TY - GEN
T1 - Improving Honey Adulteration Detection with Feature Selection and Resampling
AU - Salahuddin, Sumayyea
AU - Zafar, Mohammad Haseeb
AU - Khan, Maryam Mahsal
AU - Minallah, Nasru
AU - Khan, Shah Haseeb Ahmad
AU - Rizwan, Esha
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025/9/4
Y1 - 2025/9/4
N2 - Pure and reliable honey is essential. This research addresses honey adulteration detection using hyperspectral imagery, feature selection, resampling, and machine learning. Hyperspectral data from the New Zealand honey dataset, representing various honey types and adulteration levels, was analyzed using SVM, LR, and RF. The dataset was split 80–20% for training and testing, with fivefold cross-validation on the training set. Four models were evaluated: baseline, RFE-based feature selection, SMOTE for class imbalance, and SMOTE with PCA for dimensionality reduction. RF performed best, achieving a 0.996 mean accuracy, 0.997 test accuracy, and F1 scores of 0.986 (pure) and 0.998 (adulterated) for the RFE model with 75 key features. This study offers an accurate, efficient solution for honey adulteration detection, enhancing quality assessment and consumer trust.
AB - Pure and reliable honey is essential. This research addresses honey adulteration detection using hyperspectral imagery, feature selection, resampling, and machine learning. Hyperspectral data from the New Zealand honey dataset, representing various honey types and adulteration levels, was analyzed using SVM, LR, and RF. The dataset was split 80–20% for training and testing, with fivefold cross-validation on the training set. Four models were evaluated: baseline, RFE-based feature selection, SMOTE for class imbalance, and SMOTE with PCA for dimensionality reduction. RF performed best, achieving a 0.996 mean accuracy, 0.997 test accuracy, and F1 scores of 0.986 (pure) and 0.998 (adulterated) for the RFE model with 75 key features. This study offers an accurate, efficient solution for honey adulteration detection, enhancing quality assessment and consumer trust.
KW - Honey adulteration detection
KW - Hyperspectral imagery
KW - Machine learning
KW - Principal component analysis
KW - Recursive feature elimination
KW - Synthetic minority over-sampling technique
UR - https://www.scopus.com/pages/publications/105022933418
U2 - 10.1007/978-981-96-7400-8_5
DO - 10.1007/978-981-96-7400-8_5
M3 - Conference contribution
AN - SCOPUS:105022933418
SN - 9789819673995
T3 - Lecture Notes in Networks and Systems
SP - 53
EP - 63
BT - AI Applications in Cyber Security and Privacy of Communication Networks - Proceedings of 10th International Conference on Cyber Security, Privacy in Communication Networks, ICCS 2024
A2 - Hewage, Chaminda E. R.
A2 - Zafar, Mohammad Haseeb
A2 - Kesswani, Nishtha
PB - Springer Science and Business Media Deutschland GmbH
T2 - 10th International Conference on Cyber Security, Privacy in Communication Networks, ICCS 2024
Y2 - 9 December 2024 through 10 December 2024
ER -