (60°C), and the power level for HCRFD, MIRCD, and HCMD was fixed at 4 W/g. The results showed that hot air coupled with microwave drying gave the shortest drying time, and mid-infrared-assisted convection and hot air coupled with radio frequency drying showed better color attributes and nutrient retention. Under the conditions tested, mid-infrared-assisted convection drying yielded minimal shrinkage (maximal rehydration) and lower hardness upon rehydration. The uniform honeycomb network and less collapsed structure of MIRCD samples can be used to explain these better quality characteristics.     

Continuous real-time monitoring and neural network modeling of apple slices color changes during hot air drying

A hot air drying system equipped with real-time computer vision system was used to investigate the effects of drying variables on apple slices color changes. Drying experiments were conducted at drying air temperatures of 50–70 °C, drying air velocities of 1–2 m/s, and samples thicknesses of 2–6 mm. A multilayer perceptron (MLP) artificial neural network (ANN) was also used to correlate color parameters and moisture content of apple slices with drying variables and drying time. The effects of drying air temperature and sample thickness on color changes were dominated over the effect of drying air velocity. However, non-linear and somewhat complex trends were obtained for all color parameters as function of moisture content. The MLP ANN satisfactorily approximated the color and moisture variations of apple slices with correlation coefficient higher than 0.92. Therefore, the computer vision system supplemented with ANN can be used as a non-invasive, low cost, and easy method for fast and in-line assessing and controlling of foodstuffs color and moisture changes during drying.     

Effect of Four Drying Methods on the Quality of Osmotically Dehydrated Cranberries

Partially dehydrated cranberries (osmotically dehydrated) were dried to low water contents using one of following four methods: hot air drying; microwave-assisted convective drying; freeze-drying; and vacuum drying. Quality evaluation was performed on all samples, including sensory evaluation (appearance and taste), texture, color, water activity, and rehydration ratio. Hot air drying produced dried cranberries with the best visual appearance while freeze-dried cranberries had the highest rehydration ratio. The other methods presented similar rehydration ratios. There was no significant difference in color measurements and water activity. Few differences in texture were found, except for freeze-dried cranberries, which had a lower toughness compared to the other drying methods including commercially available dried cranberries. Microwave-assisted to hot air drying rate ratios increased as the moisture content decreased.     

Effect of Four Drying Methods on the Quality of Osmotically Dehydrated Cranberries

Abstract

Partially dehydrated cranberries (osmotically dehydrated) were dried to low water contents using one of following four methods: hot air drying; microwave-assisted convective drying; freeze-drying; and vacuum drying. Quality evaluation was performed on all samples, including sensory evaluation (appearance and taste), texture, color, water activity, and rehydration ratio. Hot air drying produced dried cranberries with the best visual appearance while freeze-dried cranberries had the highest rehydration ratio. The other methods presented similar rehydration ratios. There was no significant difference in color measurements and water activity. Few differences in texture were found, except for freeze-dried cranberries, which had a lower toughness compared to the other drying methods including commercially available dried cranberries. Microwave-assisted to hot air drying rate ratios increased as the moisture content decreased.     

Prediction of moisture content in pre-osmosed and ultrasounded dried banana using genetic algorithm and neural network

In this study, application of a versatile approach for estimation moisture content of dried banana using neural network and genetic algorithm has been presented. The banana samples were dehydrated using two non-thermal processes namely osmotic and ultrasound pretreatments, at different solution concentrations and dehydration times and were then subjected to air drying at 60 and 80 °C for 4, 5 and 6 h. The processing conditions were considered as inputs of neural network to predict final moisture content of banana. Network structure and learning parameters were optimized using genetic algorithm. It was found that the designed networks containing 7 and 10 neurons in first and second hidden layers, respectively, give the best fitting to experimental data. This configuration could predict moisture content of dried banana with correlation coefficient of 0.94. In addition, sensitivity analysis showed that the two most sensitive input variables towards such prediction were drying time and temperature.