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
  1. Home
  3. Prediction Of Quality Traits In Packaged Mango By Nir Spectroscopy.
  1. Home
  3. Prediction Of Quality Traits In Packaged Mango By Nir Spectroscopy.

Related Concept Videos

Key Elements for Plant Nutrition02:35

Key Elements for Plant Nutrition

18.6K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.6K

Related Experiment Video

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

10.5K

Prediction of quality traits in packaged mango by NIR spectroscopy.

Fangchen Ding1, Juan Francisco García-Martín2, Li Zhang3

  • 1Sanya Institute of Nanjing Agricultural University, Sanya, Hainan 572024, China; College of Food Science and Technology, Nanjing Agricultural University, No. 1, Weigang Road, Nanjing, Jiangsu 210095, China; Departamento de Ingeniería Química, Facultad de Química, Universidad de Sevilla 41012 Sevilla, Spain.

Food Research International (Ottawa, Ont.)
|March 3, 2025

View abstract on PubMed

Summary
This summary is machine-generated.

Paper bags interfere with near-infrared (NIR) spectral analysis of mangoes. A deep learning model combined with Gaussian spatial filtering effectively removed this interference, enabling accurate quality assessments of packaged mangoes.

Keywords:
Deep learningMango qualityNIR spectroscopyNon-invasive analysisPaper bag packagingSpectral filtering

More Related Videos

Fruit Volatile Analysis Using an Electronic Nose
11:02

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

21.2K
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

6.5K

Related Experiment Videos

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

10.5K
Fruit Volatile Analysis Using an Electronic Nose
11:02

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

21.2K
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

6.5K

Area of Science:

  • Agricultural Science
  • Spectroscopy
  • Machine Learning

Background:

  • Paper bag packaging protects mangoes during growth.
  • Near-infrared (NIR) spectroscopy is crucial for non-invasive quality analysis.
  • Paper bags significantly interfere with NIR spectral signals, reducing prediction accuracy.

Purpose of the Study:

  • To eliminate or minimize paper bag interference in mango NIR spectra.
  • To develop innovative solutions for accurate quality assessment of packaged mangoes.
  • To evaluate the performance of deep learning and filtering techniques for spectral correction.

Main Methods:

  • Utilized a deep learning-based fully connected neural network (FNN).
  • Applied Gaussian spatial (GS) filtering to mitigate spectral interference.
  • Employed partial least squares regression (PLSR) and principal components regression (PCR) for quality trait prediction.

Main Results:

  • FNN combined with GS filtering effectively reduced spectral interference from paper bags.
  • PLSR demonstrated superior performance over PCR for predicting firmness, dry matter content (DMC), soluble solids content (SSC), and titratable acidity (TA).
  • Achieved reliable predictive accuracy for packaged mangoes, with notable Rp2 values for DMC (0.932) and TA (0.907).

Conclusions:

  • The combination of deep learning (FNN) and GS filtering is an effective strategy for correcting spectral interferences in packaged mangoes.
  • Accurate non-invasive assessment of mango internal quality traits (firmness, DMC, SSC, TA) is achievable even with paper bag packaging.
  • This approach offers a promising solution for quality control in the fruit industry.