Multi-label UAV sound classification using Stacked Bidirectional LSTM

Dana Utebayeva, Akhan Almagambetov, Manal Alduraibi, Yelmurat Temirgaliyev, Lyazzat Ilipbayeva, Sunggat Marxuly

2020

Closed access Metadata (CSL-JSON)
DOI 10.1109/irc.2020.00086
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Nowadays Unmanned Aerial Vehicles (UAVs) pose an increasing threat to public areas such as parks, schools, hospitals and official buildings. Different methods of dealing with UAV detection are developing more and more actively. This paper primarily focuses on two key aims: the first aim is to perform a multi-label classification system and the second aim is to develop Stacked Bidirectional Long Short-Term Memory (LSTM) with two hidden layers to categorize multiple UAVs sounds. Frame-wise spectral-domain features are applied as inputs of the proposed system. Overall, the results of the study show that the sound of UAVs can be classified into multiple labels. This study has been one of the first attempts to thoroughly examine Stacked Bidirectional LSTM for UAV sound classification task.