Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security

The advanced camera systems developed for property security prove inadequate when faced with the ease of disabling the cameras. Therefore, incorporating sound data from potential threats can also play a significant role in ensuring property security. This sound event-based approach enables a more co...

Full description

Saved in:
Bibliographic Details
Main Authors: Furkan Y. Yavuz, Nejat Yumusak
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10966859/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311308646711296
author Furkan Y. Yavuz
Nejat Yumusak
author_facet Furkan Y. Yavuz
Nejat Yumusak
author_sort Furkan Y. Yavuz
collection DOAJ
description The advanced camera systems developed for property security prove inadequate when faced with the ease of disabling the cameras. Therefore, incorporating sound data from potential threats can also play a significant role in ensuring property security. This sound event-based approach enables a more compact installation and allows for the use of affordable microphones, offering an alternative to visual-based security systems. We propose deep learning based on a convolutional neural network (CNN) algorithm for classification of footstep sound events. The study includes two consecutive stages: ReaLISED dataset and refined ReaLISED supported by Epidemic Sound data. Sound event files are transformed into Mel-Frequency Cepstral Coefficients (MFCC) and a CNN is fed with the represented images of MFCC. By optimizing the model parameters, our unique model detected footstep sound events with 98% accuracy among 17 other sound events. Validation through Repeated Stratified K-Fold Cross-Validation (5 folds, 10 repetitions) and comparisons with state-of-the-art architectures demonstrated robust performance, with F1-Scores ranging from 0.905 to 0.992 and a mean of 0.960. The strategic incorporation of diverse open-source data fosters transparency and reproducibility, enhancing the model’s adaptability and reliability in handling real-world audio patterns, as evidenced by its commendable 1% error rate in precise identification.
format Article
id doaj-art-74aadc0e9a854a8c8bd2dc6041edc86f
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-74aadc0e9a854a8c8bd2dc6041edc86f2025-08-20T03:53:27ZengIEEEIEEE Access2169-35362025-01-0113707607076810.1109/ACCESS.2025.356107610966859Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property SecurityFurkan Y. Yavuz0https://orcid.org/0009-0001-0399-9011Nejat Yumusak1https://orcid.org/0000-0001-5005-8604Department of Computer Engineering, Sakarya University, Serdivan, Sakarya, TürkiyeDepartment of Computer Engineering, Sakarya University, Serdivan, Sakarya, TürkiyeThe advanced camera systems developed for property security prove inadequate when faced with the ease of disabling the cameras. Therefore, incorporating sound data from potential threats can also play a significant role in ensuring property security. This sound event-based approach enables a more compact installation and allows for the use of affordable microphones, offering an alternative to visual-based security systems. We propose deep learning based on a convolutional neural network (CNN) algorithm for classification of footstep sound events. The study includes two consecutive stages: ReaLISED dataset and refined ReaLISED supported by Epidemic Sound data. Sound event files are transformed into Mel-Frequency Cepstral Coefficients (MFCC) and a CNN is fed with the represented images of MFCC. By optimizing the model parameters, our unique model detected footstep sound events with 98% accuracy among 17 other sound events. Validation through Repeated Stratified K-Fold Cross-Validation (5 folds, 10 repetitions) and comparisons with state-of-the-art architectures demonstrated robust performance, with F1-Scores ranging from 0.905 to 0.992 and a mean of 0.960. The strategic incorporation of diverse open-source data fosters transparency and reproducibility, enhancing the model’s adaptability and reliability in handling real-world audio patterns, as evidenced by its commendable 1% error rate in precise identification.https://ieeexplore.ieee.org/document/10966859/CNNfootstep acousticsMFCCproperty securitysound event detection
spellingShingle Furkan Y. Yavuz
Nejat Yumusak
Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
IEEE Access
CNN
footstep acoustics
MFCC
property security
sound event detection
title Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
title_full Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
title_fullStr Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
title_full_unstemmed Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
title_short Utilizing Footstep Sound Event Detection by Using CNN Techniques for Assuring Property Security
title_sort utilizing footstep sound event detection by using cnn techniques for assuring property security
topic CNN
footstep acoustics
MFCC
property security
sound event detection
url https://ieeexplore.ieee.org/document/10966859/
work_keys_str_mv AT furkanyyavuz utilizingfootstepsoundeventdetectionbyusingcnntechniquesforassuringpropertysecurity
AT nejatyumusak utilizingfootstepsoundeventdetectionbyusingcnntechniquesforassuringpropertysecurity