CNN-based detection of red palm weevil using optical-fiber-distributed acoustic sensing

Islam Ashry; Yuan Mao; Biwei Wang; Mohammed Sait; Yujian Guo; Abdulmoneim Al-Shawaf; Tien Khee Ng; Boon S. Ooi

doi:10.1117/12.2609308

CNN-based detection of red palm weevil using optical-fiber-distributed acoustic sensing

Islam Ashry, Yuan Mao, Biwei Wang, Mohammed Sait, Yujian Guo, Abdulmoneim Al-Shawaf, Tien Khee Ng, Boon S. Ooi

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

3 Scopus citations

Abstract

Red palm weevil (RPW) is a harmful pest that has wiped out many palm plantations worldwide. Early detection of RPW is difficult, especially on large plantations. Here, we report on combining fiber–optic distributed acoustic sensing (DAS) and machine learning to detect weevil larvae less than three weeks old, in a controlled environment. In particular, we use the temporal and spectral data provided by a fiber–optic DAS system to train a convolutional neural network (CNN), which distinguishes “healthy” and “infested” signals with a classification accuracy higher than 97%. Additionally, a rigorous machine learning classification approach is introduced to improve the false alarm performance metric by >20%.

Original language	English (US)
Title of host publication	Photonic Instrumentation Engineering IX
Publisher	SPIE
DOIs	https://doi.org/10.1117/12.2609308
State	Published - Mar 5 2022

Bibliographical note

KAUST Repository Item: Exported on 2022-03-09
Acknowledged KAUST grant number(s): REI/1/4247-01-01
Acknowledgements: The authors gratefully acknowledge the financial support provided to this work by KAUST–Research Translation
Funding (REI/1/4247-01-01).

Access to Document

10.1117/12.2609308

Cite this

@inproceedings{3d557a52cc5a41f6a25ff7724e38b161,

title = "CNN-based detection of red palm weevil using optical-fiber-distributed acoustic sensing",

abstract = "Red palm weevil (RPW) is a harmful pest that has wiped out many palm plantations worldwide. Early detection of RPW is difficult, especially on large plantations. Here, we report on combining fiber–optic distributed acoustic sensing (DAS) and machine learning to detect weevil larvae less than three weeks old, in a controlled environment. In particular, we use the temporal and spectral data provided by a fiber–optic DAS system to train a convolutional neural network (CNN), which distinguishes “healthy” and “infested” signals with a classification accuracy higher than 97%. Additionally, a rigorous machine learning classification approach is introduced to improve the false alarm performance metric by >20%.",

author = "Islam Ashry and Yuan Mao and Biwei Wang and Mohammed Sait and Yujian Guo and Abdulmoneim Al-Shawaf and Ng, {Tien Khee} and Ooi, {Boon S.}",

note = "KAUST Repository Item: Exported on 2022-03-09 Acknowledged KAUST grant number(s): REI/1/4247-01-01 Acknowledgements: The authors gratefully acknowledge the financial support provided to this work by KAUST–Research Translation Funding (REI/1/4247-01-01).",

year = "2022",

month = mar,

day = "5",

doi = "10.1117/12.2609308",

language = "English (US)",

booktitle = "Photonic Instrumentation Engineering IX",

publisher = "SPIE",

}

TY - GEN

T1 - CNN-based detection of red palm weevil using optical-fiber-distributed acoustic sensing

AU - Ashry, Islam

AU - Mao, Yuan

AU - Wang, Biwei

AU - Sait, Mohammed

AU - Guo, Yujian

AU - Al-Shawaf, Abdulmoneim

AU - Ng, Tien Khee

AU - Ooi, Boon S.

N1 - KAUST Repository Item: Exported on 2022-03-09 Acknowledged KAUST grant number(s): REI/1/4247-01-01 Acknowledgements: The authors gratefully acknowledge the financial support provided to this work by KAUST–Research Translation Funding (REI/1/4247-01-01).

PY - 2022/3/5

Y1 - 2022/3/5

N2 - Red palm weevil (RPW) is a harmful pest that has wiped out many palm plantations worldwide. Early detection of RPW is difficult, especially on large plantations. Here, we report on combining fiber–optic distributed acoustic sensing (DAS) and machine learning to detect weevil larvae less than three weeks old, in a controlled environment. In particular, we use the temporal and spectral data provided by a fiber–optic DAS system to train a convolutional neural network (CNN), which distinguishes “healthy” and “infested” signals with a classification accuracy higher than 97%. Additionally, a rigorous machine learning classification approach is introduced to improve the false alarm performance metric by >20%.

AB - Red palm weevil (RPW) is a harmful pest that has wiped out many palm plantations worldwide. Early detection of RPW is difficult, especially on large plantations. Here, we report on combining fiber–optic distributed acoustic sensing (DAS) and machine learning to detect weevil larvae less than three weeks old, in a controlled environment. In particular, we use the temporal and spectral data provided by a fiber–optic DAS system to train a convolutional neural network (CNN), which distinguishes “healthy” and “infested” signals with a classification accuracy higher than 97%. Additionally, a rigorous machine learning classification approach is introduced to improve the false alarm performance metric by >20%.

UR - http://hdl.handle.net/10754/675749

UR - https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12008/2609308/CNN-based-detection-of-red-palm-weevil-using-optical-fiber/10.1117/12.2609308.full

U2 - 10.1117/12.2609308

DO - 10.1117/12.2609308

M3 - Conference contribution

BT - Photonic Instrumentation Engineering IX

PB - SPIE

ER -

CNN-based detection of red palm weevil using optical-fiber-distributed acoustic sensing

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this