A Feature-Reduction Scheme Based on a Two-Sample t-Test to Eliminate Useless Spectrogram Frequency Bands in Acoustic Event Detection Systems

Acoustic event detection (AED) systems, combined with video surveillance systems, can enhance urban security and safety by automatically detecting incidents, supporting the smart city concept. AED systems mostly use mel spectrograms as a well-known effective acoustic feature. The spectrogram is a co...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Electronics (Basel) 2024-06, Vol.13 (11), p.2064
Hauptverfasser:	Hajihashemi, Vahid, Gharahbagh, Abdorreza Alavi, Hajaboutalebi, Narges, Zahraei, Mohsen, Machado, José J. M., Tavares, João Manuel R. S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Acoustic properties Acoustics Algorithms Band spectra Birds Classification Convulsions & seizures Datasets Detectors Earthquakes Fourier transforms Frequencies Gravitational waves Identification methods Machine learning Methods Neural networks Smart cities Sound Spectrograms Surveillance systems System effectiveness Urban areas Wavelet transforms
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!