JAABA: interactive machine learning for automatic annotation of animal behavior

We present a machine learning-based system for automatically computing interpretable, quantitative measures of animal behavior. Through our interactive system, users encode their intuition about behavior by annotating a small set of video frames. These manual labels are converted into classifiers that can automatically annotate behaviors in screen-scale data sets. Our general-purpose system can create a variety of accurate individual and social behavior classifiers for different organisms, including mice and adult and larval Drosophila.

Animal care and use in behavioral research : regulations, issues, and applications : based on an invited paper session presented at the l988 meeting of the Animal Behavior Society /

"September 1989."

Individual differences and family resemblances in animal behavior, a study of habit formation in various strains of mice,

Published also as thesis (PH. D.) Columbia University, 1918.

Abnormal animal behavior prior to earthquakes, I : EHRP conference I /

Includes bibliographies.

The journal of animal behavior

Mode of access: Internet.

Long-duration animal tracking in difficult lighting conditions.

High-throughput analysis of animal behavior requires software to analyze videos. Such software typically depends on the experiments' being performed in good lighting conditions, but this ideal is difficult or impossible to achieve for certain classes of experiments. Here, we describe techniques that allow long-duration positional tracking in difficult lighting conditions with strong shadows or recurring "on"/"off" changes in lighting. The latter condition will likely become increasingly common, e.g., for Drosophila due to the advent of red-shifted channel rhodopsins. The techniques enabled tracking with good accuracy in three types of experiments with difficult lighting conditions in our lab. Our technique handling shadows relies on single-animal tracking and on shadows' and flies' being accurately distinguishable by distance to the center of the arena (or a similar geometric rule); the other techniques should be broadly applicable. We implemented the techniques as extensions of the widely-used tracking software Ctrax; however, they are relatively simple, not specific to Drosophila, and could be added to other trackers as well.

Canopy characteristics and behavior of Nellore heifers in Brachiaria brizantha pastures under different grazing heights at a continuous stocking rate

The objective of this study was to evaluate the Brachiaria brizantha cv. Marandu canopy structure maintained at different grazing heights under a continuous stocking rate and with a dietary supplementation strategy for the animals during the rainy season. This study also intended to observe the relationships of these variables with the grazing behaviors of the heifers. The effects of three canopy heights (15, 25 and 35 cm) were evaluated in association with three types of supplements: one mineral and two protein/energy supplements, the first with a high rumen degradable protein and energy and the others with a low ratio. Both the protein/energy supplements were provided at 0.3% of body weight/day. The experimental design was completely randomized, with two replications and repeated measures, and took place during the period from January to April 2008. The supplementation strategies did not affect any variable related to the canopy structure. Total and green herbage masses and the ratio of green/dead material increased with canopy height. The leaf/stem ratio was higher in the lowest canopy height: 15 cm. Changes in the canopy structure caused variations in the grazing behavior of the animals. Animals maintained in the 15-cm-tall pasture grazed for a longer time, increasing the time for each meal, but the number of meals was lower than that of the animals grazing within the 35-cm-tall pasture. The grazing time of animals receiving the energy/protein supplement was lower only in the period of the day during which it was supplied. Canopy structure is affected by sward height, and changes animal behavior. Supplementation does not affect the canopy structure of the pastures with similar heights.

Influence of the environment on behavior patterns of laying hens kept in cages

The aim of this paper is to verify the correlation between environmental indicators and behaviors expressed by laying hens kept in cages. The birds react to a severe environment through their behaviors, end the behaviors can be monitored to identify the birds' welfare conditions. The behaviors birds display ere the result of stress caused by the combination of environmental temperature, relative humidity, radiant heat, and air speed (environmental temperature being the most important). In order to check the influence of the environment, an experiment was carried out on a commercial poultry farm, located in the city of Bastos. The study was initiated in March 2007, during four non-consecutive weeks. The birds' behaviors were recorded using video, by cameras installed in the cages. The birds behaviors were identified and noted for the frequency of occurrence for each bird, and the average duration of each behavior (in seconds), using video samples of 15 minutes recorded from 1 PM to 4 PM. The environmental variables collected were: air temperature, concentration of ammonia, relative air humidity, velocity of the air, noise, roof temperature, and light intensity. The observed behaviors were: opening wings, stretching, threatening, ruffling feathers, drinking water, aggressive pecking, eating, running, lying down, stretching head out of the cage, preening, mounting and prostrating. Principal Components Analysis was used to determine associations between the behavior variables and environmental variables described above. In this experiment, there were no significant correlations between behavioral variables and environmental variables.

Running behavior and its energy cost in mice selectively bred for high voluntary locomotor activity

Locomotion is central to behavior and intrinsic to many fitnesscritical activities (e.g., migration, foraging), and it competes with other life-history components for energy. However, detailed analyses of how changes in locomotor activity and running behavior affect energy budgets are scarce. We quantified these effects in four replicate lines of house mice that have been selectively bred for high voluntary wheel running (S lines) and in their four nonselected control lines (C lines). We monitored wheel speeds and oxygen consumption for 24-48 h to determine daily energy expenditure (DEE), resting metabolic rate (RMR), locomotor costs, and running behavior (bout characteristics). Daily running distances increased roughly 50%-90% in S lines in response to selection. After we controlled for body mass effects, selection resulted in a 23% increase in DEE in males and a 6% increase in females. Total activity costs (DEE - RMR) accounted for 50%-60% of DEE in both S and C lines and were 29% higher in S males and 5% higher in S females compared with their C counterparts. Energetic costs of increased daily running distances differed between sexes because S females evolved higher running distances by running faster with little change in time spent running, while S males also spent 40% more time running than C males. This increase in time spent running impinged on high energy costs because the majority of running costs stemmed from postural costs (the difference between RMR and the zero-speed intercept of the speed vs. metabolic rate relationship). No statistical differences in these traits were detected between S and C females, suggesting that large changes in locomotor behavior do not necessarily effect overall energy budgets. Running behavior also differed between sexes: within S lines, males ran with more but shorter bouts than females. Our results indicate that selection effects on energy budgets can differ dramatically between sexes and that energetic constraints in S males might partly explain the apparent selection limit for wheel running observed for over 15 generations. © 2009 by The University of Chicago. All rights reserved.

Blood Cues Induce Antipredator Behavior in Nile Tilapia Conspecifics

In this study, we show that the fish Nile tilapia displays an antipredator response to chemical cues present in the blood of conspecifics. This is the first report of alarm response induced by blood-borne chemical cues in fish. There is a body of evidence showing that chemical cues from epidermal 'club' cells elicit an alarm reaction in fish. However, the chemical cues of these 'club' cells are restricted to certain species of fish. Thus, as a parsimonious explanation, we assume that an alarm response to blood cues is a generalized response among animals because it occurs in mammals, birds and protostomian animals. Moreover, our results suggest that researchers must use caution when studying chemically induced alarm reactions because it is difficult to separate club cell cues from traces of blood. © 2013 Barreto et al.

Mecanismos de movimentação animal embasados na memória espacial

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Machine vision to identify broiler breeder behavior

Animal behavioral parameters can be used to assess welfare status in commercial broiler breeders. Behavioral parameters can be monitored with a variety of sensing devices, for instance, the use of video cameras allows comprehensive assessment of animal behavioral expressions. Nevertheless, the development of efficient methods and algorithms to continuously identify and differentiate animal behavior patterns is needed. The objective this study was to provide a methodology to identify hen white broiler breeder behavior using combined techniques of image processing and computer vision. These techniques were applied to differentiate body shapes from a sequence of frames as the birds expressed their behaviors. The method was comprised of four stages: (1) identification of body positions and their relationship with typical behaviors. For this stage, the number of frames required to identify each behavior was determined; (2) collection of image samples, with the isolation of the birds that expressed a behavior of interest; (3) image processing and analysis using a filter developed to separate white birds from the dark background; and finally (4) construction and validation of a behavioral classification tree, using the software tool Weka (model 148). The constructed tree was structured in 8 levels and 27 leaves, and it was validated using two modes: the set training mode with an overall rate of success of 96.7%, and the cross validation mode with an overall rate of success of 70.3%. The results presented here confirmed the feasibility of the method developed to identify white broiler breeder behavior for a particular group of study. Nevertheless, more improvements in the method can be made in order to increase the validation overall rate of success. (C) 2013 Elsevier B.V. All rights reserved.

Human-calf relationship and its implications on animal welfare

Pós-graduação em Zootecnia - FCAV

Behavior of the Amazonian damselfly Chalcopteryx scintillans McLachlan (Zygoptera: Polythoridae) and comments on its morphological distinction from C. rutilans (Rambur)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)