Predicting methionine and lysine contents in soybean meal and fish meal using a group method of data handling-type neural network

Mottaghitalab, Majid; Nikkhah, Mohsen; Darmani-Kuhi, H.; López, Secundino; France, J.

doi:10.5424/sjar/2015131-5877

Cited by 2 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the regression equations reported in NRC (1994) for predicting the amount of AA in ingredients is variable and low in some equations ( R 2 ˂ 0.5). Mottaghitalab et al. (2015) predicted Met ( R 2 = 75%) and Lys ( R 2 = 76%) contents from chemical composition (CP, EE, ash, CF, and moisture) in SBM using artificial neural network and found positive correlation with CP and negative correlation with CF.…”

Section: Resultsmentioning

confidence: 99%

Prediction of the total and standardized ileal digestible amino acid contents from the chemical composition of soybean meals of different origin in broilers

et al. 2020

View full text Add to dashboard Cite

The objective of this experiment was to determine total amino acid ( TAA ) content, standardized ileal digestibility ( SID ) of crude protein, and standardized ileal amino acid digestibility in 9 sources of soybean meal ( SBM ) of different origin and to subsequently establish equations for predicting the TAA content and concentration of standardized ileal digestible amino acids ( SIDAA ) based on their protein content and other proximate components. Concentration of SIDAA of the samples was also predicted using TAA values. A total of 160 1-day-old male broiler chicks were randomly assigned to 10 dietary treatments consisted of 9 semipurified diets containing one SBM (200 g of crude protein/kg) as the only source of dietary amino acid ( AA ) and one N-free diet to determine endogenous ileal AA flow. The birds were fed with a standard diet from 0 to 18 D of age, and experimental diets were fed from 19 to 24 D of age. The fitness of the models of the study was tested using the adjusted coefficient of determination ( R 2 ) value, P -value regression and coefficients, and standard error of prediction ( SEP ). The coefficient of SID for Lys and Cys among SBM varied from 86.7 to 96.3 and 74.1 to 89.3, respectively, with significant difference ( P < 0.05). In equations based on protein content, the adjusted R 2 value ranged from 40.7 (Ile) to 99.6 (Met) and 37.2 (Met + Cys) to 99.6 (Met) for TAA content and concentration of SIDAA, respectively. Inclusion of other proximate components of test samples (e.g., crude fiber, neutral detergent fiber, acid detergent fiber, ash, gross energy, and so on) into the regression equation increased the adjusted R 2 value and decreased the SEP. The results of linear regression revealed that it is possible to satisfactorily estimate the TAA content and concentration of SIDAA of SBM through its protein content and other proximate components, but the prediction equations based on other proximate components were more accurate in terms of reflecting the measured results; however, additional time and costs were associated with this approach. It is also possible to estimate the concentration of SIDAA through TAA values with reasonable accuracy and lower SEP.

show abstract

Section: Resultsmentioning

confidence: 99%

Prediction of the total and standardized ileal digestible amino acid contents from the chemical composition of soybean meals of different origin in broilers

et al. 2020

View full text Add to dashboard Cite

show abstract

An automatic and non-intrusive hybrid computer vision system for the estimation of peel thickness in Thomson orange

Javadikia

Sabzi

Arribas

2019

Span. j. agric. res.

View full text Add to dashboard Cite

Orange peel has important flavor and nutrition properties and is often used for making jam and oil in the food industry. For previous reasons, oranges with high peel thickness are valuable. In order to properly estimate peel thickness in Thomson orange fruit, based on a number of relevant image features (area, eccentricity, perimeter, length/area, blue component, green component, red component, width, contrast, texture, width/area, width/length, roughness, and length) a novel automatic and non-intrusive approach based on computer vision with a hybrid particle swarm optimization (PSO), genetic algorithm (GA) and artificial neural network (ANN) system is proposed. Three features (width/area, width/length and length/area ratios) were selected as inputs to the system. A total of 100 oranges were used, performing cross validation with 100 repeated experiments with uniform random samples test sets. Taguchi’s robust optimization technique was applied to determine the optimal set of parameters. Prediction results for orange peel thickness (mm) based on the levels that were achieved by Taguchi’s method were evaluated in several ways, including orange peel thickness true-estimated boxplots for the 100 orange database and various error parameters: the sum square error (SSE), the mean absolute error (MAE), the coefficient of determination (R2), the root mean square error (RMSE), and the mean square error (MSE), resulting in mean error parameter values of R2=0.854±0.052, MSE=0.038±0.010, and MAE=0.159±0.023, over the test set, which to our best knowledge are remarkable numbers for an automatic and non-intrusive approach with potential application to real-time orange peel thickness estimation in the food industry.

show abstract

Predicting methionine and lysine contents in soybean meal and fish meal using a group method of data handling-type neural network

Cited by 2 publications

References 25 publications

Prediction of the total and standardized ileal digestible amino acid contents from the chemical composition of soybean meals of different origin in broilers

Prediction of the total and standardized ileal digestible amino acid contents from the chemical composition of soybean meals of different origin in broilers

An automatic and non-intrusive hybrid computer vision system for the estimation of peel thickness in Thomson orange

Contact Info

Product

Resources

About