Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition

Kohei Niwayama; Kenji Muto; Yosuke Kobayashi

doi:10.1109/GCCE56475.2022.10014118

Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition

Kohei Niwayama, Kenji Muto, Yosuke Kobayashi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We have been working on boat detection from environmental sound using a convolutional neural network (CNN). However, it had a problem with accuracy degrading when strong winds blew. In this study, we propose a method for boat detection using deep learning from environmental sound in strong wind conditions. Our proposal method was boat detection via convolutional recurrent neural network using the difference in duration between the boat and wind noise as a cue. The improvement of the proposed method was 0.03 points higher on the average of F-measure than the CNN.

Original language	English
Title of host publication	GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3-4
Number of pages	2
ISBN (Electronic)	9781665492324
DOIs	https://doi.org/10.1109/GCCE56475.2022.10014118
Publication status	Published - 2022
Event	11th IEEE Global Conference on Consumer Electronics, GCCE 2022 - Osaka, Japan Duration: 2022 Oct 18 → 2022 Oct 21

Publication series

Name	GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics

Conference

Conference	11th IEEE Global Conference on Consumer Electronics, GCCE 2022
Country/Territory	Japan
City	Osaka
Period	22/10/18 → 22/10/21

Keywords

boat noise
convolutional neural network
recurrent neural network
sound recognition
wind noise

ASJC Scopus subject areas

Signal Processing
Information Systems and Management
Electrical and Electronic Engineering
Media Technology
Instrumentation
Social Psychology

Access to Document

10.1109/GCCE56475.2022.10014118

Cite this

Niwayama, K., Muto, K., & Kobayashi, Y. (2022). Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition. In GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics (pp. 3-4). (GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE56475.2022.10014118

Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition. / Niwayama, Kohei; Muto, Kenji; Kobayashi, Yosuke.

GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc., 2022. p. 3-4 (GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Niwayama, K, Muto, K & Kobayashi, Y 2022, Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition. in GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics. GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics, Institute of Electrical and Electronics Engineers Inc., pp. 3-4, 11th IEEE Global Conference on Consumer Electronics, GCCE 2022, Osaka, Japan, 22/10/18. https://doi.org/10.1109/GCCE56475.2022.10014118

Niwayama K, Muto K, Kobayashi Y. Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition. In GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc. 2022. p. 3-4. (GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics). doi: 10.1109/GCCE56475.2022.10014118

@inproceedings{c9ae36248f6a469bb48e7960a91c7d48,

title = "Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition",

abstract = "We have been working on boat detection from environmental sound using a convolutional neural network (CNN). However, it had a problem with accuracy degrading when strong winds blew. In this study, we propose a method for boat detection using deep learning from environmental sound in strong wind conditions. Our proposal method was boat detection via convolutional recurrent neural network using the difference in duration between the boat and wind noise as a cue. The improvement of the proposed method was 0.03 points higher on the average of F-measure than the CNN.",

keywords = "boat noise, convolutional neural network, recurrent neural network, sound recognition, wind noise",

author = "Kohei Niwayama and Kenji Muto and Yosuke Kobayashi",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 11th IEEE Global Conference on Consumer Electronics, GCCE 2022 ; Conference date: 18-10-2022 Through 21-10-2022",

year = "2022",

doi = "10.1109/GCCE56475.2022.10014118",

language = "English",

series = "GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3--4",

booktitle = "GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics",

}

TY - GEN

T1 - Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition

AU - Niwayama, Kohei

AU - Muto, Kenji

AU - Kobayashi, Yosuke

PY - 2022

Y1 - 2022

N2 - We have been working on boat detection from environmental sound using a convolutional neural network (CNN). However, it had a problem with accuracy degrading when strong winds blew. In this study, we propose a method for boat detection using deep learning from environmental sound in strong wind conditions. Our proposal method was boat detection via convolutional recurrent neural network using the difference in duration between the boat and wind noise as a cue. The improvement of the proposed method was 0.03 points higher on the average of F-measure than the CNN.

AB - We have been working on boat detection from environmental sound using a convolutional neural network (CNN). However, it had a problem with accuracy degrading when strong winds blew. In this study, we propose a method for boat detection using deep learning from environmental sound in strong wind conditions. Our proposal method was boat detection via convolutional recurrent neural network using the difference in duration between the boat and wind noise as a cue. The improvement of the proposed method was 0.03 points higher on the average of F-measure than the CNN.

KW - boat noise

KW - convolutional neural network

KW - recurrent neural network

KW - sound recognition

KW - wind noise

UR - http://www.scopus.com/inward/record.url?scp=85147248574&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147248574&partnerID=8YFLogxK

U2 - 10.1109/GCCE56475.2022.10014118

DO - 10.1109/GCCE56475.2022.10014118

M3 - Conference contribution

AN - SCOPUS:85147248574

T3 - GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics

SP - 3

EP - 4

BT - GCCE 2022 - 2022 IEEE 11th Global Conference on Consumer Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IEEE Global Conference on Consumer Electronics, GCCE 2022

Y2 - 18 October 2022 through 21 October 2022

ER -

Convolutional Recurrent Neural Network-Based Boat Detection Method for Wind Noise Condition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this