Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2023 Feb 15;13:2688. doi: 10.1038/s41598-023-29574-0

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2023

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Classifier performance. (A) Test set accuracy and overall F1 score of the classifier on the home-cage dataset as a function of the proportion of the dataset used to train it. The proportion of data denoted on the x-axis is used to train the classifier, which is then evaluated on the remainder of the dataset. (B) Sample ethogram of classifier labels and ground-truth annotations from 10 randomly selected home-cage clips. Each colored line indicates the label of that behavior at the corresponding time stamp. Vertical black lines denote the divisions of the video into clips (one minute in duration). (C) Test set accuracy on the home-cage dataset as a function of the proportion of data used to train the classifier, for clips of varying length (clip duration denoted in minutes). (D) Total number of annotated frames in each dataset. (E–G) Same as (A–C), but for the CRIM13 dataset. (H) Test set accuracy on the CRIM13 dataset as a function of the amount of training data for classifiers trained with features from the side camera, top camera, and both the side and top cameras. Lines and shaded regions in (A,C,E,G,H) indicate mean and standard error, respectively, across 10 random splits of the data.