The surveillance state of behavioral automation

Abstract

Genetics' demand for increased throughput is driving automatization of behavior analysis far beyond experimental workhorses like circadian monitors and the operant conditioning box. However, the new automation is not just faster: it is also allowing new kinds of experiments, many of which erase the boundaries of the traditional neuroscience disciplines (psychology, ethology and physiology) while producing insight into problems that were otherwise opaque. Ironically, a central theme of current automatization is to improve observation of animals in increasingly naturalistic environments. This is not just a return to 19th century priorities: the new observational methods provide unprecedented quantitation of actions and ever-closer integration with experimentation.

Figure 1

A system for tracking multiple animals and classifying behaviors: ctrax. (a) A representative trace of 1 of 20 simultaneously tracked flies from a 2 min interval. The trace is annotated with instances of seven automatically classified behaviors. (b) A time-resolved ethogram of 30 s, showing the behavioral epochs and two locomotor measures, speed and turning angle. Images from [29^••] with permission.

Figure 2

Tagging individual mice with RFID chips allows for social housing yet through distinct gates and tunnels makes it possible to automatically separate and channel individual mice to arbitrary conditioning units [26,27^•,54^•]. There, standard automatic high-resolution behavioral analysis can take place using defined auditory, visual, olfactory, somatosensory or other stimuli (Schaefer & Bus, Soc Neurosci. Abstr. 670.5 2010). This approach combines interruption free group housing over periods of months with highly quantitative and sensitive behavioral analysis in a low maintenance, high-throughput and cost effective way.