A Machine Learning Integrated 5.8-GHz Continuous-Wave Radar for Honeybee Monitoring and Behavior Classification

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

doi:10.1109/TMTT.2023.3248785

A Machine Learning Integrated 5.8-GHz Continuous-Wave Radar for Honeybee Monitoring and Behavior Classification

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

S&A Produce, Ltd.

Research output: Contribution to journal › Article › peer-review

Abstract

A 5.8-GHz continuous-wave (CW) radar was devel- oped and integrated on a compact printed circuit board (PCB) for near-hive monitoring of honeybees. It supported noninvasive detection of free-flying honeybees at 2 m and micro-Doppler extraction of bee wingbeat signatures at a closer range using both a double-balanced mixer and an in-phase/quadrature (IQ) mixer. An original technique combining full-wave simulations and Doppler-radar monitoring of pendulum motion was used for: radar calibration through spherical targets of different material and size; precise extraction of bee radar cross section (RCS) at 5.8 GHz; and estimation of detection range enhancement through partial silver coating of targets. Finally, the CW radar was integrated with machine learning (ML) to allow automated classification of incoming, outgoing, and hovering honeybees. Different ML approaches were tested, where the highest accuracy of 93.37% was found in ternary classification via support vector machine acting on line spectral frequencies.

Original language	English
Pages (from-to)	4098-4108
Number of pages	11
Journal	IEEE Transactions on Microwave Theory and Techniques
Volume	71
Issue number	9
Early online date	6 Mar 2023
DOIs	https://doi.org/10.1109/TMTT.2023.3248785
Publication status	Published - Sept 2023

Keywords

Continuous-wave (CW) radar, Doppler radar, machine learning (ML), micro-Doppler.

Access to Document

10.1109/TMTT.2023.3248785

BU-IIA Funded Project: Automated flying insect tracking for pollination services protection and optimization
Palego, C. (Contributor), Cross, P. (Contributor) & Aldabashi, N. (Contributor)
1 Apr 2022 → 31 Mar 2023
Activity: Other

Cite this

@article{bd3100015dfc4e5fb86dd87e76594e96,

title = "A Machine Learning Integrated 5.8-GHz Continuous-Wave Radar for Honeybee Monitoring and Behavior Classification",

abstract = "A 5.8-GHz continuous-wave (CW) radar was devel- oped and integrated on a compact printed circuit board (PCB) for near-hive monitoring of honeybees. It supported noninvasive detection of free-flying honeybees at 2 m and micro-Doppler extraction of bee wingbeat signatures at a closer range using both a double-balanced mixer and an in-phase/quadrature (IQ) mixer. An original technique combining full-wave simulations and Doppler-radar monitoring of pendulum motion was used for: radar calibration through spherical targets of different material and size; precise extraction of bee radar cross section (RCS) at 5.8 GHz; and estimation of detection range enhancement through partial silver coating of targets. Finally, the CW radar was integrated with machine learning (ML) to allow automated classification of incoming, outgoing, and hovering honeybees. Different ML approaches were tested, where the highest accuracy of 93.37\% was found in ternary classification via support vector machine acting on line spectral frequencies.",

keywords = "Continuous-wave (CW) radar, Doppler radar, machine learning (ML), micro-Doppler.",

author = "Nawaf Aldabashi and \{Morton Williams\}, Samuel and Amira Eltokhy and Edward Palmer and Paul Cross and Cristiano Palego",

year = "2023",

month = sep,

doi = "10.1109/TMTT.2023.3248785",

language = "English",

volume = "71",

pages = "4098--4108",

journal = "IEEE Transactions on Microwave Theory and Techniques",

issn = "0018-9480",

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

number = "9",

}

TY - JOUR

T1 - A Machine Learning Integrated 5.8-GHz Continuous-Wave Radar for Honeybee Monitoring and Behavior Classification

AU - Aldabashi, Nawaf

AU - Morton Williams, Samuel

AU - Eltokhy, Amira

AU - Palmer, Edward

AU - Cross, Paul

AU - Palego, Cristiano

PY - 2023/9

Y1 - 2023/9

N2 - A 5.8-GHz continuous-wave (CW) radar was devel- oped and integrated on a compact printed circuit board (PCB) for near-hive monitoring of honeybees. It supported noninvasive detection of free-flying honeybees at 2 m and micro-Doppler extraction of bee wingbeat signatures at a closer range using both a double-balanced mixer and an in-phase/quadrature (IQ) mixer. An original technique combining full-wave simulations and Doppler-radar monitoring of pendulum motion was used for: radar calibration through spherical targets of different material and size; precise extraction of bee radar cross section (RCS) at 5.8 GHz; and estimation of detection range enhancement through partial silver coating of targets. Finally, the CW radar was integrated with machine learning (ML) to allow automated classification of incoming, outgoing, and hovering honeybees. Different ML approaches were tested, where the highest accuracy of 93.37% was found in ternary classification via support vector machine acting on line spectral frequencies.

AB - A 5.8-GHz continuous-wave (CW) radar was devel- oped and integrated on a compact printed circuit board (PCB) for near-hive monitoring of honeybees. It supported noninvasive detection of free-flying honeybees at 2 m and micro-Doppler extraction of bee wingbeat signatures at a closer range using both a double-balanced mixer and an in-phase/quadrature (IQ) mixer. An original technique combining full-wave simulations and Doppler-radar monitoring of pendulum motion was used for: radar calibration through spherical targets of different material and size; precise extraction of bee radar cross section (RCS) at 5.8 GHz; and estimation of detection range enhancement through partial silver coating of targets. Finally, the CW radar was integrated with machine learning (ML) to allow automated classification of incoming, outgoing, and hovering honeybees. Different ML approaches were tested, where the highest accuracy of 93.37% was found in ternary classification via support vector machine acting on line spectral frequencies.

KW - Continuous-wave (CW) radar, Doppler radar, machine learning (ML), micro-Doppler.

U2 - 10.1109/TMTT.2023.3248785

DO - 10.1109/TMTT.2023.3248785

M3 - Article

SN - 0018-9480

VL - 71

SP - 4098

EP - 4108

JO - IEEE Transactions on Microwave Theory and Techniques

JF - IEEE Transactions on Microwave Theory and Techniques

IS - 9

ER -

A Machine Learning Integrated 5.8-GHz Continuous-Wave Radar for Honeybee Monitoring and Behavior Classification

Abstract

Keywords

Access to Document

Fingerprint

Activities

BU-IIA Funded Project: Automated flying insect tracking for pollination services protection and optimization

Cite this