dc.contributor.author |
Nahar, Khalid M.O. |
|
dc.contributor.author |
Al-Omari, Fedaa |
|
dc.contributor.author |
Alhindawi, Nouh |
|
dc.contributor.author |
Banikhalaf, Mustafa |
|
dc.date.accessioned |
2022-02-12T01:20:43Z |
|
dc.date.available |
2022-02-12T01:20:43Z |
|
dc.date.issued |
2022-02-15 |
|
dc.identifier.issn |
2210-142X |
|
dc.identifier.uri |
https://journal.uob.edu.bh:443/handle/123456789/4588 |
|
dc.description.abstract |
Predicting enemy movements on the battlefield, especially when military raids occur is one of the important factors in battle winning. The enemies may be far away or hidden, but sounds are heard. Based on sounds that are outcomes from hidden enemies and by identifying the type of sound, a lot of information could be gained in further physical processing. The approximate location, distance, and the sound direction could be predicted. Moreover, establishing a sensitive model that relies on distinguishing military sounds will assist soldiers in alerting their military troops or camps for a near or faraway danger. Therefore, in this research, we build a Convolutional Neural Network (CNN) model for sound recognition in the battlefield. The mel frequency cepstral coefficients (MFCCs) features is used in this research to distinguish five types of sound; soldiers marching sound, plane sound, refiles sound, military vehicle sound, and missile launchers sound. The results showed that the CNN model accomplished the mission with an accuracy of 95.3% on testing data, while it showed 93.6% of accuracy on the outlet or unseen data. As a novel attempt and idea, the results were so promising. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
University Of Bahrain |
en_US |
dc.subject |
Convolutional Neural Network (CNN) |
en_US |
dc.subject |
Deep Learning |
en_US |
dc.subject |
Sounds Recognition |
en_US |
dc.subject |
MFCC |
en_US |
dc.subject |
Sound Classification |
en_US |
dc.subject |
Battlefield Sounds |
en_US |
dc.title |
Sounds Recognition in the Battlefield Using Convolutional Neural Network |
en_US |
dc.identifier.doi |
https://dx.doi.org/10.12785/ijcds/110196 |
|
dc.volume |
11 |
en_US |
dc.issue |
1 |
en_US |
dc.pagestart |
189 |
en_US |
dc.pageend |
198 |
en_US |
dc.contributor.authorcountry |
Jordan |
en_US |
dc.contributor.authoraffiliation |
Department of Computer Sciences, Yarmouk University |
en_US |
dc.contributor.authoraffiliation |
Directorate of Education of the District of Qasbah Irbid, Irbid Governorate |
en_US |
dc.contributor.authoraffiliation |
Department of Computer Science and Software Engineering, Faculty of Sciences and Information Technology, Jadara University |
en_US |
dc.source.title |
International Journal of Computing and Digital Systems |
en_US |
dc.abbreviatedsourcetitle |
IJCDS |
en_US |