Automated monitoring of animal behaviour with barcodes and convolutional neural networks

Barcode-based tracking of individuals revolutionizes the study of animal behaviour, but further progress hinges on whether specific behaviours can be monitored. We achieve this goal by combining information obtained from the barcodes with image analysis through convolutional neural networks. Applying this novel approach to a challenging test case, the honeybee hive, we reveal that food exchange among bees generates two distinct social networks with qualitatively different transmission capabilities.

[1]  A. F. Adams,et al.  The Survey , 2021, Dyslexia in Higher Education.

[2]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Andrew M. Mountcastle,et al.  Spatial fidelity of workers predicts collective response to disturbance in a social insect , 2018, Nature Communications.

[6]  Jieping Ye,et al.  Object Detection in 20 Years: A Survey , 2019, Proceedings of the IEEE.

[7]  S. Combes,et al.  Neonicotinoid exposure disrupts bumblebee nest behavior, social networks, and thermoregulation , 2018, Science.

[8]  Alessandro Crespi,et al.  Social network plasticity decreases disease transmission in a eusocial insect , 2018, Science.

[9]  Atsuto Maki,et al.  A systematic study of the class imbalance problem in convolutional neural networks , 2017, Neural Networks.

[10]  A. Crespi,et al.  Tracking Individuals Shows Spatial Fidelity Is a Key Regulator of Ant Social Organization , 2013, Science.

[11]  L. Levin,et al.  Biodiversity on the Rocks: Macrofauna Inhabiting Authigenic Carbonate at Costa Rica Methane Seeps , 2015, PloS one.

[12]  Jacob M. Graving,et al.  DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning , 2019, bioRxiv.

[13]  Martin Middendorf,et al.  Automated monitoring of behavior reveals bursty interaction patterns and rapid spreading dynamics in honeybee social networks , 2018, Proceedings of the National Academy of Sciences.

[14]  Arjan Durresi,et al.  A survey: Control plane scalability issues and approaches in Software-Defined Networking (SDN) , 2017, Comput. Networks.

[15]  Mikhail Kislin,et al.  Fast animal pose estimation using deep neural networks , 2018, Nature Methods.

[16]  Fernando Wario,et al.  Automatic methods for long-term tracking and the detection and decoding of communication dances in honeybees , 2015, Front. Ecol. Evol..

[17]  Christian Rutz,et al.  Reality mining of animal social systems. , 2013, Trends in ecology & evolution.

[18]  Kevin M. Cury,et al.  DeepLabCut: markerless pose estimation of user-defined body parts with deep learning , 2018, Nature Neuroscience.

[19]  George Leitmann,et al.  Dynamics and Control , 2020, Fundamentals of Robotics.

[20]  N. Koeniger The biology of the honey bee , 1988, Insectes Sociaux.

[21]  Harry Dankowicz,et al.  Lifetime-preserving reference models for characterizing spreading dynamics on temporal networks , 2017, Scientific Reports.

[22]  Keith D. Waddington,et al.  Symposium: Insects in Altered Environments: Body Size and the Functional Length of the Proboscis of Honey Bees , 1987 .

[23]  Alessandro Crespi,et al.  Automated computer-based detection of encounter behaviours in groups of honeybees , 2017, Scientific Reports.

[24]  Gene E. Robinson,et al.  Honey bee virus causes context-dependent changes in host social behavior , 2020, Proceedings of the National Academy of Sciences.

[25]  Laurent Keller,et al.  Oral transfer of chemical cues, growth proteins and hormones in social insects , 2016, eLife.

[26]  W. Farina,et al.  Thermographic recordings show that honeybees may receive nectar from foragers even during short trophallactic contacts , 2001, Insectes Sociaux.

[27]  Ovidiu Lungu,et al.  Consolidation alters motor sequence-specific distributed representations , 2018, bioRxiv.

[28]  Jacob M. Graving,et al.  An automated barcode tracking system for behavioural studies in birds , 2017, bioRxiv.

[29]  Andrew M. Mountcastle,et al.  BEEtag: A Low-Cost, Image-Based Tracking System for the Study of Animal Behavior and Locomotion , 2015, bioRxiv.