JAABA: interactive machine learning for automatic annotation of animal behavior
JAABA: interactive machine learning for automatic annotation of animal behavior
复制标题
DOI：
10.1038/nmeth.2281
复制
发表时间：
2013-01-01
期刊：
影响因子：
48
通讯作者：
Branson, Kristin
中科院分区：
文献类型：
--
作者：
Kabra, Mayank;Robie, Alice A.;Branson, Kristin
我们提出了一个基于机器学习的系统，用于自动计算动物行为的可解释的定量测量。通过我们的交互系统，用户通过注释一小部分视频帧来编码他们对行为的直觉。这些手动标签被转换为分类器，可以自动注释屏幕规模数据集中的行为。我们的通用系统可以为不同的生物创建各种准确的个人和社会行为分类器，包括老鼠和成虫和幼虫果蝇。
We present a machine learning-based system for automatically computing interpretable, quantitative measures of animal behavior. Through our interactive system, users encode their intuition about behavior by annotating a small set of video frames. These manual labels are converted into classifiers that can automatically annotate behaviors in screen-scale data sets. Our general-purpose system can create a variety of accurate individual and social behavior classifiers for different organisms, including mice and adult and larval Drosophila.