The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of MATHEMATICAL MODELS AND METHODS IN APPLIED SCIENCES
Transactions ID Number: 17-108
Full Name: Milan Navratil
Position: Doctor (Researcher)
Age: ON
Sex: Male
Address: Nad Stranemi 4511, Zlin, 76005
Country: CZECH REPUBLIC
Tel:
Tel prefix:
Fax:
E-mail address: navratil@fai.utb.cz
Other E-mails:
Title of the Paper: Neural network classification of gunshots using spectral characteristics
Authors as they appear in the Paper: Milan Navrátil, Vojtìch Køesálek, PetrDostálek
Email addresses of all the authors: navratil@fai.utb.cz, kresalek@fai.utb.cz, dostalek@fai.utb.cz
Number of paper pages: 8
Abstract: The paper describes neural network classification of specific audio sources into given categories. Audio sources are represented by various gunshots, from handguns or big bore guns. This article is a follow-up to an existing system for localization of audio sources from security and military areas. The question of successful classification lies in the convenient discrimination of the feature vector in the feature vector space. A set of feature vectors based on power spectral density is evaluated a tested for the best classification of gunshots.
Keywords: Neural network, classification, gunshots, spectral analysis, feature vector.
EXTENSION of the file: .pdf
Special (Invited) Session: Neural network classification of gunshots using spectral characteristics
Organizer of the Session: 655-241
How Did you learn about congress:
IP ADDRESS: 195.178.89.154
