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

Stable and tunable MeV γ-ray generation via dual-laser inverse Thomson scattering from a laser-plasma accelerator.

Scientific reports·2026
Same author

Evaluation of the Radioactive Material Released in the Harborview Research and Training Building and Some Implications for Emergency Response.

Health physics·2025
Same author

A comparison of smartphone and infrasound microphone data from a fuel air explosive and a high explosive.

The Journal of the Acoustical Society of America·2024
Same author

Passive high explosive neutron inspection (PHENIX): a new method to confirm the presence or absence of high explosives for nuclear treaty verification.

Scientific reports·2024
Same author

Laser-Induced Fluorescence for Monitoring Environmental Contamination and Stress in the Moss <i>Thuidium plicatile</i>.

Plants (Basel, Switzerland)·2023
Same author

A prognostic risk score for development and spread of chronic pain.

Nature medicine·2023

Related Experiment Video

Updated: Jun 9, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K

Explosion Detection Using Smartphones: Ensemble Learning with the Smartphone High-Explosive Audio Recordings Dataset

Samuel K Takazawa1, Sarah K Popenhagen1, Luis A Ocampo Giraldo2

  • 1Infrasound Laboratory, Hawai'i Institute of Geophysics and Planetology, School of Ocean and Earth Science and Technology, University of Hawai'i at Mānoa, Kailua-Kona, HI 96740, USA.

Sensors (Basel, Switzerland)
|October 26, 2024
PubMed
Summary

This study proposes using smartphone microphones for cost-effective explosion detection. An ensemble machine learning model achieved over 96% accuracy in classifying explosions, ambient sounds, and other audio signals.

Keywords:
datadetectionexplosioninfrasoundmachine learningsmartphone

More Related Videos

Real-time Tracking of DNA Fragment Separation by Smartphone
06:58

Real-time Tracking of DNA Fragment Separation by Smartphone

Published on: June 1, 2017

14.5K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

680

Related Experiment Videos

Last Updated: Jun 9, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Real-time Tracking of DNA Fragment Separation by Smartphone
06:58

Real-time Tracking of DNA Fragment Separation by Smartphone

Published on: June 1, 2017

14.5K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

680

Area of Science:

  • Geophysics
  • Acoustics
  • Machine Learning

Background:

  • Global explosion monitoring relies on infrasound and seismoacoustic networks, which are sparsely distributed and costly to maintain.
  • Increasing interest in detecting smaller explosions necessitates denser sensor networks, particularly at local scales.

Purpose of the Study:

  • To investigate the feasibility of using smartphone sensors for cost-effective and accessible explosion detection.
  • To develop and evaluate a machine learning model for classifying explosion events using smartphone audio data.

Main Methods:

  • Utilized the Smartphone High-explosive Audio Recordings Dataset (SHAReD) and the ESC-50 dataset for training.
  • Developed and combined two machine learning models into an ensemble model for audio signal classification.
  • Classified audio signals into 'explosion', 'ambient', or 'other' categories.

Main Results:

  • The ensemble machine learning model demonstrated high performance in explosion detection.
  • Achieved true positive rates (recall) exceeding 96% for all three classification categories: explosion, ambient, and other.
  • Validated the effectiveness of smartphone microphones as a viable sensor for explosion monitoring.

Conclusions:

  • Smartphone sensors offer a promising, cost-effective solution for enhancing explosion detection capabilities.
  • The developed ensemble model shows significant potential for real-world application in explosion monitoring networks.
  • Further technological development in this nascent field can improve the density and effectiveness of explosion detection systems.