Decision Tree and K-Means Analysis of Raman Spectra for Edible Oils: A Physics-Informed AI Approach
Summary
The study establishes a physics-informed AI framework using Raman spectroscopy and machine learning to authenticate edible oils, achieving high classification accuracy with compact spectral representations.
View Cached Full Text
Cached at: 08/24/26, 04:29 AM
# Decision Tree and K-Means Analysis of Raman Spectra for Edible Oils: A Physics-Informed AI Approach Source: [https://arxiv.org/abs/2608.20440](https://arxiv.org/abs/2608.20440) [View PDF](https://arxiv.org/pdf/2608.20440) > Abstract:Authentication of edible oils in processed foods is important for food quality, fraud prevention, and regulatory compliance\. This study establishes an integrated Raman spectroscopy and machine\-learning framework that links intrinsic spectral organization, interpretable classification, and Physics\-Informed Artificial Intelligence \(PI\-AI\)\. Five edible oils were investigated in pure form and within a fried\-potato\-chip matrix using t\-SNE, K\-means clustering, Decision Trees, and Non\-Negative Least Squares \(NNLS\)\-based spectral decomposition\. Unsupervised analyses revealed substantially stronger class organization and separability in pure oils, whereas food\-matrix effects introduced pronounced spectral overlap\. Decision Trees achieved 100% classification accuracy for pure oils using only four Raman variables from the original 1866\-feature spectral space\. These four variables, consistently identified by both pre\-pruned and post\-pruned models, represented only approximately 0\.21% of the available spectral information while retaining perfect test\-set performance\. For matrix\-containing samples, NNLS\-based PI\-AI spectral decomposition substantially improved classification by separating oil\-related signatures from paper and potato contributions\. Optimized post\-pruned models achieved accuracies of 86\.4% and 85\.4% for paper\-subtracted and paper\-plus\-potato\-subtracted datasets, respectively, while reducing the number of important Raman variables to only five and four\. The compact four\-feature representation further reduced the data footprint by 99\.44% without loss of classification accuracy\. Collectively, these findings demonstrate that accurate Raman\-based oil identification can be achieved through physically meaningful, highly compact, and interpretable spectral representations, providing a promising foundation for Frugal AI, Edge AI, portable sensing, and embedded food\-quality monitoring\. ## Submission history From: Deepak Kallepalli Dr\. \[[view email](https://arxiv.org/show-email/91cf581c/2608.20440)\] **\[v1\]**Thu, 20 Aug 2026 14:07:32 UTC \(1,814 KB\)
Similar Articles
Machine Learning for Biomedical Raman Spectroscopy: From Spectral Acquisition to Clinical Translation
This review examines the role of machine learning across the biomedical Raman spectroscopy pipeline, from preprocessing and signal correction to clinical translation, highlighting barriers and future directions for reliable Raman-AI systems.
Hybrid Machine Learning-Assisted Raman Spectroscopy with Generative Feature Augmentation for Pharmaceutical Identification
This paper proposes HyMLRaman, a hybrid framework combining EfficientNet-B3 spectral embeddings with classical classifiers (notably SVM) and DDPM-based generative feature augmentation to identify six pharmaceutical compounds via Raman spectroscopy, achieving 96.31% accuracy.
Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
This paper demonstrates the use of Sharpness-Aware Minimization (SAM) to enhance the generalization of machine learning models for classifying bacterial Raman spectral data, improving accuracy by up to 10.5% and advancing portable diagnostic tools for antimicrobial resistance.
A Kernel Fisher Discriminant Analysis-Based Tree Ensemble Classifier: KFDA Forest
Proposes a tree-based ensemble classifier called KFDA Forest that applies kernel Fisher discriminant analysis for rotation, using bootstrap and random variable subsets to promote diversity, achieving improved classification accuracy.
Operational Range Bounding in Spectroscopy: A Safety Cage Framework for Machine Learning Models
This paper introduces a safety cage framework for bounding the operational range of machine learning models in transit spectroscopy, demonstrating error reductions through indicator fusion to enhance reliability in safety-critical space missions.