Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

858
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
858

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

High-Accuracy Prediction of Chunmee Tea Grade via DeepSpectra Model and Near-Infrared Spectroscopy.

Foods (Basel, Switzerland)·2026
Same author

Spectroscopic Methods Applied in Food Quality Determination.

Foods (Basel, Switzerland)·2026
Same author

Deep Learning-Enhanced Spectroscopic Technologies for Food Quality Assessment: Convergence and Emerging Frontiers.

Foods (Basel, Switzerland)·2025
Same author

Combining Feature Extraction Methods and Categorical Boosting to Discriminate the Lettuce Storage Time Using Near-Infrared Spectroscopy.

Foods (Basel, Switzerland)·2025
Same author

Geographical Origin Identification of Chinese Red Jujube Using Near-Infrared Spectroscopy and Adaboost-CLDA.

Foods (Basel, Switzerland)·2025
Same author

Near-Infrared Spectroscopy Combined with Fuzzy Improved Direct Linear Discriminant Analysis for Nondestructive Discrimination of Chrysanthemum Tea Varieties.

Foods (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 23, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

10.6K

Several Feature Extraction Methods Combined with Near-Infrared Spectroscopy for Identifying the Geographical Origins

Xiaohong Wu1,2, Yixuan Wang1, Chengyu He1

  • 1School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China.

Foods (Basel, Switzerland)
|June 19, 2024
PubMed
Summary

Fuzzy Direct Linear Discriminant Analysis (FDLDA) combined with Near-Infrared (NIR) spectroscopy accurately identifies milk origin. This method, using the k-nearest neighbor classifier, achieved 97.33% accuracy, outperforming other techniques for dairy traceability.

Keywords:
classificationfeature extractiongeographical originsmilknear-infrared spectroscopy

More Related Videos

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.6K
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.2K

Related Experiment Videos

Last Updated: Jun 23, 2025

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
10:25

Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements

Published on: June 28, 2016

10.6K
O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
06:50

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

6.6K
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.2K

Area of Science:

  • Food Science
  • Analytical Chemistry
  • Machine Learning

Background:

  • Tracing milk origin is crucial for consumer protection and dairy market stability.
  • Near-Infrared (NIR) spectroscopy offers a non-destructive method for analyzing milk composition.
  • Existing methods require robust data analysis techniques for accurate origin determination.

Purpose of the Study:

  • To develop and evaluate a novel method for determining milk origin using spectral data.
  • To compare the performance of Fuzzy Direct Linear Discriminant Analysis (FDLDA) with traditional methods.
  • To identify the most effective classification model for milk origin traceability.

Main Methods:

  • Collected Near-Infrared (NIR) spectral data from milk samples using a portable spectrometer.
  • Preprocessed spectral data using Savitzky-Golay (SG) and Standard Normal Variables (SNV) for noise reduction.
  • Reduced data dimensionality with Principal Component Analysis (PCA) and applied Linear Discriminant Analysis (LDA), Direct Linear Discriminant Analysis (DLDA), and FDLDA for feature extraction.
  • Classified samples using k-nearest neighbor (KNN), Extreme Learning Machine (ELM), and Naïve Bayes classifiers.

Main Results:

  • FDLDA achieved higher classification accuracy than DLDA when using the KNN classifier.
  • The highest recognition accuracy for FDLDA, DLDA, and LDA with KNN was 97.33%, 94.67%, and 94.67%, respectively.
  • FDLDA also outperformed DLDA with ELM and Naïve Bayes classifiers, though KNN demonstrated superior overall performance.

Conclusions:

  • FDLDA combined with NIR spectroscopy is an effective method for determining milk origin.
  • The k-nearest neighbor classifier is the most effective among the tested classifiers for this application.
  • This approach enhances dairy traceability and supports consumer interests.