|
|
Development of an artificial neural network asa tool for predicting the chemical attributes offresh peach fruits
|
|
|
Abstract: This investigation aimed to develop a method to predict the total soluble solids (TSS), titratableacidity, TSS/titratable acidity, vitamin C, anthocyanin, and total carotenoids contentsusing surface color values (L*, Hue and chroma), single fruit weight, juice volume, and sphericitypercent of fresh peach fruit. Multiple regression analysis (MLR) and an artificial neuralnetwork (ANN) were employed. An ANN model was developed with six inputs and 15 neuronsin the first hidden layer for the prediction of six chemical composition parameters. The resultsconfirmed that the ANN model R2 = 974–0.998 outperformed the MLR models R2= 0.473–0.840 using testing dataset. Moreover, sensitivity analysis revealed that the juice volume wasthe most dominating parameter for the prediction of titratable acidity, TSS/titratable acidityand vitamin C with corresponding contribution values of 39.97%, 50.40%, and 33.08%,respectively. In addition, sphericity percent contributed by 23.70% to anthocyanin and by24.08% to total carotenoids. Furthermore, hue on TSS prediction was the highest comparedwith the other parameters, with a contribution percentage of 20.86%. Chroma contributed bydifferent values to all variables in the range of 5.29% to 19.39%. Furthermore, fruit weight contributedby different values to all variables in the range of 16.67% to 23.48%. The ANN predictionmethod denotes a promising methodology to estimate targeted chemical compositionlevels of fresh peach fruits. The information of peach quality reported in this investigation canbe used as a baseline for understanding and further examining peach fruit quality.
|
| Publication year |
2021
|
| Organization Name |
|
| serial title |
PLoSONE
|
| Web Page |
|
| Author(s) from ARC |
|
| External authors (outside ARC) |
|
| Publication Type |
Journal
|