TY - JOUR
T1 - SPECTROSCOPY DATA CALIBRATION USING STACKED ENSEMBLE MACHINE LEARNING
AU - SOLIHIN, MAHMUD IWAN
AU - YUAN, CHAN JIN
AU - HONG, WAN SIU
AU - PUI, LIEW PHING
AU - ANG, CHUN KIT
AU - HOSSAIN, W. A.F.A.
AU - MACHMUDAH, AFFIANI
N1 - Publisher Copyright:
© (2024) International Islamic University Malaysia-IIUM.
PY - 2024
Y1 - 2024
N2 - Near infrared spectroscopy (NIRS) is a widely used analytical technique for non-destructive analysis of various materials including food fraud detection. However, the accurate calibration of NIRS data can be challenging due to the complexity of the underlying relationships between the spectral data and the target variables of interest. Ensemble learning, which combines multiple models to make predictions, has been shown to improve the accuracy and robustness of predictive models in various domains. This paper proposes stacking ensemble machine learning (SEML) for calibration of NIRS data with two levels of learning involved. Eight (8) spectroscopy datasets from public repository and previously published works by the authors are used as the case study. The model well generalized the data in the respective regression tasks with R2 of at least ≈0.8 in the test samples and in therespective classification tasks with classification accuracy (CA) of at least ≈0.8 also. In addition, the proposed SEML can improve, or at least reach par with, the accuracy of individual base learners in both train and test samples for all cases of regression and classification datasets. It shows superior performance in test samples for both regression and classification datasets with respectively R2 ranging from 0.86 to nearly 1 and CA rangingfrom 0.89 to 1.
AB - Near infrared spectroscopy (NIRS) is a widely used analytical technique for non-destructive analysis of various materials including food fraud detection. However, the accurate calibration of NIRS data can be challenging due to the complexity of the underlying relationships between the spectral data and the target variables of interest. Ensemble learning, which combines multiple models to make predictions, has been shown to improve the accuracy and robustness of predictive models in various domains. This paper proposes stacking ensemble machine learning (SEML) for calibration of NIRS data with two levels of learning involved. Eight (8) spectroscopy datasets from public repository and previously published works by the authors are used as the case study. The model well generalized the data in the respective regression tasks with R2 of at least ≈0.8 in the test samples and in therespective classification tasks with classification accuracy (CA) of at least ≈0.8 also. In addition, the proposed SEML can improve, or at least reach par with, the accuracy of individual base learners in both train and test samples for all cases of regression and classification datasets. It shows superior performance in test samples for both regression and classification datasets with respectively R2 ranging from 0.86 to nearly 1 and CA rangingfrom 0.89 to 1.
KW - chemometrics calibration
KW - food fraud detection
KW - food safety and security
KW - near infrared spectroscopy
KW - stacking ensemble machine learning
UR - http://www.scopus.com/inward/record.url?scp=85186886879&partnerID=8YFLogxK
U2 - 10.31436/iiumej.v25i1.2796
DO - 10.31436/iiumej.v25i1.2796
M3 - Article
AN - SCOPUS:85186886879
SN - 1511-788X
VL - 25
SP - 208
EP - 224
JO - IIUM Engineering Journal
JF - IIUM Engineering Journal
IS - 1
ER -