Journal article Open Access

Supplementary Materials for: Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Robert D. Chambers; Nathanael C. Yoder; Aletha B. Carson; Christian Junge; David E. Allen; Laura M. Prescott; Sophie Bradley; Garrett Wymore; Kevin Lloyd; Scott Lyle

Supplementary Materials

 

Figure S1: Guide to interpreting supplementary videos. The videos listed below follow the template in this frame capture. The source video file is played in an inset (a), and the synchronized accelerometer data is scrolled through the plot in (b). The head motion estimate produced by the algorithm (accounting for device position and orientation on the collar) is visualized in (c). The algorithm estimates the probability that various behaviors (d) and postures (e) are occurring, based solely on the accelerometer data (the video data is not seen or otherwise used by the algorithm). A small visual display of the most likely predicted class is superimposed on the inset (f). 

 

Table S1: Index of supplementary videos

Reason Included

Video

Examples of eating- and drinking-related behaviors, including licking the empty bowl.

S1, S2, S3

 

Example of general behavior, including playing.

S4

Examples of dermatology-related behaviors: scratching, self-licking, rubbing, and shaking.

S5

S6

Classification of eating behavior while eating from a slow-feed bowl, which presents some challenges to the algorithms.

S7

 

 

Files (44.9 MB)
Name Size
S1.mp4
md5:555896e839ead1db0b640ba09f28d332
6.8 MB Download
S2.mp4
md5:84f60797d21a6d0c806b084267d4989a
3.7 MB Download
S3.mp4
md5:17f9bf717e70aa40d618719462695634
10.0 MB Download
S4.mp4
md5:2f49c6db5c5fcded1d55473353c38c9d
9.2 MB Download
S5.mp4
md5:649f05831bcf4f952999978abee0bc6f
3.7 MB Download
S6.mp4
md5:33d1b315646c0508ea9aee8049bb9c40
2.0 MB Download
S7.mp4
md5:5f278d5b7bfb01a9b67021228660307b
9.4 MB Download
174
161
views
downloads
All versions This version
Views 174174
Downloads 161161
Data volume 1.0 GB1.0 GB
Unique views 150150
Unique downloads 4747

Share

Cite as