The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art
The lateral line organ of fish has inspired engineers to develop flow sensor arrays—dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4558 |
| _version_ | 1827688177414963200 |
|---|---|
| author | Daniël M. Bot Ben J. Wolf Sietse M. van Netten |
| author_facet | Daniël M. Bot Ben J. Wolf Sietse M. van Netten |
| author_sort | Daniël M. Bot |
| collection | DOAJ |
| description | The lateral line organ of fish has inspired engineers to develop flow sensor arrays—dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisation algorithms for ALLs. Differences in the studied domain, sensor sensitivity axes, and available data prevent a fair comparison between these algorithms from their original works. We compare them with our novel quadrature method (QM), which is based on a geometric property specific to 2D-sensitive ALLs. We show how the area in which each algorithm can accurately determine the position and orientation of a simulated dipole source is affected by (1) the amount of training and optimisation data, and (2) the sensitivity axes of the sensors. Overall, we find that each algorithm benefits from 2D-sensitive sensors, with alternating sensitivity axes as the second-best configuration. From the machine learning approaches, an MLP required an impractically large training set to approach the optimisation-based algorithms’ performance. Regardless of the data set size, QM performs best with both a large area for accurate predictions and a small tail of large errors. |
| first_indexed | 2024-03-10T09:50:14Z |
| format | Article |
| id | doaj.art-cd027f5095cc4a31b62b0e8195850015 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:50:14Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cd027f5095cc4a31b62b0e81958500152023-11-22T02:51:06ZengMDPI AGSensors1424-82202021-07-012113455810.3390/s21134558The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the ArtDaniël M. Bot0Ben J. Wolf1Sietse M. van Netten2I-BioStat, Data Science Institute, Hasselt University, 3500 Hasselt, BelgiumDelft Center for Systems and Control, Delft University of Technology, 2628 CD Delft, The NetherlandsBernoulli Institute of Mathematics, Computer Science and Artificial Intelligence, Faculty of Science and Engineering, University of Groningen, 9747 AG Groningen, The NetherlandsThe lateral line organ of fish has inspired engineers to develop flow sensor arrays—dubbed artificial lateral lines (ALLs)—capable of detecting near-field hydrodynamic events for obstacle avoidance and object detection. In this paper, we present a comprehensive review and comparison of ten localisation algorithms for ALLs. Differences in the studied domain, sensor sensitivity axes, and available data prevent a fair comparison between these algorithms from their original works. We compare them with our novel quadrature method (QM), which is based on a geometric property specific to 2D-sensitive ALLs. We show how the area in which each algorithm can accurately determine the position and orientation of a simulated dipole source is affected by (1) the amount of training and optimisation data, and (2) the sensitivity axes of the sensors. Overall, we find that each algorithm benefits from 2D-sensitive sensors, with alternating sensitivity axes as the second-best configuration. From the machine learning approaches, an MLP required an impractically large training set to approach the optimisation-based algorithms’ performance. Regardless of the data set size, QM performs best with both a large area for accurate predictions and a small tail of large errors.https://www.mdpi.com/1424-8220/21/13/4558hydrodynamic imagingdipole localisationartificial lateral lineneural networks |
| spellingShingle | Daniël M. Bot Ben J. Wolf Sietse M. van Netten The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art Sensors hydrodynamic imaging dipole localisation artificial lateral line neural networks |
| title | The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art |
| title_full | The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art |
| title_fullStr | The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art |
| title_full_unstemmed | The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art |
| title_short | The Quadrature Method: A Novel Dipole Localisation Algorithm for Artificial Lateral Lines Compared to State of the Art |
| title_sort | quadrature method a novel dipole localisation algorithm for artificial lateral lines compared to state of the art |
| topic | hydrodynamic imaging dipole localisation artificial lateral line neural networks |
| url | https://www.mdpi.com/1424-8220/21/13/4558 |
| work_keys_str_mv | AT danielmbot thequadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart AT benjwolf thequadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart AT sietsemvannetten thequadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart AT danielmbot quadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart AT benjwolf quadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart AT sietsemvannetten quadraturemethodanoveldipolelocalisationalgorithmforartificiallaterallinescomparedtostateoftheart |