A Machine Learning Approach for Honey Adulteration Detection using Mineral Element Profiles

TL;DR

This study develops a machine learning system that accurately detects honey adulteration by analyzing mineral element profiles, achieving over 98% accuracy with random forest classifiers.

Contribution

The paper introduces a novel ML-based approach using mineral element profiles for honey adulteration detection, demonstrating high accuracy and effectiveness.

Findings

Random forest classifier achieved 98.37% accuracy.

Mineral element content effectively discriminates authentic and adulterated honey.

ML models outperform traditional methods in honey adulteration detection.

Abstract

This paper aims to develop a Machine Learning (ML)-based system for detecting honey adulteration utilizing honey mineral element profiles. The proposed system comprises two phases: preprocessing and classification. The preprocessing phase involves the treatment of missing-value attributes and normalization. In the classifica-tion phase, we use three supervised ML models: logistic regression, decision tree, and random forest, to dis-criminate between authentic and adulterated honey. To evaluate the performance of the ML models, we use a public dataset comprising measurements of mineral element content of authentic honey, sugar syrups, and adul-terated honey. Experimental findings show that mineral element content in honey provides robust discriminative information for detecting honey adulteration. Results also demonstrate that the random forest-based classifier outperforms other classifiers on this dataset, achieving the highest cross-validation accuracy of 98.37%.