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

You might also read

Related Articles

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

Sort by
Same author

Gold-Nanorod-Assisted Live Cell Nuclear Imaging Based on Near-Infrared II Dark-Field Microscopy.

Biology·2023
Same author

Photodissociation dynamics of the ethyl radical via the Ã2A'(3s) state: H-atom product channels and ethylene product vibrational state distribution.

The Journal of chemical physics·2023
Same author

Laser-Induced Breakdown Spectroscopy Combined with Nonlinear Manifold Learning for Improvement Aluminum Alloy Classification Accuracy.

Sensors (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Oct 18, 2025

Dependence of Laser-induced Breakdown Spectroscopy Results on Pulse Energies and Timing Parameters Using Soil Simulants
08:53

Dependence of Laser-induced Breakdown Spectroscopy Results on Pulse Energies and Timing Parameters Using Soil Simulants

Published on: September 23, 2013

11.5K

Performing sequential forward selection and variational autoencoder techniques in soil classification based on

Edward Harefa1, Weidong Zhou1

  • 1Key Laboratory of Optical Information Detection and Display Technology of Zhejiang, Zhejiang Normal University, Jinhua, 321004, China. wdzhou@zjnu.cn.

Analytical Methods : Advancing Methods and Applications
|October 5, 2021
PubMed
Summary
This summary is machine-generated.

This study explored combining classification models with feature selection and dimensionality reduction for soil analysis using laser-induced breakdown spectroscopy (LIBS). Combining methods significantly improved classification accuracy, with Support Vector Machine (SVM) achieving the highest performance.

More Related Videos

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.4K
Improving Infrared Spectroscopy Characterization of Soil Organic Matter with Spectral Subtractions
08:57

Improving Infrared Spectroscopy Characterization of Soil Organic Matter with Spectral Subtractions

Published on: January 10, 2019

12.7K

Related Experiment Videos

Last Updated: Oct 18, 2025

Dependence of Laser-induced Breakdown Spectroscopy Results on Pulse Energies and Timing Parameters Using Soil Simulants
08:53

Dependence of Laser-induced Breakdown Spectroscopy Results on Pulse Energies and Timing Parameters Using Soil Simulants

Published on: September 23, 2013

11.5K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.4K
Improving Infrared Spectroscopy Characterization of Soil Organic Matter with Spectral Subtractions
08:57

Improving Infrared Spectroscopy Characterization of Soil Organic Matter with Spectral Subtractions

Published on: January 10, 2019

12.7K

Area of Science:

  • Analytical Chemistry
  • Spectroscopy
  • Machine Learning

Background:

  • Laser-induced breakdown spectroscopy (LIBS) is a powerful technique for elemental analysis.
  • Soil classification using LIBS data presents challenges due to high dimensionality and complex feature correlations.
  • Optimizing classification models is crucial for accurate and efficient LIBS data analysis.

Purpose of the Study:

  • To evaluate the effectiveness of combining classification models with feature selection and dimensionality reduction techniques for soil classification using LIBS.
  • To compare the performance of various classification algorithms (QDA, RF, BNB, SVM) when integrated with sequential feature selection (SFS) and dimensionality reduction methods (VAE, TSVD, Isomap).
  • To identify the optimal combination of techniques for maximizing classification accuracy in LIBS soil analysis.

Main Methods:

  • Investigated combinations of Quadratic Discriminant Analysis (QDA), Random Forest (RF), Bernoulli Naive Bayes (BNB), and Support Vector Machine (SVM) classifiers.
  • Applied Sequential Feature Selection (SFS) to reduce irrelevant features and improve model performance.
  • Utilized dimensionality reduction techniques including Variational Autoencoder (VAE), Truncated Singular Value Decomposition (TSVD), and Isomap.
  • Assessed classification performance based on accuracy metrics.

Main Results:

  • Sequential Feature Selection (SFS) improved the performance of all tested classification models, with SFS-SVM achieving 97.88% accuracy.
  • Dimensionality reduction techniques (VAE, TSVD, Isomap) further enhanced classification accuracy for all combined models.
  • The highest accuracies were obtained using Support Vector Machine (SVM) combined with dimensionality reduction: 98.12% with TSVD-SVM and 98.24% with VAE-SVM.
  • These methods effectively reduced uncorrelated features, high dimensionality, and redundant information in the LIBS dataset.

Conclusions:

  • Combining classification models with feature selection and dimensionality reduction techniques significantly optimizes LIBS soil classification performance.
  • Techniques like SFS, VAE, and TSVD are effective in handling the complexities of LIBS data, leading to higher accuracy.
  • The study demonstrates a robust approach for enhancing the utility of LIBS in soil analysis and related applications.