An Initial Machine Learning-Based Victim’s Scream Detection Analysis for Burning Sites

dc.contributor.authorSaeed, Fairuz Samiha
dc.contributor.authorBashit, Abdullah Al
dc.contributor.authorViswanathan, Vishu
dc.contributor.authorValles, Damian
dc.date.accessioned2022-11-16T21:22:23Z
dc.date.available2022-11-16T21:22:23Z
dc.date.issued2021-09-10
dc.description.abstractFire incidents are responsible for severe damage and thousands of deaths every year all over the world. Extreme temperatures, low visibility, toxic gases, and unknown locations of victims create difficulties and delays in rescue operations, escalating the risk of injury or death. It is time-critical to detect the victims trapped inside the burning sites for facilitating the rescue operations. This research work presents an audio-based automated system for victim detection in fire emergencies, investigating two machine learning (ML) methods: support vector machines (SVM) and long short-term memory (LSTM). The performance of these two ML techniques has been evaluated based on a variety of performance metrics. Our analyses show that both ML methods provide superior scream detection performance, with SVM slightly overperforming LSTM. Because of its lower complexity, SVM is a better candidate for real-time implementation in our autonomous embedded system vehicle (AESV).
dc.description.departmentEngineering
dc.formatText
dc.format.extent22 pages
dc.format.medium1 file (.pdf)
dc.identifier.citationSaeed, F. S., Bashit, A. A., Viswanathan, V., & Valles, D. (2021). An initial machine learning-based victim’s scream detection analysis for burning sites. Applied Sciences, 11(18), 8425.
dc.identifier.doihttps://doi.org/10.3390/app11188425
dc.identifier.issn2076-3417
dc.identifier.urihttps://hdl.handle.net/10877/16311
dc.language.isoen
dc.publisherMultidisciplinary Digital Publishing Institute
dc.rights.licenseThis work is licensed under a Creative Commons Attribution 4.0 International License.
dc.sourceApplied Sciences, 2021, Vol. 11, No. 18, Article 8425, pp. 1-22.
dc.subjectscream
dc.subjectfire
dc.subjecttrapped victims
dc.subjectSVM
dc.subjectLSTM
dc.subjectAESV
dc.subjectfeatures
dc.subjectmachine learning
dc.subjectIngram School of Engineering
dc.titleAn Initial Machine Learning-Based Victim’s Scream Detection Analysis for Burning Sites
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
applsci-11-08425.pdf
Size:
5.32 MB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.54 KB
Format:
Item-specific license agreed upon to submission
Description: