NIR Spectroscopy Oranges Origin Identification Framework Based on Machine Learning
importance 3/10
partially solved
Spectroscopy and Chemometric Analyses food authentication stage: research
Problem
Identifying the geographic origin of oranges from NIR spectral data is needed for food authentication and quality control.
Why it matters
Origin mislabeling affects food safety, trade integrity and consumer trust.
What the AI did
A machine learning framework combining data preprocessing, feature selection, model building and cross-validation classified orange origins from NIR spectra.
Results
Best origin identification accuracy of 92.8%.
Impact
Evidence supports ML-based orange origin identification at 92.8% accuracy on tested data.
Record
| Venue | International Journal on Semantic Web and Information Systems |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Songjian Dan |
| Citations | 15 (OpenAlex, at import time) |
| References | 32 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.4018/ijswis.297039 |
| Open access | diamond |
| Keywords | NIR spectroscopy, machine learning, food authentication, orange origin, classification |
Importance rating
3
incremental / niche
Orange origin authentication via NIR supports food quality control; abstract reports only classification accuracy on tested data, a niche application with no stated scale of mislabeling or trade impact.