Hybrid neural network based on novel audio feature for vehicle type identification

Abstract Due to the audio information of different types of vehicle models are distinct, the vehicle information can be identified by the audio signal of vehicle accurately. In real life, in order to determine the type of vehicle, we do not need to obtain the visual information of vehicles and just...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haoze Chen, Zhijie Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/618e05b13e3d44bb87c593ae8c7d004a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:618e05b13e3d44bb87c593ae8c7d004a
record_format	dspace
spelling	oai:doaj.org-article:618e05b13e3d44bb87c593ae8c7d004a2021-12-02T18:15:33ZHybrid neural network based on novel audio feature for vehicle type identification10.1038/s41598-021-87399-12045-2322https://doaj.org/article/618e05b13e3d44bb87c593ae8c7d004a2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87399-1https://doaj.org/toc/2045-2322Abstract Due to the audio information of different types of vehicle models are distinct, the vehicle information can be identified by the audio signal of vehicle accurately. In real life, in order to determine the type of vehicle, we do not need to obtain the visual information of vehicles and just need to obtain the audio information. In this paper, we extract and stitching different features from different aspects: Mel frequency cepstrum coefficients in perceptual characteristics, pitch class profile in psychoacoustic characteristics and short-term energy in acoustic characteristics. In addition, we improve the neural networks classifier by fusing the LSTM unit into the convolutional neural networks. At last, we put the novel feature to the hybrid neural networks to recognize different vehicles. The results suggest the novel feature we proposed in this paper can increase the recognition rate by 7%; destroying the training data randomly by superimposing different kinds of noise can improve the anti-noise ability in our identification system; and LSTM has great advantages in modeling time series, adding LSTM to the networks can improve the recognition rate of 3.39%.Haoze ChenZhijie ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Haoze Chen Zhijie Zhang Hybrid neural network based on novel audio feature for vehicle type identification
description	Abstract Due to the audio information of different types of vehicle models are distinct, the vehicle information can be identified by the audio signal of vehicle accurately. In real life, in order to determine the type of vehicle, we do not need to obtain the visual information of vehicles and just need to obtain the audio information. In this paper, we extract and stitching different features from different aspects: Mel frequency cepstrum coefficients in perceptual characteristics, pitch class profile in psychoacoustic characteristics and short-term energy in acoustic characteristics. In addition, we improve the neural networks classifier by fusing the LSTM unit into the convolutional neural networks. At last, we put the novel feature to the hybrid neural networks to recognize different vehicles. The results suggest the novel feature we proposed in this paper can increase the recognition rate by 7%; destroying the training data randomly by superimposing different kinds of noise can improve the anti-noise ability in our identification system; and LSTM has great advantages in modeling time series, adding LSTM to the networks can improve the recognition rate of 3.39%.
format	article
author	Haoze Chen Zhijie Zhang
author_facet	Haoze Chen Zhijie Zhang
author_sort	Haoze Chen
title	Hybrid neural network based on novel audio feature for vehicle type identification
title_short	Hybrid neural network based on novel audio feature for vehicle type identification
title_full	Hybrid neural network based on novel audio feature for vehicle type identification
title_fullStr	Hybrid neural network based on novel audio feature for vehicle type identification
title_full_unstemmed	Hybrid neural network based on novel audio feature for vehicle type identification
title_sort	hybrid neural network based on novel audio feature for vehicle type identification
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/618e05b13e3d44bb87c593ae8c7d004a
work_keys_str_mv	AT haozechen hybridneuralnetworkbasedonnovelaudiofeatureforvehicletypeidentification AT zhijiezhang hybridneuralnetworkbasedonnovelaudiofeatureforvehicletypeidentification
_version_	1718378334736351232

Hybrid neural network based on novel audio feature for vehicle type identification

Ejemplares similares