Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks
This study presents a novel method that combines a computational fluid-structure interaction model with an interpretable deep-learning model to explore the fundamental mechanisms of seal whisker sensing. By establishing connections between crucial signal patterns, flow characteristics, and attribute...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-08-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2023.1231715/full |
_version_ | 1797755434938925056 |
---|---|
author | Dariush Bodaghi Yuxing Wang Geng Liu Dongfang Liu Qian Xue Qian Xue Xudong Zheng Xudong Zheng |
author_facet | Dariush Bodaghi Yuxing Wang Geng Liu Dongfang Liu Qian Xue Qian Xue Xudong Zheng Xudong Zheng |
author_sort | Dariush Bodaghi |
collection | DOAJ |
description | This study presents a novel method that combines a computational fluid-structure interaction model with an interpretable deep-learning model to explore the fundamental mechanisms of seal whisker sensing. By establishing connections between crucial signal patterns, flow characteristics, and attributes of upstream obstacles, the method has the potential to enhance our understanding of the intricate sensing mechanisms. The effectiveness of the method is demonstrated through its accurate prediction of the location and orientation of a circular plate placed in front of seal whisker arrays. The model also generates temporal and spatial importance values of the signals, enabling the identification of significant temporal-spatial signal patterns crucial for the network’s predictions. These signal patterns are further correlated with flow structures, allowing for the identification of important flow features relevant for accurate prediction. The study provides insights into seal whiskers’ perception of complex underwater environments, inspiring advancements in underwater sensing technologies. |
first_indexed | 2024-03-12T17:47:48Z |
format | Article |
id | doaj.art-b00973802fc147f78038b3ac1030fcf0 |
institution | Directory Open Access Journal |
issn | 2296-9144 |
language | English |
last_indexed | 2024-03-12T17:47:48Z |
publishDate | 2023-08-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Robotics and AI |
spelling | doaj.art-b00973802fc147f78038b3ac1030fcf02023-08-03T12:33:16ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442023-08-011010.3389/frobt.2023.12317151231715Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networksDariush Bodaghi0Yuxing Wang1Geng Liu2Dongfang Liu3Qian Xue4Qian Xue5Xudong Zheng6Xudong Zheng7Department of Mechanical Engineering, University of Maine, Orono, ME, United StatesDepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY, United StatesDepartment of Engineering, King’s College, Wilkes-Barre, PA, United StatesDepartment of Computer Engineering, Rochester Institute of Technology, Rochester, NY, United StatesDepartment of Mechanical Engineering, University of Maine, Orono, ME, United StatesDepartment of Mechanical Engineering, Rochester Institute of Technology, Rochester, NY, United StatesDepartment of Mechanical Engineering, University of Maine, Orono, ME, United StatesDepartment of Mechanical Engineering, Rochester Institute of Technology, Rochester, NY, United StatesThis study presents a novel method that combines a computational fluid-structure interaction model with an interpretable deep-learning model to explore the fundamental mechanisms of seal whisker sensing. By establishing connections between crucial signal patterns, flow characteristics, and attributes of upstream obstacles, the method has the potential to enhance our understanding of the intricate sensing mechanisms. The effectiveness of the method is demonstrated through its accurate prediction of the location and orientation of a circular plate placed in front of seal whisker arrays. The model also generates temporal and spatial importance values of the signals, enabling the identification of significant temporal-spatial signal patterns crucial for the network’s predictions. These signal patterns are further correlated with flow structures, allowing for the identification of important flow features relevant for accurate prediction. The study provides insights into seal whiskers’ perception of complex underwater environments, inspiring advancements in underwater sensing technologies.https://www.frontiersin.org/articles/10.3389/frobt.2023.1231715/fullbioinspired flow sensingwake identificationseal whiskerinterpretable machine learningfluid-structure interaction |
spellingShingle | Dariush Bodaghi Yuxing Wang Geng Liu Dongfang Liu Qian Xue Qian Xue Xudong Zheng Xudong Zheng Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks Frontiers in Robotics and AI bioinspired flow sensing wake identification seal whisker interpretable machine learning fluid-structure interaction |
title | Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks |
title_full | Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks |
title_fullStr | Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks |
title_full_unstemmed | Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks |
title_short | Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks |
title_sort | deciphering the connection between upstream obstacles wake structures and root signals in seal whisker array sensing using interpretable neural networks |
topic | bioinspired flow sensing wake identification seal whisker interpretable machine learning fluid-structure interaction |
url | https://www.frontiersin.org/articles/10.3389/frobt.2023.1231715/full |
work_keys_str_mv | AT dariushbodaghi decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT yuxingwang decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT gengliu decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT dongfangliu decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT qianxue decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT qianxue decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT xudongzheng decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks AT xudongzheng decipheringtheconnectionbetweenupstreamobstacleswakestructuresandrootsignalsinsealwhiskerarraysensingusinginterpretableneuralnetworks |