TBU Publications
Repository of TBU Publications

Classification of audio sources using neural network applicable in security or military industry

DSpace Repository

Show simple item record


dc.title Classification of audio sources using neural network applicable in security or military industry en
dc.contributor.author Navrátil, Milan
dc.contributor.author Dostálek, Petr
dc.contributor.author Křesálek, Vojtěch
dc.relation.ispartof 44th Annual 2010 IEEE International Carnahan Conference on Security Technology
dc.identifier.issn 1071-6572 OCLC, Ulrich, Sherpa/RoMEO, JCR
dc.identifier.isbn 978-1-4244-7400-4
dc.date.issued 2010
dc.citation.spage 369
dc.citation.epage 374
dc.event.title 44th Annual 2010 IEEE International Carnahan Conference on Security Technology
dc.event.location San Jose
utb.event.state-en United States
utb.event.state-cs Spojené státy americké
dc.event.sdate 2010-10-05
dc.event.edate 2010-10-08
dc.type conferenceObject
dc.language.iso en
dc.publisher The Institute of Electrical and Electronics Engineers (IEEE) en
dc.identifier.doi 10.1109/CCST.2010.5678725
dc.relation.uri http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5678725&tag=1
dc.subject classification en
dc.subject audio en
dc.subject neural network en
dc.subject Fourier transform en
dc.subject spectrum en
dc.subject analysis en
dc.description.abstract In this paper, classification of audio sources is presented to supplement current work on existing system for localization of audio sources. The question of achieving the audio classification lies in the convenient discrimination of the feature vector in the feature vector space. Characteristics based on frequency analysis were chosen and used as feature vector. Artificial neural network was applied in order to classify different audio classes especially from security and military areas, such as different shots and explosions. The information about specific type of a sound can trigger localization process of given audio source. Moreover, it can improve situation when guards get ready for the alert state. This classification method is currently developed as an additional part of the system for audio source hyperbolic localization; the paper also gives some basic structure of that system. Its utilization can be found for additional securing of larger objects like squares or military basis, for instance. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1001756
utb.identifier.rivid RIV/70883521:28140/10:63508954!RIV11-MSM-28140___
utb.identifier.obdid 43863746
utb.identifier.scopus 2-s2.0-78751695194
utb.identifier.wok 000287496000053
utb.source d-wok
dc.date.accessioned 2011-08-09T07:33:50Z
dc.date.available 2011-08-09T07:33:50Z
utb.contributor.internalauthor Navrátil, Milan
utb.contributor.internalauthor Dostálek, Petr
utb.contributor.internalauthor Křesálek, Vojtěch
Find Full text

Files in this item

Show simple item record