A Deep Learning Approach for Distant Infrasound Signals Classification

Infrasound signal classification represents a critical challenge that demands immediate attention. Feature extraction stands as the core concept for enhancing classification accuracy in infrasound signal processing. However, existing feature extraction methodologies fail to meet the requirements for...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaofeng Tan, Xihai Li, Hongru Li, Xiaoniu Zeng, Tianyou Liu, Shengjie Luo
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/7/2058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769391826141184
author Xiaofeng Tan
Xihai Li
Hongru Li
Xiaoniu Zeng
Tianyou Liu
Shengjie Luo
author_facet Xiaofeng Tan
Xihai Li
Hongru Li
Xiaoniu Zeng
Tianyou Liu
Shengjie Luo
author_sort Xiaofeng Tan
collection DOAJ
description Infrasound signal classification represents a critical challenge that demands immediate attention. Feature extraction stands as the core concept for enhancing classification accuracy in infrasound signal processing. However, existing feature extraction methodologies fail to meet the requirements for long-distance detection scenarios. To address these limitations, this study proposes a novel classification framework based on the spatiotemporal characteristics of infrasound signals. The proposed framework incorporates advanced signal processing techniques, signal enhancement algorithms, and deep learning architectures to achieve precise classification of infrasound signals. This paper designs three sets of comparative experiments, and the results demonstrate that the proposed method achieves a classification accuracy rate of 83.9% on chemical explosion and seismic infrasound datasets, outperforming eight other comparative classification methods. This substantiates the efficacy of the proposed approach.
format Article
id doaj-art-c9ef84e7867c4c0b8a705f0900a7f7f0
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c9ef84e7867c4c0b8a705f0900a7f7f02025-08-20T03:03:25ZengMDPI AGSensors1424-82202025-03-01257205810.3390/s25072058A Deep Learning Approach for Distant Infrasound Signals ClassificationXiaofeng Tan0Xihai Li1Hongru Li2Xiaoniu Zeng3Tianyou Liu4Shengjie Luo5School of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaSchool of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaSchool of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaSchool of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaSchool of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaSchool of nuclear Engineering, Rocket Force University of Engneering, Xi’an 710025, ChinaInfrasound signal classification represents a critical challenge that demands immediate attention. Feature extraction stands as the core concept for enhancing classification accuracy in infrasound signal processing. However, existing feature extraction methodologies fail to meet the requirements for long-distance detection scenarios. To address these limitations, this study proposes a novel classification framework based on the spatiotemporal characteristics of infrasound signals. The proposed framework incorporates advanced signal processing techniques, signal enhancement algorithms, and deep learning architectures to achieve precise classification of infrasound signals. This paper designs three sets of comparative experiments, and the results demonstrate that the proposed method achieves a classification accuracy rate of 83.9% on chemical explosion and seismic infrasound datasets, outperforming eight other comparative classification methods. This substantiates the efficacy of the proposed approach.https://www.mdpi.com/1424-8220/25/7/2058infrasound signal classificationdeep learningnoise reductionstation signal combinationCNN
spellingShingle Xiaofeng Tan
Xihai Li
Hongru Li
Xiaoniu Zeng
Tianyou Liu
Shengjie Luo
A Deep Learning Approach for Distant Infrasound Signals Classification
Sensors
infrasound signal classification
deep learning
noise reduction
station signal combination
CNN
title A Deep Learning Approach for Distant Infrasound Signals Classification
title_full A Deep Learning Approach for Distant Infrasound Signals Classification
title_fullStr A Deep Learning Approach for Distant Infrasound Signals Classification
title_full_unstemmed A Deep Learning Approach for Distant Infrasound Signals Classification
title_short A Deep Learning Approach for Distant Infrasound Signals Classification
title_sort deep learning approach for distant infrasound signals classification
topic infrasound signal classification
deep learning
noise reduction
station signal combination
CNN
url https://www.mdpi.com/1424-8220/25/7/2058
work_keys_str_mv AT xiaofengtan adeeplearningapproachfordistantinfrasoundsignalsclassification
AT xihaili adeeplearningapproachfordistantinfrasoundsignalsclassification
AT hongruli adeeplearningapproachfordistantinfrasoundsignalsclassification
AT xiaoniuzeng adeeplearningapproachfordistantinfrasoundsignalsclassification
AT tianyouliu adeeplearningapproachfordistantinfrasoundsignalsclassification
AT shengjieluo adeeplearningapproachfordistantinfrasoundsignalsclassification
AT xiaofengtan deeplearningapproachfordistantinfrasoundsignalsclassification
AT xihaili deeplearningapproachfordistantinfrasoundsignalsclassification
AT hongruli deeplearningapproachfordistantinfrasoundsignalsclassification
AT xiaoniuzeng deeplearningapproachfordistantinfrasoundsignalsclassification
AT tianyouliu deeplearningapproachfordistantinfrasoundsignalsclassification
AT shengjieluo deeplearningapproachfordistantinfrasoundsignalsclassification