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

Corrigendum to "Legacy and emerging organohalogenated contaminants in wild edible aquatic organisms: Implications for bioaccumulation and human exposure" [Sci. Total Environ., 616-617 (2018) 38-45].

The Science of the total environment·2026
Same author

Time-domain optimization based NMPC path tracking control for underground LHD.

Scientific reports·2025
Same author

Seasonal bioaccumulation and biomagnification of typical organochlorine pesticides in the Pearl River Estuary, South China.

Environmental pollution (Barking, Essex : 1987)·2025
Same author

Heterozygosity for Crohn's disease risk allele of ATG16L1 promotes unique protein interactions and protects against bacterial infection.

Immunity·2025
Same author

Evolution of airblast induced by roof collapse based on LBM-DEM.

Scientific reports·2025
Same author

Association of pericoronary inflammation with atherosclerotic plaque progression in diabetic patients with improved modifiable cardiovascular risk factors: a longitudinal CCTA cohort study.

Diabetology & metabolic syndrome·2025

Related Experiment Video

Updated: Dec 11, 2025

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

497

Microseismic records classification using capsule network with limited training samples in underground mining.

Pingan Peng1,2, Zhengxiang He3,4, Liguan Wang1,2

  • 1School of Resources and Safety Engineering, Central South University, Changsha, 410083, China.

Scientific Reports
|August 20, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a new method for classifying microseismic events in mines using capsule networks (CapsNet), achieving high accuracy even with limited data. The approach outperforms traditional machine learning and convolutional neural networks (CNN).

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.6K
Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt
07:58

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt

Published on: August 7, 2017

9.7K

Related Experiment Videos

Last Updated: Dec 11, 2025

Mining Spatial Transcriptomics Datasets using DeepSpaceDB
10:16

Mining Spatial Transcriptomics Datasets using DeepSpaceDB

Published on: September 5, 2025

497
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.6K
Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt
07:58

Data Processing Methods for 3D Seismic Imaging of Subsurface Volcanoes: Applications to the Tarim Flood Basalt

Published on: August 7, 2017

9.7K

Area of Science:

  • Geophysics
  • Seismology
  • Machine Learning

Background:

  • Accurate identification of microseismic events is critical for mine safety and operational efficiency.
  • Current automatic classification methods require extensive manual data, posing challenges for mines with limited historical records.
  • Developing robust classification techniques for microseismic data with small sample sizes is an ongoing research need.

Purpose of the Study:

  • To present an effective method for automatic classification of microseismic records in underground mines using limited training samples.
  • To evaluate the performance of capsule networks (CapsNet) for microseismic event classification compared to existing methods.
  • To demonstrate the feasibility of applying advanced machine learning techniques in environments with scarce labeled data.

Main Methods:

  • Microseismic records were divided into 33 frames, and 21 time- and frequency-domain features were extracted per frame.
  • A 21x33 feature matrix was used as input for a capsule network (CapsNet) model.
  • Classification models were trained with varying sizes of limited training sets and compared against convolutional neural networks (CNN) and traditional machine learning algorithms.

Main Results:

  • The proposed CapsNet method achieved a classification accuracy of 99.2% with limited training samples.
  • The method demonstrated superior performance over CNN and traditional machine learning approaches across multiple metrics, including Accuracy, Precision, Recall, and F1-Measure.
  • The reliability of the CapsNet model was validated in classifying microseismic records.

Conclusions:

  • Capsule networks offer a highly effective solution for microseismic event classification, particularly in scenarios with limited available training data.
  • The developed method provides a reliable and accurate alternative to conventional techniques, enhancing microseismic data processing in mining environments.
  • This research highlights the potential of CapsNet for addressing data scarcity challenges in specialized scientific domains.