Dataset Information

Automated computer-based detection of encounter behaviours in groups of honeybees.

ABSTRACT: Honeybees form societies in which thousands of members integrate their behaviours to act as a single functional unit. We have little knowledge on how the collaborative features are regulated by workers' activities because we lack methods that enable collection of simultaneous and continuous behavioural information for each worker bee. In this study, we introduce the Bee Behavioral Annotation System (BBAS), which enables the automated detection of bees' behaviours in small observation hives. Continuous information on position and orientation were obtained by marking worker bees with 2D barcodes in a small observation hive. We computed behavioural and social features from the tracking information to train a behaviour classifier for encounter behaviours (interaction of workers via antennation) using a machine learning-based system. The classifier correctly detected 93% of the encounter behaviours in a group of bees, whereas 13% of the falsely classified behaviours were unrelated to encounter behaviours. The possibility of building accurate classifiers for automatically annotating behaviours may allow for the examination of individual behaviours of worker bees in the social environments of small observation hives. We envisage that BBAS will be a powerful tool for detecting the effects of experimental manipulation of social attributes and sub-lethal effects of pesticides on behaviour.

SUBMITTER: Blut C

PROVIDER: S-EPMC5732155 | biostudies-literature | 2017 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated computer-based detection of encounter behaviours in groups of honeybees.

Blut Christina C Crespi Alessandro A Mersch Danielle D Keller Laurent L Zhao Linlin L Kollmann Markus M Schellscheidt Benjamin B Fülber Carsten C Beye Martin M

Scientific reports 20171215 1

Honeybees form societies in which thousands of members integrate their behaviours to act as a single functional unit. We have little knowledge on how the collaborative features are regulated by workers' activities because we lack methods that enable collection of simultaneous and continuous behavioural information for each worker bee. In this study, we introduce the Bee Behavioral Annotation System (BBAS), which enables the automated detection of bees' behaviours in small observation hives. Cont ...[more]

PMID: 29247217

Similar Datasets

Project description:The global rise in nature-based recreation increases the need for research on visitor activity use and interaction especially for multi-use trail systems. Conflict often arises during negatively perceived physical encounters (i.e., direct observation) of different user groups. Our study addresses these encounters on a winter multi-use refuge in Fairbanks, Alaska. Our goal was to develop a method that generates spatially and temporally explicit estimates of trail occupancy and encounter probabilities among different user groups. We used trail cameras with optic alteration to protect individual identity. We monitored winter recreational activity from November 2019 to April 2020 (n = 133 days) and sorted users into three user groups: 1) motor-powered, 2) dog-powered, and 3) human-powered. We calculated the total number of occurrences and proportion of activity across all user groups at each camera location. We identified hotspots of activity overlap (e.g., near trail access points), and peak times (14:01-15:00), days (Saturdays and Sundays), and months (December, February, and March) that may have had higher potential for physical encounters and conflict. We used multiplication and addition probability rules to estimate two probabilities: 1) the probability of user groups occupying individual trail segments, and 2) the probability of encounter between different user groups. We scaled up these probability estimates both temporally (hourly and daily) and spatially (refuge quadrant and refuge-wide). Researchers can adapt our novel method to any recreational trail system to identify locations with potential for congestion and conflict. This method can help inform management that improves visitor experience and overall trail user satisfaction.Management implicationsWe provide managers of recreational trail systems with a quantitative, objective, and noninvasive method to monitor activity among trail user groups. This method can be altered both spatially and temporally to fit any recreational trail system's research questions. These questions may involve congestion, trail carrying capacity, or user group and wildlife encounters. Our method advances current knowledge of trail use dynamics by quantifying the extent of activity overlap between different user groups that may be prone to conflict. Managers can use this information to incorporate relevant management strategies to mitigate congestion and conflict for their own recreational trail system.

Project description:BackgroundLike most living organisms, the fruit fly Drosophila melanogaster exhibits strong and diverse behavioural reactions to light. Drosophila is a diurnal animal that displays both short- and long-term responses to light, important for, instance, in avoidance and light wavelength preference, regulation of eclosion, courtship, and activity, and provides an important model organism for understanding the regulation of circadian rhythms both at molecular and circuit levels. However, the assessment and comparison of light-based behaviours is still a challenge, mainly due to the lack of a standardised platform to measure behaviour and different protocols created across studies. Here, we describe the Drosophila Interactive System for Controlled Optical manipulations (DISCO), a low-cost, automated, high-throughput device that records the flies' activity using infrared beams while performing LED light manipulations.ResultsTo demonstrate the effectiveness of this tool and validate its potential as a standard platform, we developed a number of distinct assays, including measuring the locomotor response of flies exposed to sudden darkness (lights-off) stimuli. Both white-eyed and red-eyed wild-type flies exhibit increased activity after the application of stimuli, while no changes can be observed in Fmr1 null allele flies, a model of fragile X syndrome. Next, to demonstrate the use of DISCO in long-term protocols, we monitored the circadian rhythm of the flies for 48 h while performing an alcohol preference test. We show that increased alcohol consumption happens intermittently throughout the day, especially in the dark phases. Finally, we developed a feedback-loop algorithm to implement a place preference test based on the flies' innate aversion to blue light and preference for green light. We show that both white-eyed and red-eyed wild-type flies were able to learn to avoid the blue-illuminated zones.ConclusionsOur results demonstrate the versatility of DISCO for a range of protocols, indicating that this platform can be used in a variety of ways to study light-dependent behaviours in flies.

Project description:Focus of this study is to design an automated image processing pipeline for handling uncontrolled acquisition conditions of images acquired in the field. The pipeline has been tested on the automated identification and count of uncapped brood cells in honeybee (Apis Mellifera) comb images to reduce the workload of beekeepers during the study of the hygienic behavior of honeybee colonies. The images used to develop and test the model were acquired by beekeepers on different days and hours in summer 2020 and under uncontrolled conditions. This resulted in images differing for background noise, illumination, color, comb tilts, scaling, and comb sizes. All the available 127 images were manually cropped to approximately include the comb area. To obtain an unbiased evaluation, the cropped images were randomly split into a training image set (50 images), which was used to develop and tune the proposed model, and a test image set (77 images), which was solely used to test the model. To reduce the effects of varied illuminations or exposures, three image enhancement algorithms were tested and compared followed by the Hough Transform, which allowed identifying individual cells to be automatically counted. All the algorithm parameters were automatically chosen on the training set by grid search. When applied to the 77 test images the model obtained a correlation of 0.819 between the automated counts and the experts' counts. To provide an assessment of our model with publicly available images acquired by a different equipment and under different acquisition conditions, we randomly extracted 100 images from a comb image dataset made available by a recent literature work. Though it has been acquired under controlled exposure, the images in this new set have varied illuminations; anyhow, our pipeline obtains a correlation between automatic and manual counts equal to 0.997. In conclusion, our tests on the automatic count of uncapped honey bee comb cells acquired in the field and on images extracted from a publicly available dataset suggest that the hereby generated pipeline successfully handles varied noise artifacts, illumination, and exposure conditions, therefore allowing to generalize our method to different acquisition settings. Results further improve when the acquisition conditions are controlled.

Project description:Monitoring animals in their natural habitat is essential for advancement of animal behavioural studies, especially in pollination studies. Non-invasive techniques are preferred for these purposes as they reduce opportunities for research apparatus to interfere with behaviour. One potentially valuable approach is image-based tracking. However, the complexity of tracking unmarked wild animals using video is challenging in uncontrolled outdoor environments. Out-of-the-box algorithms currently present several problems in this context that can compromise accuracy, especially in cases of occlusion in a 3D environment. To address the issue, we present a novel hybrid detection and tracking algorithm to monitor unmarked insects outdoors. Our software can detect an insect, identify when a tracked insect becomes occluded from view and when it re-emerges, determine when an insect exits the camera field of view, and our software assembles a series of insect locations into a coherent trajectory. The insect detecting component of the software uses background subtraction and deep learning-based detection together to accurately and efficiently locate the insect among a cluster of wildflowers. We applied our method to track honeybees foraging outdoors using a new dataset that includes complex background detail, wind-blown foliage, and insects moving into and out of occlusion beneath leaves and among three-dimensional plant structures. We evaluated our software against human observations and previous techniques. It tracked honeybees at a rate of 86.6% on our dataset, 43% higher than the computationally more expensive, standalone deep learning model YOLOv2. We illustrate the value of our approach to quantify fine-scale foraging of honeybees. The ability to track unmarked insect pollinators in this way will help researchers better understand pollination ecology. The increased efficiency of our hybrid approach paves the way for the application of deep learning-based techniques to animal tracking in real-time using low-powered devices suitable for continuous monitoring.

Dataset Information

Automated computer-based detection of encounter behaviours in groups of honeybees.

Publications

Automated computer-based detection of encounter behaviours in groups of honeybees.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets