Application of Artificial Neural Networks to Food and Fermentation Technology

Bhotmange, Madhukar; Shastri, P. N.

doi:10.5772/16067

Cited by 13 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, ANNs can be used to analyze more data at the same time with more complicated and complex interactions. Even if the data is incomplete and noisy, ANNs can outperform MLR in prediction, modeling, and optimization [ 52 ]. Therefore, MLR models were unsuitable for our research, whereas the ANNs prediction model accurately predicted the quality attributes we were looking for.…”

Section: Resultsmentioning

confidence: 99%

“…Therefore, ANN applications are considered useful food quality and safety tools, such as modeling microbial growth; interpreting spectroscopic data; and predicting the food safety, physiochemical, sensory, and functional properties of food products during processing, storing, and distribution. In addition, these models are innovative techniques that offer a lot more potential for complicated modeling tasks in simulation and process control for food safety and quality management [ 52 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models

Mohammed

Munir

Aljabr³

2022

Foods

View full text Add to dashboard Cite

Evaluating and predicting date fruit quality during cold storage is critical for ensuring a steady supply of high-quality fruits to meet market demands. The traditional destructive methods take time in the laboratory, and the results are based on one specific parameter being tested. Modern modeling techniques, such as Machine Learning (ML) algorithms, offer unique benefits in nondestructive methods for food safety detection and predicting quality attributes. In addition, the electrical properties of agricultural products provide crucial information about the interior structures of biological tissues and their physicochemical status. Therefore, this study aimed to use an alternative approach to predict physicochemical properties, i.e., the pH, total soluble solids (TSS), water activity (aw), and moisture content (MC) of date fruits (Tamar), during cold storage based on their electrical properties using Artificial Neural Networks (ANNs), which is the most popular ML technique. Ten date fruit cultivars were studied to collect data for the targeted parameters at different cold storage times (0, 2, 4, and 6 months) to train and test the ANNs models. The electrical properties of the date fruits were measured using a high-precision LCR (inductance, capacitance, and resistance) meter from 10 Hz to 100 kHz. The ANNs models were compared with a Multiple Linear Regression (MLR) at all testing frequencies of the electrical properties. The MLR models were less accurate than ANNs models in predicting fruit pH and had low performance and weak predictive ability for the TSS, aw, and MC at all testing frequencies. The optimal ANNs prediction model consisted of the input layer with 14 neurons, one hidden layer with 15 neurons, and the output layer with 4 neurons, which was determined depending on the measurements of the electrical properties at a 10 kHz testing frequency. This optimal ANNs model was able to predict the pH with R2 = 0.938 and RMSE = 0.121, TSS with R2 = 0.954 and RMSE = 2.946, aw with R2 = 0.876 and RMSE = 0.020, and MC with R2 = 0.855 and RMSE = 0.803 b by using the measured electrical properties. The developed ANNs model is a powerful tool for predicting fruit quality attributes after learning from the experimental measurement parameters. It can be suggested to efficiently predict the pH, total soluble solids, water activity, and moisture content of date fruits based on their electrical properties at 10 kHz.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models

Mohammed

Munir

Aljabr³

2022

Foods

View full text Add to dashboard Cite

show abstract

“…Deep learning has outperformed manual feature extraction and conventional machine learning techniques in food quality analysis [31]. Deep learning has been used in food classification, quality detection, calorie estimation and food contamination investigation [4,8,31].…”

Section: Computer Visionmentioning

confidence: 99%

OnionBot: A System for Collaborative Computational Cooking

Cobley,

Boyle

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…ANN is a biologically inspired optimization technique which predicts the dependent variable accurately by recognizing the complex patterns from the data through a model development between independent and dependent variables based on the repeated learnings and stored examples (Yu et al, 2018). ANN was used for optimization of food processing and used in predictive modeling (Basak et al, 2020; Bhotmange & Shastri, 2011; Pandiselvam, Manikantan, Sunoj, Sreejith, & Beegum, 2019; Piekutowska et al, 2021). ANN modeling was used to study the influence of microwave power, time, butter level, and sodium bicarbonate level on microwave puffing characteristics of preconditioned rice (Dash & Das, 2021); to optimize process parameters of fluidized bed dryer for drying green tea leaves with feed forward back propagation method (Kalathingal, Basak, & Mitra, 2020); to study the effect of time and temperature of hot air roasting on characteristics of Chironji kernels was studied using ANN model combined genetic algorithm (Pradhan & Pradhan, 2020a) and ANN model combined genetic algorithm was used for optimization process parameters of Chironji (Buchanania lanzan) nut decorticator (Pradhan & Pradhan, 2020b).…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Modeling of process parameters to predict the efficiency of shallots stem cutting machine using multiple regression and artificial neural network

Anand

Pare

Chandrasekar

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

The shallot stem cutting machine process parameters were optimized and analyzed to develop predictive models for predicting the efficiency of the machine for scale up process. The efficiency of the machine was above 90%. Influence of peripheral speed of the rollers and inclination angle of the rollers on efficiency was determined and models were developed using multiple linear regression and artificial neural network (ANN) models. The coefficients of multiple linear models were estimated and the equations were constructed.A two-layer neural network consists of eight neurons in hidden layer and one neuron in the output layer was established. The models were validated and their performance was assessed using statistical parameters like R 2 , adjusted R 2 , and root mean square error values. R values of ANN model's training, testing, and validation were .998, .990, .998, and .996, respectively. R 2 values of multiple linear regression analysis ranged from .618 to .722 and .992 for ANN model. The developed models have minimum mean square error of 0.47, 0.13, 0.59, 0.58, and 0.77 for multiple regression models and 0.208 for ANN model. The degree of fitting between estimated and predicted values was described using bias factor ranged from 0.99 to 1.02. The comparison plots of actual efficiency versus predicted efficiency showed that the machine efficiency predicted by ANN model was in good agreement with actual efficiency. Hence, the results concluded that the ANN model is more suitable for predict the efficiency of shallot's stem cutting machine. Practical ApplicationsProcessing of onion at industrial scale is very essential to ease the process of preparation of dishes at household. The shallot onion stem cutting is part of the unit operation involved in onion processing. A stem cutting machine was designed, developed, and process parameters were optimized. Mathematical model was developed to predict the efficiency using multiple linear regression and artificial neural network. The models will be used for developing automatic industrial scale machine.

show abstract

Application of Artificial Neural Networks to Food and Fermentation Technology

Cited by 13 publications

References 30 publications

Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models

Prediction of Date Fruit Quality Attributes during Cold Storage Based on Their Electrical Properties Using Artificial Neural Networks Models

OnionBot: A System for Collaborative Computational Cooking

Modeling of process parameters to predict the efficiency of shallots stem cutting machine using multiple regression and artificial neural network

Contact Info

Product

Resources

About