Acoustic detection of mouse scratching has been automated at least once. This report tells about the mice involved, and about their scratching, and about the detection — done acoustically — of that scratching:
“Automated Acoustic Detection of Mouse Scratching,” Peter Elliott, Max G’Sell, Lindsey M. Snyder, Sarah E. Ross, and Valérie Ventura, PLoS ONE, vol. 12, no. 7, 2017, e0179662. The authors, at Carnegie Mellon University and the University of Pittsburgh, report:
“we propose a novel automated method for acoustic detection of mouse scratching. Using this approach, we show that chloroquine-induced scratching behavior in C57BL/6 mice can be quantified with reasonable accuracy… This report is the first method to apply supervised learning techniques to automate acoustic scratch detection…. Mouse scratching occurs in small sets of rapid swipes, which we refer to as scratch bouts. The goal of our procedure is to detect scratch bouts rather than individual scratches….though our results were collected from a single strain and small number of mice tested with a single pruritogen, it is likely that the approach will be broadly applicable to the audio detection of scratch.”
