Behavior Recognition: Data, performance and accuracy

Data

With the Rat/Mouse Behavior Recognition functions, the following behaviors can be automatically detected: digging (only for mice), drinking, eating, grooming, hopping (for mice), jumping (for rats), rearing (unsupported and supported), resting, sniffing, twitching (for rats), and walking. For the definition of those behaviors, see Behavior Recognition.

For each video frame, behavior is detected analyzing a number of frames before and after the current one.

▪Behavior data are available from the start of the track, to about 13 s before the end of the track when using a default Trial Control Settings, which has an additional condition for starting the track (see the figure below).

▪When the Trial Control Settings does not have the special condition mentioned above, behavior is not scored in the first 3 seconds of the track (see (*) in the figure below).

▪When samples are missed or the subject is not found for a maximum of 0.4 seconds, the subject’s position and size is interpolated using the adjacent frames.

▪When samples are missed or the subject is not found in for more than 0.4 seconds, or when the subject enters a hidden zone, the behavior detector is reset. This means that behavior is not scored some time before the first missing sample (or before entering the hidden zone) and after last missing sample (or after exiting the hidden zone). The behavior is set to Unknown (see the figure below for the exact times).

We advise you to adjust the duration of the trial in the Trial Control Settings. For example, set 6 minutes of track duration to get at least 5 minutes of automatically-detected behaviors.

Below: Schematic representation of which portions of the track do not result in detection of behavior with the Behavior Recognition function. Times next to Unknown are shown for Mouse Behavior Recognition (in bold) and Rat Behavior Recognition.

*) The first part of the track is scored as Unknown only if you start tracking as soon as the animal is detected in the arena. If your Trial Control rule includes a condition that waits 3 seconds after the animal is detected, then you make sure that behavior is scored from the start of the track. We recommend to use the default Trial Control Settings for experiments set to Rat or Mouse Behavior Recognition, which include this additional condition.

note To visualize or analyze the portions of the tracks scored as Unknown, select Unknown in the behavior property window in the Analysis profile.

Performance

When Behavior recognition is selected, and you track live, use maximally one arena. To improve performance, and avoid samples being discarded because of the use of too much processor capacity, follow these rules:

▪As a detection method, use one of the Subtraction methods, not Differencing.

▪For the nose-tail tracking, try first Rodents / Default, not Rodents / For occlusions. Use the latter only if the first does not give good results.

Accuracy

▪Rat Behavior Recognition was trained on Sprague Dawley rats and tested on various strains by DeltaPhenomics and Radboud University Nijmegen, The Netherlands. The details of this validation are in the publication listed below.

▪Mouse Behavior Recognition was trained on C57Bl6 mice, and tested on various models and strains including BalbC, CD1 (white), and TgAD models. The module has been beta tested by four experienced animal behavior specialists at different labs (two in USA, two in Europe).

The average recall rate, that is, the fraction of ground truth manually scored behaviors that EthoVision XT recognizes correctly, is 0.70.

See the following paper:

van Dam, E., J.E. van der Harst, C.J.F. ter Braak, R.A.J. Tegelenbosch, B.M. Spruijt, L.P.J.J. Noldus (2013). An automated system for the recognition of various specific rat behaviours. Journal of Neuroscience Methods 218 (2), 214–224.

http://dx.doi.org/10.1016/j.jneumeth.2013.05.012