Automated monitoring of honey bees with barcodes and artificial intelligence reveals two distinct social networks from a single affiliative behavior.
Automated monitoring of honey bees with barcodes and artificial intelligence reveals two distinct social networks from a single affiliative behavior.
复制标题
DOI：
10.1038/s41598-022-26825-4
复制
发表时间：
2023-01-27
影响因子：
4.6
通讯作者：
Robinson, Gene E. E.
中科院分区：
文献类型：
--
作者：
Gernat, Tim;Jagla, Tobias;Jones, Beryl M. M.;Middendorf, Martin;Robinson, Gene E. E.
基于条形码的个体跟踪正在彻底改变动物行为研究，但进一步的进展取决于除了确定个体的位置之外，是否可以识别和监测特定的行为。我们使用来自条形码的信息来识别可能显示感兴趣行为的紧密边界图像区域来实现这一目标。然后用卷积神经网络分析这些图像区域，以验证行为是否发生。当应用到一个具有挑战性的测试案例中，检测蜂巢中的社会液体转移（营养轴）时，该方法比迄今为止最好的蜜蜂营养轴检测器的灵敏度高67%，错误率低11%。此外，我们还能够自动检测蜜蜂是否捐献或接受液体，而以前需要人工观察。通过将我们的营养轴探测器应用于三个蜂群的记录并进行模拟，我们发现蜜蜂之间的液体交换产生了两个具有不同传播能力的不同社会网络。最后，我们证明了我们的方法可以推广到检测其他特定行为。我们设想它的广泛应用将使自动、高分辨率的行为研究成为可能，这些研究将解决进化生物学、行为学、神经科学和分子生物学中广泛的以前难以解决的问题。
Barcode-based tracking of individuals is revolutionizing animal behavior studies, but further progress hinges on whether in addition to determining an individual’s location, specific behaviors can be identified and monitored. We achieve this goal using information from the barcodes to identify tightly bounded image regions that potentially show the behavior of interest. These image regions are then analyzed with convolutional neural networks to verify that the behavior occurred. When applied to a challenging test case, detecting social liquid transfer (trophallaxis) in the honey bee hive, this approach yielded a 67% higher sensitivity and an 11% lower error rate than the best detector for honey bee trophallaxis so far. We were furthermore able to automatically detect whether a bee donates or receives liquid, which previously required manual observations. By applying our trophallaxis detector to recordings from three honey bee colonies and performing simulations, we discovered that liquid exchanges among bees generate two distinct social networks with different transmission capabilities. Finally, we demonstrate that our approach generalizes to detecting other specific behaviors. We envision that its broad application will enable automatic, high-resolution behavioral studies that address a broad range of previously intractable questions in evolutionary biology, ethology, neuroscience, and molecular biology.
登录
查看更多内容
影响因子：
25
作者：
Mathis, Alexander;Mamidanna, Pranav;Bethge, Matthias
通讯作者：
Bethge, Matthias
影响因子：
16.6
作者：
Crall, James D.;Gravish, Nick;Combes, Stacey A.
通讯作者：
Combes, Stacey A.
影响因子：
7.7
作者：
Gal A;Saragosti J;Kronauer DJ
通讯作者：
Kronauer DJ
影响因子：
4.6
作者：
Blut, Christina;Crespi, Alessandro;Beye, Martin
通讯作者：
Beye, Martin
影响因子：
7.7
作者：
Jones BM;Rao VD;Gernat T;Jagla T;Cash-Ahmed AC;Rubin BE;Comi TJ;Bhogale S;Husain SS;Blatti C;Middendorf M;Sinha S;Chandrasekaran S;Robinson GE
通讯作者：
Robinson GE