Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

Stenford Ruvinga; Gordon J.A. Hunter; Olga Duran; Jean-Christophe Nebel

doi:10.1109/IE51775.2021.9486575

Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

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

15 Downloads (Pure)

Abstract

Honeybees are of vital importance to both agriculture and ecology, but honeybee populations have been in serious decline over recent years. The queen bee is of crucial importance to the success of a colony. In this paper, we make a contribution to addressing these problems by employing LSTM, Multi-Layer Perceptron Neural Networks and Logistic Regression approaches applied to audio data recorded from ‟queen-less” and ‟queen-right” hives to provide a method of prompt detection of a hive lacking a healthy queen. The initial results - particularly from the LSTM - are highly encouraging.

Original language	English
Title of host publication	Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai
DOIs	https://doi.org/10.1109/IE51775.2021.9486575
Publication status	Published - 2021

Bibliographical note

Note: Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792.

Organising Body: Middlesex University Dubai

Organising Body: Middlesex University Dubai

Keywords

Agriculture, veterinary and food science

Access to Document

10.1109/IE51775.2021.9486575

Ruvinga-S-48448-AAMAccepted author manuscript, 499 KBLicence: Unspecified

https://doi.org/10.1109/IE51775.2021.9486575

Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals
Ruvinga, S., Hunter, G. J. A., Duran, O. & Nebel, J. C., 2021.
Research output: Contribution to conference › Paper › peer-review

Open Access
File
8 Downloads (Pure)

Cite this

Ruvinga, S., Hunter, G. J. A., Duran, O., & Nebel, J.-C. (2021). Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. In Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai https://doi.org/10.1109/IE51775.2021.9486575

Ruvinga, Stenford ; Hunter, Gordon J.A. ; Duran, Olga et al. / Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai. 2021.

@inproceedings{4917d5e9fe354dd393e05ae379d0dcb2,

title = "Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals",

abstract = "Honeybees are of vital importance to both agriculture and ecology, but honeybee populations have been in serious decline over recent years. The queen bee is of crucial importance to the success of a colony. In this paper, we make a contribution to addressing these problems by employing LSTM, Multi-Layer Perceptron Neural Networks and Logistic Regression approaches applied to audio data recorded from ‟queen-less” and ‟queen-right” hives to provide a method of prompt detection of a hive lacking a healthy queen. The initial results - particularly from the LSTM - are highly encouraging.",

keywords = "Agriculture, veterinary and food science",

author = "Stenford Ruvinga and Hunter, \{Gordon J.A.\} and Olga Duran and Jean-Christophe Nebel",

note = "Note: Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai",

year = "2021",

doi = "10.1109/IE51775.2021.9486575",

language = "English",

booktitle = "Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai",

}

Ruvinga, S, Hunter, GJA , Duran, O & Nebel, J-C 2021, Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. in Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai. https://doi.org/10.1109/IE51775.2021.9486575

Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. / Ruvinga, Stenford; Hunter, Gordon J.A.; Duran, Olga et al.
Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai. 2021.

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

TY - GEN

T1 - Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

AU - Ruvinga, Stenford

AU - Hunter, Gordon J.A.

AU - Duran, Olga

AU - Nebel, Jean-Christophe

N1 - Note: Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai

PY - 2021

Y1 - 2021

N2 - Honeybees are of vital importance to both agriculture and ecology, but honeybee populations have been in serious decline over recent years. The queen bee is of crucial importance to the success of a colony. In this paper, we make a contribution to addressing these problems by employing LSTM, Multi-Layer Perceptron Neural Networks and Logistic Regression approaches applied to audio data recorded from ‟queen-less” and ‟queen-right” hives to provide a method of prompt detection of a hive lacking a healthy queen. The initial results - particularly from the LSTM - are highly encouraging.

AB - Honeybees are of vital importance to both agriculture and ecology, but honeybee populations have been in serious decline over recent years. The queen bee is of crucial importance to the success of a colony. In this paper, we make a contribution to addressing these problems by employing LSTM, Multi-Layer Perceptron Neural Networks and Logistic Regression approaches applied to audio data recorded from ‟queen-less” and ‟queen-right” hives to provide a method of prompt detection of a hive lacking a healthy queen. The initial results - particularly from the LSTM - are highly encouraging.

KW - Agriculture, veterinary and food science

U2 - 10.1109/IE51775.2021.9486575

DO - 10.1109/IE51775.2021.9486575

M3 - Conference contribution

BT - Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai

ER -

Ruvinga S, Hunter GJA , Duran O , Nebel JC. Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. In Published in 2021 17th International Conference on Intelligent Environments (IE). ISBN: 9781665403467. ISSN (electronic) 2472-7571. ISSN (Print on Demand) 2469-8792. Organising Body: Middlesex University Dubai Organising Body: Middlesex University Dubai. 2021 Epub 2021 Jul 20. doi: 10.1109/IE51775.2021.9486575

Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

Cite this