Deep learning-assisted comparative analysis of animal trajectories with DeepHL
| العنوان: | Deep learning-assisted comparative analysis of animal trajectories with DeepHL |
|---|---|
| المؤلفون: | Koji Yamazaki, Kaoru Ide, Yizhe Zhang, Koutarou D. Kimura, Ryusuke Fujisawa, Susumu Takahashi, Shinsuke Koike, Takahisa Miyatake, Hisashi Shidara, Kentarou Matsumura, Matasaburo Fukutomi, Naohisa Nagaya, Kazuya Ohara, Shuhei J. Yamazaki, Takuya Maekawa, Sakiko Matsumoto, Ken Yoda, Hiroto Ogawa |
| المصدر: | Nature Communications, Vol 11, Iss 1, Pp 1-15 (2020) Nature Communications |
| بيانات النشر: | Nature Publishing Group, 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | 0301 basic medicine, Insecta, Computer science, Movement, Science, Big data, General Physics and Astronomy, Animal migration, Machine learning, computer.software_genre, General Biochemistry, Genetics and Molecular Biology, Article, Birds, 03 medical and health sciences, Mice, 0302 clinical medicine, Software, Deep Learning, Animals, lcsh:Science, Data mining, Focus (computing), Multidisciplinary, Artificial neural network, Behavior, Animal, business.industry, Deep learning, Contrast (statistics), General Chemistry, 030104 developmental biology, Global Positioning System, Female, lcsh:Q, Artificial intelligence, Neural Networks, Computer, business, Scale (map), computer, 030217 neurology & neurosurgery, Ursidae |
| الوصف: | A comparative analysis of animal behavior (e.g., male vs. female groups) has been widely used to elucidate behavior specific to one group since pre-Darwinian times. However, big data generated by new sensing technologies, e.g., GPS, makes it difficult for them to contrast group differences manually. This study introduces DeepHL, a deep learning-assisted platform for the comparative analysis of animal movement data, i.e., trajectories. This software uses a deep neural network based on an attention mechanism to automatically detect segments in trajectories that are characteristic of one group. It then highlights these segments in visualized trajectories, enabling biologists to focus on these segments, and helps them reveal the underlying meaning of the highlighted segments to facilitate formulating new hypotheses. We tested the platform on a variety of trajectories of worms, insects, mice, bears, and seabirds across a scale from millimeters to hundreds of kilometers, revealing new movement features of these animals. Comparative analysis of animal behaviour using locomotion data such as GPS data is difficult because the large amount of data makes it difficult to contrast group differences. Here the authors apply deep learning to detect and highlight trajectories characteristic of a group across scales of millimetres to hundreds of kilometres. |
| اللغة: | English |
| تدمد: | 2041-1723 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dbbddb54c1981ef5c6a4a10ef0468555Test http://link.springer.com/article/10.1038/s41467-020-19105-0Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....dbbddb54c1981ef5c6a4a10ef0468555 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 20411723 |
|---|