Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F21%3APU142097" target="_blank" >RIV/00216305:26220/21:PU142097 - isvavai.cz</a>

Výsledek na webu

<a href="https://eejournal.ktu.lt/index.php/elt/article/view/28877" target="_blank" >https://eejournal.ktu.lt/index.php/elt/article/view/28877</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5755/j02.eie.28877" target="_blank" >10.5755/j02.eie.28877</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

Popis výsledku v původním jazyce

This paper presents an efficient approach to automatic gunshot detection based on a combination of two feature sets: adapted standard sound features and hand-crafted novel features. The standard features are mel-frequency cepstral coefficients adapted for gunshot recognition in terms of uniform gamma-tone filters linearly spaced over the whole frequency range from 0 kHz to 16 kHz. The novel features were derived in the time domain from individual significant points of the raw waveform after amplitude normalization. Experiments were performed using single and ensemble neural networks to verify the effectiveness of the novel features for supplementing the standard features. In binary classification, the developed approach achieved an accuracy of 95.02 % in gunshot detection.

Název v anglickém jazyce

Efficient Feature Set Developed for Acoustic Gunshot Detection in Open Space

Popis výsledku anglicky

This paper presents an efficient approach to automatic gunshot detection based on a combination of two feature sets: adapted standard sound features and hand-crafted novel features. The standard features are mel-frequency cepstral coefficients adapted for gunshot recognition in terms of uniform gamma-tone filters linearly spaced over the whole frequency range from 0 kHz to 16 kHz. The novel features were derived in the time domain from individual significant points of the raw waveform after amplitude normalization. Experiments were performed using single and ensemble neural networks to verify the effectiveness of the novel features for supplementing the standard features. In binary classification, the developed approach achieved an accuracy of 95.02 % in gunshot detection.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Elektronika Ir Elektrotechnika

ISSN

1392-1215

e-ISSN

—

Svazek periodika

27

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

LT - Litevská republika

Počet stran výsledku

7

Strana od-do

62-68

Kód UT WoS článku

000689125400008

EID výsledku v databázi Scopus

2-s2.0-85113600635