Machine Learning Application in Food Safety, Production, and Quality

Kaviani, Mitra; Dara, Rozita; Farber, Jeffrey M.

doi:10.1007/978-3-031-07179-9_1

Cited by 1 publication

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks based on supervised learning aims to estimate the primary functions by modeling problems having non-linear nature. 16 The high efficiency and customizability of these networks can make effective predictions for quality of food products developed from different blend formulations under efficiently controlled conditions. 17 Multilayer perceptron neural network is a feedforward neural network algorithm which learns association between non-linear and linear data and utilizes backpropagation algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…Evaluation of a function based on known examples is called supervised learning. Artificial neural networks based on supervised learning aims to estimate the primary functions by modeling problems having non‐linear nature 16 . The high efficiency and customizability of these networks can make effective predictions for quality of food products developed from different blend formulations under efficiently controlled conditions 17 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effectual study, statistical optimization, and neural network‐based predictive model of pearl millet and amaranth flours formulations for gluten‐free pasta

Rathore,

Pandey

2023

JSFA Reports

View full text Add to dashboard Cite

BackgroundPasta is prepared from high‐gluten wheat flour but poses great harm to gluten‐intolerant population or celiac disease patients. Pearl millet flour is the cheapest among gluten‐free flours and has a high nutritive index. Amaranth is a promising source of protein and fiber and is gluten‐free in nature. Several studies have been done for the development of gluten‐free pasta using different flour blends but an optimized formulation with high nutritive value and consumer satisfaction has not yet been identified.ResultsIn this study, different blends of pearl millet and amaranth flour were used in ratios of 90:10, 80:20, 70:30, 60:40, and 50:50 for pasta preparation and their analysis based on farinographic parameters, cooking quality, and sensory scores was done. Statistical analysis by analysis of variance followed by Duncan's Multiple Range Test was performed to evaluate the optimized formulation. 60:40 blend ratio for pearl millet and amaranth flour displayed comparable farinographic properties and cooking yield to wheat‐based pasta with optimized cooking loss and an overall sensory score of 8.65. Scanning electron microscopy analysis of flours and the cooked and uncooked pasta samples was also performed. Further, a multilayer perceptron neural network was developed to predict the overall quality and grade of pasta. The developed neural network gave high classification accuracy of 90.9% and 100% for training and testing sets, respectively, and can be utilized for pasta quality prediction.ConclusionThis study provides optimized pearl millet and amaranth flour blend formulation to prepare gluten‐free delicious pasta for celiac disease patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%