Machine Learning-Based Detection of Lard Adulteration from IRMS and TAG Chromatographic Data
Item
-
Tittle
-
Machine Learning-Based Detection of Lard Adulteration from IRMS and TAG Chromatographic Data
-
Conference Acronym
-
IHSATEC 2025: 18th HASIB
-
DOI Number
-
doi.org/10.31098/HST25128
-
Conference Date
-
December 18, 2025
-
presented at
-
The International Halal Science and Technology Conference 2025 (IHSATEC): 18th Halal Science Industry and Business (HASIB)
-
Poster Author(S)
-
Nor Nadiha Mohd Zaki
-
Conference Theme
-
IHSATEC 2025: 18th HASIB
-
Abstract
-
Background – The authentication of fish feed ingredients is critical for ensuring compliance with Halal standards, particularly the absence of lard-derived fats.
Purpose – This study compares the analytical performance of high-performance liquid chromatography, and isotope ratio mass spectrometry (IRMS) for detecting lard adulteration in fish feed formulations
Design/methodology/approach – Triacylglycerol (TAG) and Delta C (C) were analyzed and integrated with chemometric and machine learning approaches to classify samples containing different proportions of lard and palm oil. Principal Component Analysis (PCA) and Partial Least Squares–Discriminant Analysis (PLS-DA) were employed for pattern recognition and exploratory classification, while Support Vector Machine (SVM) and Random Forest (RF) models were optimized using stratified cross-validation for predictive validation.
Findings – The SVM model achieved an overall accuracy of 82%, effectively distinguishing feed formulations containing as low as 2–6% lard. Variable Importance in Projection (VIP) and feature importance analyses consistently identified key discriminatory fatty acids, including POL, PPO, and C18:1, which contributed significantly to class separation.
Research limitations – Small dataset (54 replicates)
Originality/value – These results confirm that integrating chromatographic data with chemometrics and machine learning provides a reproducible, data-driven workflow for reliable and scalable authentication of Halal fish feed ingredients.
-
Publisher Name
-
Yayasan Sinergi Riset dan Edukasi
-
Publication Date Online
-
December 18, 2025
