Integration of 5.8GHz Doppler Radar and Machine Learning for Automated Honeybee Hive Surveillance and Logging

Nawaf Aldabashi; Sam Williams; Amira Eltokhy; Edward  Palmer; Paul Cross; Cristiano Palego

doi:10.1109/IMS19712.2021.9574826

Integration of 5.8GHz Doppler Radar and Machine Learning for Automated Honeybee Hive Surveillance and Logging

Nawaf Aldabashi
, Sam Williams
, Amira Eltokhy
, Edward Palmer
, Paul Cross
, Cristiano Palego

MSA University, Cairo
S&A Produce, Ltd.

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion Cynhadledd › Cyfraniad i Gynhadledd › adolygiad gan gymheiriaid

Crynodeb

A 5.8GHz Doppler radar was used to monitor free flying honeybees entering and leaving their hive at a 2m distance. Free falling metal spheres of different size and materials were first used, along with radar cross section (RCS) simulations, for calibration of an in house continuous-wave (CW) radar system. The system was then applied to extract the RCS of free flying honeybees (n=164) at 5.8GHz, which fills a gap in the literature and was found to be in the range of −55 to −60dBsm ± 3dBsm. The Doppler radar was hence integrated with machine learning (ML) techniques to autonomously discriminate the incoming and outgoing flights of honeybees. A neural network built through a random forest algorithm and processing of the data as Line Spectral Pairs (LSPs) achieved a maximum accuracy of 87.83% with a Binary Cross Entropy loss of 0.4274 when interpreting hive departure/entrance events.

Iaith wreiddiol	Saesneg
Teitl	2021 IEEE MTT-S International Microwave Symposium (IMS)
Cyhoeddwr	IEEE
Dynodwyr Gwrthrych Digidol (DOIs)	https://doi.org/10.1109/IMS19712.2021.9574826
Statws	Cyhoeddwyd - 27 Hyd 2021

Mynediad at Ddogfen

10.1109/IMS19712.2021.9574826

Dyfynnu hyn

@inproceedings{3cd0bb1aab354a5d9568ea6203bbfd89,

title = "Integration of 5.8GHz Doppler Radar and Machine Learning for Automated Honeybee Hive Surveillance and Logging",

abstract = "A 5.8GHz Doppler radar was used to monitor free flying honeybees entering and leaving their hive at a 2m distance. Free falling metal spheres of different size and materials were first used, along with radar cross section (RCS) simulations, for calibration of an in house continuous-wave (CW) radar system. The system was then applied to extract the RCS of free flying honeybees (n=164) at 5.8GHz, which fills a gap in the literature and was found to be in the range of −55 to −60dBsm ± 3dBsm. The Doppler radar was hence integrated with machine learning (ML) techniques to autonomously discriminate the incoming and outgoing flights of honeybees. A neural network built through a random forest algorithm and processing of the data as Line Spectral Pairs (LSPs) achieved a maximum accuracy of 87.83\% with a Binary Cross Entropy loss of 0.4274 when interpreting hive departure/entrance events.",

author = "Nawaf Aldabashi and Sam Williams and Amira Eltokhy and Edward Palmer and Paul Cross and Cristiano Palego",

year = "2021",

month = oct,

day = "27",

doi = "10.1109/IMS19712.2021.9574826",

language = "English",

booktitle = "2021 IEEE MTT-S International Microwave Symposium (IMS)",

publisher = "IEEE",

}

TY - GEN

T1 - Integration of 5.8GHz Doppler Radar and Machine Learning for Automated Honeybee Hive Surveillance and Logging

AU - Aldabashi, Nawaf

AU - Williams, Sam

AU - Eltokhy, Amira

AU - Palmer, Edward

AU - Cross, Paul

AU - Palego, Cristiano

PY - 2021/10/27

Y1 - 2021/10/27

N2 - A 5.8GHz Doppler radar was used to monitor free flying honeybees entering and leaving their hive at a 2m distance. Free falling metal spheres of different size and materials were first used, along with radar cross section (RCS) simulations, for calibration of an in house continuous-wave (CW) radar system. The system was then applied to extract the RCS of free flying honeybees (n=164) at 5.8GHz, which fills a gap in the literature and was found to be in the range of −55 to −60dBsm ± 3dBsm. The Doppler radar was hence integrated with machine learning (ML) techniques to autonomously discriminate the incoming and outgoing flights of honeybees. A neural network built through a random forest algorithm and processing of the data as Line Spectral Pairs (LSPs) achieved a maximum accuracy of 87.83% with a Binary Cross Entropy loss of 0.4274 when interpreting hive departure/entrance events.

AB - A 5.8GHz Doppler radar was used to monitor free flying honeybees entering and leaving their hive at a 2m distance. Free falling metal spheres of different size and materials were first used, along with radar cross section (RCS) simulations, for calibration of an in house continuous-wave (CW) radar system. The system was then applied to extract the RCS of free flying honeybees (n=164) at 5.8GHz, which fills a gap in the literature and was found to be in the range of −55 to −60dBsm ± 3dBsm. The Doppler radar was hence integrated with machine learning (ML) techniques to autonomously discriminate the incoming and outgoing flights of honeybees. A neural network built through a random forest algorithm and processing of the data as Line Spectral Pairs (LSPs) achieved a maximum accuracy of 87.83% with a Binary Cross Entropy loss of 0.4274 when interpreting hive departure/entrance events.

U2 - 10.1109/IMS19712.2021.9574826

DO - 10.1109/IMS19712.2021.9574826

M3 - Conference contribution

BT - 2021 IEEE MTT-S International Microwave Symposium (IMS)

PB - IEEE

ER -

Integration of 5.8GHz Doppler Radar and Machine Learning for Automated Honeybee Hive Surveillance and Logging

Crynodeb

Mynediad at Ddogfen

Ôl bys

Dyfynnu hyn