Artificial neural networks modeling of kinetic curves of celeriac (Apium graveolens L.) in vacuum drying

Beigi, Mohsen; Ahmadi, Iman

doi:10.1590/fst.35717

Cited by 10 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model parameters were obtained with the nonlinear regression method. The objective of a previous study (Beigi & Ahmadi, ) was to predict the drying curves of celeriac ( Apium graveolens L.) with ANN. To predict the moisture content, chamber pressure, air temperature, and time values were selected as the input variables of ANN.…”

Section: Introductionmentioning

confidence: 99%

Kinetic and artificial neural network modeling techniques to predict the drying kinetics of Mentha spicata L.

Karakaplan

Göz

Tosun

et al. 2019

J Food Process Preserv

View full text Add to dashboard Cite

This study presented both the empirical and artificial neural network (ANN) approaches to estimate the moisture content of Mentha spicata. Two different types of drying methods (in shade and in oven (35 and 50°C)) were used to investigate the drying kinetics of the Mentha spicata samples. The effects of drying methods on effective diffusion coefficient, moisture ratio (MR), drying rate, and activation energy were investigated. Moreover, six different thin layer drying models (Page, Diffusion approach, Newton, Modified Henderson, Henderson and Pabis and Pabis and Midilli) and an ANN with feed forward structure were used to define the drying kinetics of these samples. In order to estimate the kinetic model parameters, sequential quadratic programming (SQP) was used. Model performances were evaluated based on the coefficient of determination (R2), root mean square error (RMSE) and mean absolute percentage error (MAPE%) values. In the kinetic part of the modeling study, the Midilli model provided better results than the others. However, the ANN had the best results when a total assessment was made. The effective diffusion coefficient values were found in the range between 1.31 × 10–12 and 4.43 × 10–12 m2/s. The activation energy was obtained as 44.31 kJ/kmol. The R2, MAPE%, and RMSE values for the ANN test data were 1.00, 0.2257, and 5.9447 × 10−4, respectively. In the future, different modeling approaches will be applied to describe this drying process. Practical applications Drying is a process where heat transfer and mass transfer take place together. Modeling is an innovative approach used in evaluation of experimental data and has increasing popularity in recent years. ANNs are a powerful data‐driven method, and they have a very broad area of usage from medicine to engineering issues. Empirical models are another approach for describing experimental data. In this study, these two modeling approaches were used to obtain the MR. Humidity is a condition that needs to be checked in food safety and protection. Therefore, it is very important to ensure control with robust modeling techniques. In this study, the developed ANN model had a high R2 value (R2 = 1.00). This indicated that it may be used successfully in real applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Kinetic and artificial neural network modeling techniques to predict the drying kinetics of Mentha spicata L.

Karakaplan

Göz

Tosun

et al. 2019

J Food Process Preserv

View full text Add to dashboard Cite

show abstract

“…Vacuum drying has been widely used in drying various fruits and vegetables. In the paper [16], artificial neural networks (ANNs) were used to predict celeriac drying curves in vacuum drying. The air temperature, chamber pressure and time values were used as ANN inputs.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

The influence of different drying methods on the quality attributes of beetroots

Liu

Sabadash

Duan

et al. 2022

EEJET

View full text Add to dashboard Cite

Beetroot is recognized as a health-promoting vegetable due to its abundant source of bioactive compounds. Drying methods significantly influence the quality of products. Therefore, it is important to choose a suitable drying method to obtain high quality of dried beetroots. The aim of this research was to investigate the influence of different drying methods on the quality attributes of beetroots. Fresh beetroots were dehydrated by freeze drying (FD), heat pump drying (HPD), vacuum drying (VD), microwave drying (MD) and microwave vacuum drying (MVD), respectively. The drying time, final moisture content, rehydration ratio, color, microstructure, betalain content and total flavonoids content of beetroots prepared by different drying methods were analyzed. The results showed that MVD and MD were superior to VD, HPD and FD in terms of drying time. The drying time (0.77±0.03 h) of MD was reduced by 97.40 % compared with FD, which was only 9.83 % of VD and 11.27 % of HPD. No significant differences in the final moisture content among beetroots dried using different drying methods were observed. Beetroots dried by FD showed the most desirable color and porous structure. Besides, beetroots dried by MVD exhibited the largest rehydration ratio, while the lowest rehydration ratio appeared in the beetroots obtained using MD. In addition, beetroots prepared by HPD illustrated the highest contents of betacyanin, betaxanthin and total flavonoids, which were 5.48±0.03 mg/g, 2.40±0.02 mg/g and 24.71±0.47 mg rutin equivalent/g, respectively. These results identify that it is difficult to achieve the best quality dried beetroots using a single drying method. Therefore, considering the quality attributes, the combined drying method (HPD+MVD) would be a very promising alternative method for obtaining dehydrated beetroots

show abstract

“…Artificial neural network model [27][28][29][30][31][32][33] is a machine learning technique most popular in high-energy physics community. In the last decade important physics results have been separated utilizing this model.…”

Section: B Artificial Neural Network(ann) Modelmentioning

confidence: 99%

Entropy per rapidity in Pb-Pb central collisions using Thermal and Artificial neural network(ANN) models at LHC energies

Habashy,

El-Bakry,

Scheinast

et al. 2021

Preprint

View full text Add to dashboard Cite

The entropy per rapidity dS/dy produced in central Pb-Pb ultra-relativistic nuclear collisions at LHC energies is calculated using experimentally observed identified particle spectra and source radii estimated from Hanbury Brown-Twiss (HBT) for particles, π, k, p, Λ, Ω, and Σ, and π, k, p, Λ and K 0 s at √ s = 2.76 and 5.02 TeV, respectively. Artificial neural network (ANN) simulation model is used to estimate the entropy per rapidity dS/dy at the considered energies. The simulation results are compared with equivalent experimental data, and good agreement is achieved. A mathematical equation describes experimental data is obtained. Extrapolating the transverse momentum spectra at p T = 0 is required to calculate dS/dy thus we use two different fitting functions, Tsallis distribution and the Hadron Resonance Gas (HRG) model. The success of ANN model to describe the experimental measurements will imply further prediction for the entropy per rapidity in the absence of the experiment.

show abstract

Artificial neural networks modeling of kinetic curves of celeriac (Apium graveolens L.) in vacuum drying

Cited by 10 publications

References 24 publications

Kinetic and artificial neural network modeling techniques to predict the drying kinetics of Mentha spicata L.

Kinetic and artificial neural network modeling techniques to predict the drying kinetics of Mentha spicata L.

The influence of different drying methods on the quality attributes of beetroots

Entropy per rapidity in Pb-Pb central collisions using Thermal and Artificial neural network(ANN) models at LHC energies

Contact Info

Product

Resources

About