Thomas Ashleigh, Bates Kathleen, Elchesen Alex, Hartsock Iryna, Lu Hang, Bubenik Peter
School of Chemical and Biomolecular Engineering, Georgia Institute of Technology, Atlanta, GA, United States.
Department of Mathematics, University of Florida, Gainesville, FL, United States.
Front Artif Intell. 2021 Jun 29;4:668395. doi: 10.3389/frai.2021.668395. eCollection 2021.
We apply topological data analysis to the behavior of , a widely studied model organism in biology. In particular, we use topology to produce a quantitative summary of complex behavior which may be applied to high-throughput data. Our methods allow us to distinguish and classify videos from various environmental conditions and we analyze the trade-off between accuracy and interpretability. Furthermore, we present a novel technique for visualizing the outputs of our analysis in terms of the input. Specifically, we use representative cycles of persistent homology to produce synthetic videos of stereotypical behaviors.
我们将拓扑数据分析应用于生物学中广泛研究的模式生物的行为。特别是，我们使用拓扑来生成复杂行为的定量总结，该总结可应用于高通量数据。我们的方法使我们能够区分和分类来自各种环境条件的视频，并分析准确性和可解释性之间的权衡。此外，我们提出了一种新颖的技术，用于根据输入可视化我们分析的输出。具体来说，我们使用持久同调的代表性循环来生成典型行为的合成视频。
