Freeze-drying behaviour prediction of button mushrooms using artificial neural network and comparison with semi-empirical models

Tarafdar, Ayon; Shahi, Navin Chandra; Singh, Anupama

doi:10.1007/s00521-018-3567-1

Cited by 38 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For a drying process, suitable model can be identified based on statistical indicators such as the coefficient of determination ( R 2 ) and mean square error (MSE). Equations (4) and (5) provide the mathematical expression for estimating these statistical indicators (Tarafdar et al, ).

R^{2} = 1 - \frac{\sum_{i = 1}^{n} {(y_{i} - \overset{false^}{y_{i}})}^{2}}{\sum_{i = 1}^{n} {(y_{i} - \overset{true¯}{y_{i}})}^{2}}

MSE = \frac{1}{N} \sum_{i = 1}^{N} {(y_{i} - {\overset{y}{true}}_{i})}^{2}

…”

Section: Methodsmentioning

confidence: 99%

“…Since drying of biomaterials is a complex process, trends in drying characteristics may not be efficiently mapped using generic mathematical models. In this regard, the application of artificial neural networks or ANNs has proved to be useful for predicting drying characteristics (Aghbashlo, Hossseinpour, & Mujumdar, ; Tarafdar, Shahi, & Singh, ). ANNs are a mathematical expression of the functions of a human brain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent modeling and detailed analysis of drying, hydration, thermal, and spectral characteristics for convective drying of chicken breast slices

Kumar

Tarafdar

Kumar

et al. 2019

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

Chicken breast slices were convectively dried at three different temperatures (60, 70, and 80 C). Drying characteristics were analyzed and the predictive capabilities of artificial neural network (ANN) and semiempirical models were exploited. Low complexity ANN model with 10 hidden layer neurons was developed which provided improved results over eight tested semiempirical models. Influence of drying temperature on water activity, rehydration, shrinkage, color, thermal, and spectroscopic properties of the dried product was investigated. Samples dried at 70 C displayed lower moisture content (7.13% w.b.), water activity (a w = 0.45) and color change;while, exhibiting better rehydration potential. Effect of pH on hydration showed that alkaline pH (12.0) facilitated the hydration rate in the samples. Shrinkage in dried samples varied within 20-40% and increased with increase in drying temperature.Thermograms of the dried samples revealed a shift in glass transition temperature from 93 to 140 with an increase in drying temperature, indicating a change in protein structure, which was later confirmed by Fourier transform infrared spectroscopy. Practical ApplicationData on drying, thermal, and hydration characteristics for chicken slices generated in this study could aid the meat industry in developing faster and more convenient processes. Moreover, the low complexity model engineered in this study will facilitate the development of robust control systems for industrial applications. Salient findings of the study such as: (a) optimum time and temperature combination (i.e., 70 C/5 hr) for drying of chicken breast slices; (b) increased rehydration rate with increase in pH from 3.0 to 12.0; and (c) thermal and spectral characteristics have been reported for dried chicken slices which provides vital information on drying process for improvement in the end product obtained.

show abstract

R^{2} = 1 - \frac{\sum_{i = 1}^{n} {(y_{i} - \overset{false^}{y_{i}})}^{2}}{\sum_{i = 1}^{n} {(y_{i} - \overset{true¯}{y_{i}})}^{2}}

MSE = \frac{1}{N} \sum_{i = 1}^{N} {(y_{i} - {\overset{y}{true}}_{i})}^{2}

…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Intelligent modeling and detailed analysis of drying, hydration, thermal, and spectral characteristics for convective drying of chicken breast slices

Kumar

Tarafdar

Kumar

et al. 2019

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Drying experimental measurements have relied on mass loss. Moisture ratio (MR) gives information of the diffusion behavior of water inside the product (Tarafdar et al, ). The MR is expressed using the following equation:

MR = \frac{normalM - M_{e}}{M_{0} - M_{e}}

where, M 0 denotes the initial moisture content (kg‐water/kg‐drymatter), M represents the instant moisture content (kg‐water/kg‐drymatter), M e represents the equilibrium moisture content (kg‐water/kg‐drymatter).…”

Section: Methodsmentioning

confidence: 99%

“…Drying experimental measurements have relied on mass loss. Moisture ratio (MR) gives information of the diffusion behavior of water inside the product (Tarafdar et al, 2018). The MR is expressed using the following equation:…”

Section: Moisture Ratio and Drying Ratementioning

confidence: 99%

“…The development of a mathematical model for the freeze‐drying process is crucial for design engineers to select the appropriate drying conditions that meet the desired operating parameters (Avhad & Marchetti, ). There have been various studies on the modeling of food drying; such as development a model using regression analysis for rehydration kinetics in freeze‐drying of tomatoes (Lopez‐Quiroga, Prosapio, Fryer, Norton, & Bakalis, ), simulation of the spatiotemporal behavior of grapes during convective drying (Azzouz, Hermassi, Chouikh, Guizani, & Belghith, ), prediction of freeze‐dried mushrooms behavior using artificial neural network model (Tarafdar, Shahi, & Singh, ). However, there are not enough studies as yet based on the GEP approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mathematical model for mint drying kinetics prediction by freeze‐drying process: Gene expression programming

Kovacı

Dikmen

Şahin

2020

J Food Process Engineering

View full text Add to dashboard Cite

The drying ratio (DR) and the moisture ratio (MR) are the main drying characteristics properties which play an important role in the drying conditions. Therefore, it has been crucial for the accurate estimation of the selection of drying conditions needed for improving optimal drying process. In this study, DR and MR values have been experimentally determined, and these characteristics have been predicted as mathematical expressions by using gene expression programming (GEP). The outcomes of present study have been pointed out that the developed GEP models have been estimating target values with an acceptable accuracy guaranteed by using different statistical techniques. The R2 values have been denoted 0.973 and 0.972, whereas the RMSE values have been determined as 0.032324 and 0.013146 for developed models of DR and MR, respectively. The χ2values have been specified 0.001306 and 0.000194 for developed models of DR and MR, respectively. The developed nonlinear equations could be evaluated in areas you need to accurate and quick estimation of drying characteristics such as drying rate and moisture rate of mint. Practical Applications Mint drying kinetics (DR and MR) at different pressure of 30, 50, and 80 kPa and temperature of 40, 50, and 60°C have been experimentally studied. GEP model has been developed to predict this drying kinetics in the freeze‐drying process. Developed model can be evaluated in areas where you need to accurate and quick estimation of drying characteristics such as drying rate and moisture rate of mint.

show abstract

Artificial Intelligence (AI) in Food Processing

Abinaya,

Panghal,

Kumar

et al. 2024

Nonthermal Food Engineering Operations

View full text Add to dashboard Cite

Freeze-drying behaviour prediction of button mushrooms using artificial neural network and comparison with semi-empirical models

Cited by 38 publications

References 22 publications

Intelligent modeling and detailed analysis of drying, hydration, thermal, and spectral characteristics for convective drying of chicken breast slices

Intelligent modeling and detailed analysis of drying, hydration, thermal, and spectral characteristics for convective drying of chicken breast slices

Mathematical model for mint drying kinetics prediction by freeze‐drying process: Gene expression programming

Artificial Intelligence (AI) in Food Processing

Contact Info

Product

Resources

About