The Experts below are selected from a list of 5901 Experts worldwide ranked by ideXlab platform
Emmanouil Benetos - One of the best experts on this subject based on the ideXlab platform.
-
Audio-based Identification of Beehive States
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
-
ICASSP - Audio-based Identification of Beehive States
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
-
to bee or not to bee investigating machine learning approaches for beehive sound recognition
arXiv: Sound, 2018Co-Authors: Ines Nolasco, Emmanouil BenetosAbstract:In this work, we aim to explore the potential of machine learning methods to the problem of beehive sound recognition. A major contribution of this work is the creation and release of annotations for a selection of beehive recordings. By experimenting with both support vector machines and convolutional neural networks, we explore important aspects to be considered in the development of beehive sound recognition systems using machine learning approaches.
-
audio based identification of beehive states
arXiv: Sound, 2018Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. % The system is built on top of a method for beehive sound recognition in order to detect bee sounds from other external sounds. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
Ines Nolasco - One of the best experts on this subject based on the ideXlab platform.
-
Audio-based Identification of Beehive States
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
-
ICASSP - Audio-based Identification of Beehive States
ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2019Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
-
to bee or not to bee investigating machine learning approaches for beehive sound recognition
arXiv: Sound, 2018Co-Authors: Ines Nolasco, Emmanouil BenetosAbstract:In this work, we aim to explore the potential of machine learning methods to the problem of beehive sound recognition. A major contribution of this work is the creation and release of annotations for a selection of beehive recordings. By experimenting with both support vector machines and convolutional neural networks, we explore important aspects to be considered in the development of beehive sound recognition systems using machine learning approaches.
-
audio based identification of beehive states
arXiv: Sound, 2018Co-Authors: Ines Nolasco, Stefania Cecchi, Simone Orcioni, Alessandro Terenzi, Helen L. Bear, Emmanouil BenetosAbstract:The absence of the queen in a beehive is a very strong indicator of the need for beekeeper intervention. Manually searching for the queen is an arduous recurrent task for beekeepers that disrupts the normal life cycle of the beehive and can be a source of stress for bees. Sound is an indicator for signalling different states of the beehive, including the absence of the queen bee. In this work, we apply machine learning methods to automatically recognise different states in a beehive using audio as input. % The system is built on top of a method for beehive sound recognition in order to detect bee sounds from other external sounds. We investigate both support vector machines and convolutional neural networks for beehive state recognition, using audio data of Beehives collected from the NU-Hive project. Results indicate the potential of machine learning methods as well as the challenges of generalizing the system to new hives.
Abdul Azim Azlan - One of the best experts on this subject based on the ideXlab platform.
-
i-BeeHOME: An Intelligent Stingless Honey Beehives Monitoring Tool Based On TOPSIS Method By Implementing LoRaWan – A Preliminary Study
Computational Science and Technology, 2020Co-Authors: Wan Nor Shuhadah Wan Nik, Aznida Hayati Zakaria, Zarina Mohamad, Abdul Azim AzlanAbstract:This paper describes a preliminary study on the development of an intelligent bee hives monitoring tool called i-BeeHOME . This tool benefits LoRa and LoRaWan (LoRa in low power WANs) technology. This intelligent tool is capable to collect crucial information on bee colony hives in real-time despite of its remote location. The capability as a smart device of i-BeeHOME is further advanced when these information is then analyzed using one of the most well-known multi-criteria decision making (MCDM) method, i.e. TOPSIS. Therefore, it is realized that the capability of i-BeeHOME is three-fold, i.e. (1) collects and retrieves crucial information from Beehives despite of its remote/rural location where WiFi/BLE based networks are ineffective by using LoRa technology, (2) analyzes information collected to predict the conformity of bee hives location for high quality of honey production by using TOPSIS method, and (3) tracking the geographical location of Beehives in protecting it from being stolen/lost by using LoRaWAN technology. It is expected that the development of this tool will not only help the beekeepers to monitor honey Beehives with minimum effort, but also implicitly allows further investigation on how to promote high quality of honey production by stingless bees.
-
i beehome an intelligent stingless honey Beehives monitoring tool based on topsis method by implementing lorawan a preliminary study
2020Co-Authors: Wan Nor Shuhadah Wan Nik, Aznida Hayati Zakaria, Zarina Mohamad, Abdul Azim AzlanAbstract:This paper describes a preliminary study on the development of an intelligent bee hives monitoring tool called i-BeeHOME. This tool benefits LoRa and LoRaWan (LoRa in low power WANs) technology. This intelligent tool is capable to collect crucial information on bee colony hives in real-time despite of its remote location. The capability as a smart device of i-BeeHOME is further advanced when these information is then analyzed using one of the most well-known multi-criteria decision making (MCDM) method, i.e. TOPSIS. Therefore, it is realized that the capability of i-BeeHOME is three-fold, i.e. (1) collects and retrieves crucial information from Beehives despite of its remote/rural location where WiFi/BLE based networks are ineffective by using LoRa technology, (2) analyzes information collected to predict the conformity of bee hives location for high quality of honey production by using TOPSIS method, and (3) tracking the geographical location of Beehives in protecting it from being stolen/lost by using LoRaWAN technology. It is expected that the development of this tool will not only help the beekeepers to monitor honey Beehives with minimum effort, but also implicitly allows further investigation on how to promote high quality of honey production by stingless bees.
Tanya Strateva - One of the best experts on this subject based on the ideXlab platform.
-
WGS-based characterization of the potentially beneficial Enterococcus faecium EFD from a beehive
Molecular Biology Reports, 2020Co-Authors: Svetoslav G. Dimov, Anita Guyrova, Antoniya Vladimirova, Martin Dimitrov, Slavil Peykov, Tanya StratevaAbstract:Nowadays, due to their potential application as probiotics for humans or animals, many beneficial lactic acid bacteria have been isolated from different natural environments. These include members of the genus Enterococcus - quite specific due to their ambiguous nature, varying from pathogens to probiotics. In our work we present a whole-genome sequencing (WGS)-based approach for assessing the potential of bacteriocin-producing Enterococcus isolates from Beehives to serve as natural preserving agents against bacterial infections associated with honeybees. Potential Enterococcus spp. isolates from pollen granules were tested with the well diffusion assay for bacteriocin activity against Paenibacillus larvae , the causative agent of the American foulbrood disease (AFB). Two of them gave positive results and were determined at species level by 16S rRNA genes sequencing. They were then subjected to WGS using the Illumina HiSeq platform. The resulting raw data reads were processed and further analyzed by using only freely available web-based tools (the Shovill pipeline, QUAST, BAGEL4, ResFinder, VirulenceFinder and PlasmidFinder). The analysis revealed that both of them represent clonally identical isolates of the same strain. This specific strain was named Enterococcus faecium EFD, and was genotyped by the MLST-2.0 Server. Five bacteriocin genes were found in the assembled genome, providing a possible explanation for the antimicrobial properties of the isolate. The protein nature of the inhibitory agent/s was confirmed by treatment with proteinase K. No resistance determinants for clinically important antibiotics and functional virulence factor genes were detected. The bioinformatic analyses of the draft genome sequence suggest that E. faecium EFD is not pathogenic.The observation that E. faecium EFD was present within more than one of the Beehives in the apiary proposes the idea that E. faecium EFD is there as a part of the normal beehive microbiota. This finding, in combination with its antibacterial activity against P. larvae , highlights this novel isolate as a potential natural preserving agent against AFB. Furthermore, the WGS-based approach reported here proved to be very cost- and time- efficient, for screening the applicability of new pro- and prebiotic Enterococcus strains as beehive protection agents.
Elizabeth R. Gebhard - One of the best experts on this subject based on the ideXlab platform.
-
New Chemical Evidence for the Use of Combed Ware Pottery Vessels as Beehives in Ancient Greece
Journal of Archaeological Science, 2003Co-Authors: Richard P. Evershed, Dudd, Virginia R. Anderson-stojanovic, Elizabeth R. GebhardAbstract:Abstract Coarseware vessels from excavations at Isthmia, Greece, in contexts dating from the Hellenistic and Roman periods, resemble ceramic Beehives used by the ancient Greeks and still in recent use on the Cycladic islands and Crete. Chemical investigations of absorbed residues were performed with the aim of obtaining direct evidence for the use of these vessels as Beehives. High-temperature gas chromatography (HT-GC) and HT-GC/mass spectrometry (HT-GC/MS) were used to screen lipid extracts for the presence of compounds characteristic of beeswax. Samples of beeswax taken from a 19C ethnographic beehive was used as reference material. Potsherds from 10 pithoi recovered from the same Isthmia excavation served as controls. A significant proportion of the sherds from the putative beehive vessels contained compounds, i.e. n- alkanes, wax esters, fatty acids and long-chain alcohols congruent with those seen in the reference beeswax. δ 13 C values were determined for the individual components of the lipid extracts and reference beeswax by means of compound specific GC-combustion-isotope ratio mass spectrometry (GC-C-IRMS). On the basis of the molecular structures, carbon number distributions and δ 13 C values 16 of the 40 sherds studied were shown to contain residues of beeswax. None of the pithoi contained beeswax residues although two yielded residues consistent with degraded triacylglycerols.