Producing non-traditional flour from watermelon rind pomace: Artificial neural network (ANN) modeling of the drying process

Fabani, María Paula; Capossio, Juan Pablo; Román, María Celia; Zhu, Wenlei; Rodríguez, Rosa; Mazza, Germán

doi:10.1016/j.jenvman.2020.111915

Cited by 50 publications

(24 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With trained algorithms, the prediction of a new drying curve is done within seconds with great accuracy, thus avoiding time‐consuming new experiments. Also, extending the model (adding new inputs and/or outputs) is very practical (Fabani et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Prediction of moisture ratio and drying rate of orange slices using machine learning approaches

Çetin

2022

Food Processing Preservation

View full text Add to dashboard Cite

In order to improve the drying characteristics and to optimization of drying conditions, machine learning (ML) and response surface methodology (RSM) were applied in air‐convective drying of orange slices (Washington Navel and Valencia cultivars). Interactions of temperature (T, 50–60°C), sample thickness (ST, 5–9 mm), and drying time (DT, 8–10 h) like independent variables with specific moisture extraction rate, effective moisture diffusivity, energy efficiency, and energy consumption like dependent variables were determined. In addition, five machine learning algorithms (random forest‐RF; artificial neural network‐ANN; gaussian processes‐GP support vector regression‐SVR, and k‐nearest neighbors‐kNN) were used to predict moisture ratio and drying rate. In Washington Navel and Valencia cultivars, the greatest correlation coefficients (R) for prediction of moisture ratio were obtained k‐NN algorithm with values of 0.9944 and 0.9898, respectively. Also, drying rate prediction results showed that k‐NN achieved higher R with values of 1.0000 and 0.9954, respectively. Experimental findings were adapted by a second‐degree polynomial model through variance analysis to identify model fitness and optimal drying conditions. Combined desirability value was calculated as 0.8812 for Valencia and 0.8564 for Washington. Increasing energy consumption was encountered with increasing drying time and sample thickness. Besides, energy consumption had a decreasing trend at higher temperatures. Practical applications Machine learning models are novelty and rapid methods that have been successfully utilized to solve such challenges agricultural commodities. Drying is common process to preserve the food quality. This study provides optimum conditions for drying orange slices in single unit air‐convective dryer and improves the effect of drying system on some drying characteristics energy aspects. In addition, this study can be able to present a technical knowledge for orange slice drying and related equipment design.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of moisture ratio and drying rate of orange slices using machine learning approaches

Çetin

2022

Food Processing Preservation

View full text Add to dashboard Cite

show abstract

“…Many researchers have used GAs for prediction purposes [22][23][24]36] and reported successful predictability using ANN without normalization. Hence, original experimental data were used for modeling.…”

Section: Ga-ann Modelingmentioning

confidence: 99%

Minimum Fluidization Velocities of Binary Solid Mixtures: Empirical Correlation and Genetic Algorithm‐Artificial Neural Network Modeling

et al. 2021

View full text Add to dashboard Cite

Experimental investigation of the fluidization behavior in single and binary solidliquid fluidized beds of nonspherical particles as solid phase and water as liquid phase was performed in a Perspex column. Different particle sizes were used to prepare single and binary mixtures with different weight ratios for fluidization. Minimum fluidization velocity increased with increasing average particle size and decreasing sphericity for the binary mixture. An empirical correlation was developed to predict the minimum fluidization velocity. Genetic algorithm-artificial neural network (GA-ANN) modeling was applied to predict the minimum fluidization velocity for single and binary solid-liquid fluidized beds. The application of GA-ANN analysis leads to designing binary solid-liquid fluidization systems without experimentation.

show abstract

“…Botanically watermelon is an annual creeping herb that originated from Southern Africa has attained the level of most economically fruit vegetable crop. Based on the statics of Food and Agriculture Organization the global watermelon production and production area reached approximately 104 million tons and 3084217 ha in 2019, respectively (Fabani et al, 2021;FAO 2021). In the current situation, watermelon can be grown in almost 122 countries and around 1200 various cultivars are available on all cultivated continents.…”

Section: Introductionmentioning

confidence: 99%

Current state of the art biotechnological strategies for conversion of watermelon wastes residues to biopolymers production: A review

et al. 2022

View full text Add to dashboard Cite

Producing non-traditional flour from watermelon rind pomace: Artificial neural network (ANN) modeling of the drying process

Cited by 50 publications

References 36 publications

Prediction of moisture ratio and drying rate of orange slices using machine learning approaches

Prediction of moisture ratio and drying rate of orange slices using machine learning approaches

Minimum Fluidization Velocities of Binary Solid Mixtures: Empirical Correlation and Genetic Algorithm‐Artificial Neural Network Modeling

Current state of the art biotechnological strategies for conversion of watermelon wastes residues to biopolymers production: A review

Contact Info

Product

Resources

About