Non‐destructive measurement of eggshell strength using NIR spectroscopy and explainable artificial intelligence DOI Creative Commons

Md Wadud Ahmed,

S. Sharar Alam,

Alin Khaliduzzaman

et al.

Journal of the Science of Food and Agriculture, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Abstract Background Eggshell strength is crucial for ensuring high‐quality eggs, reducing breakage during handling, and meeting consumer expectations freshness integrity. Conventional methods of eggshell measurement are often destructive, time‐consuming unsuitable large‐scale applications. This study evaluated the potential near‐infrared (NIR) spectroscopy combined with explainable artificial intelligence (AI) as a rapid, non‐destructive method determining strength. Various multivariate analysis techniques were explored to enhance prediction accuracy, including spectral pre‐processing variable selection methods. Results Principal component partial least squares discriminant effectively classified eggs based on threshold shell 30 N. Regression models, regression, random forest (RF), light gradient boosting machine K‐nearest neighbors, evaluated. Using only 14 selected variables, RF model achieved very good performance 0.83, root mean square error 1.49 N ratio deviation 2.44. The Shapley additive explanation approach provided insights into contributions, enhancing model's interpretability. Conclusion demonstrated that NIR spectroscopy, integrated AI, robust, environmentally sustainable prediction. innovative holds significant optimizing resource utilization quality control in egg industry. © 2025 Author(s). Journal Science Food Agriculture published by John Wiley & Sons Ltd behalf Society Chemical Industry.

Language: Английский

Non-destructive detection of pre-incubated chicken egg fertility using hyperspectral imaging and machine learning DOI Creative Commons

Md Wadud Ahmed,

Asher Sprigler,

J.L. Emmert

et al.

Smart Agricultural Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100857 - 100857

Published: Feb. 1, 2025

Language: Английский

Citations

1
Non-destructive pre-incubation sex determination in chicken eggs using hyperspectral imaging and machine learning DOI Creative Commons
Md Wadud Ahmed,

Asher Sprigler,

J.L. Emmert

et al.

Food Control, Journal Year: 2025, Volume and Issue: unknown, P. 111233 - 111233

Published: Feb. 1, 2025

Language: Английский

Citations

0
A systematic review of explainable artificial intelligence for spectroscopic agricultural quality assessment DOI Creative Commons
Md. Toukir Ahmed,

Md Wadud Ahmed,

Mohammed Kamruzzaman

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 235, P. 110354 - 110354

Published: April 4, 2025

Language: Английский

Citations

0
Non‐destructive measurement of eggshell strength using NIR spectroscopy and explainable artificial intelligence DOI Creative Commons

Md Wadud Ahmed,

S. Sharar Alam,

Alin Khaliduzzaman

et al.

Journal of the Science of Food and Agriculture, Journal Year: 2025, Volume and Issue: unknown

Published: April 17, 2025

Abstract Background Eggshell strength is crucial for ensuring high‐quality eggs, reducing breakage during handling, and meeting consumer expectations freshness integrity. Conventional methods of eggshell measurement are often destructive, time‐consuming unsuitable large‐scale applications. This study evaluated the potential near‐infrared (NIR) spectroscopy combined with explainable artificial intelligence (AI) as a rapid, non‐destructive method determining strength. Various multivariate analysis techniques were explored to enhance prediction accuracy, including spectral pre‐processing variable selection methods. Results Principal component partial least squares discriminant effectively classified eggs based on threshold shell 30 N. Regression models, regression, random forest (RF), light gradient boosting machine K‐nearest neighbors, evaluated. Using only 14 selected variables, RF model achieved very good performance 0.83, root mean square error 1.49 N ratio deviation 2.44. The Shapley additive explanation approach provided insights into contributions, enhancing model's interpretability. Conclusion demonstrated that NIR spectroscopy, integrated AI, robust, environmentally sustainable prediction. innovative holds significant optimizing resource utilization quality control in egg industry. © 2025 Author(s). Journal Science Food Agriculture published by John Wiley & Sons Ltd behalf Society Chemical Industry.

Language: Английский

Citations

0