Underwater Translational Target Direction Recognition Based on Lateral Line Perception Principle and Deep Learning

Abstract Inspired by the lateral line systems of various aquatic organisms that are capable of hydrodynamic imaging using ambient flow information, this study develops a deep learning-based object localization model that can detect the location of objects using flow information measured from a moving sensor array. In numerical simulations with the assumption of a potential flow, a two-dimensional hydrofoil navigates around four stationary cylinders in a uniform flow and obtains two types of sensory data during a simulation, namely flow velocity and pressure, from an array of sensors located on the surface of the hydrofoil. Several neural network models are constructed using the flow velocity and pressure data, and these are used to detect the positions of the hydrofoil and surrounding objects. The model based on a long short-term memory network, which is capable of learning order dependence in sequence prediction problems, outperforms the other models. The number of sensors is then optimized using feature selection techniques. This sensor optimization leads to a new object localization model that achieves impressive accuracy in predicting the locations of the hydrofoil and objects with only 40$\%$ of the sensors used in the original model.

Download Full-text

A Study on the Fine Structure of the Lateral Line Organ of the Sea Eel

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100073684 ◽

1973 ◽

Vol 31 ◽

pp. 648-649

Author(s):

K. Hama

Keyword(s):

Fine Structure ◽

Electron Microscope ◽

Lateral Line ◽

Low Frequency ◽

Sensory Cells ◽

Apical Surface ◽

Voltage Electron ◽

Sensory Epithelia ◽

Low Frequency Vibration ◽

Transmission Electron

The lateral line organs of the sea eel consist of canal and pit organs which are different in function. The former is a low frequency vibration detector whereas the latter functions as an ion receptor as well as a mechano receptor.The fine structure of the sensory epithelia of both organs were studied by means of ordinary transmission electron microscope, high voltage electron microscope and of surface scanning electron microscope.The sensory cells of the canal organ are polarized in front-caudal direction and those of the pit organ are polarized in dorso-ventral direction. The sensory epithelia of both organs have thinner surface coats compared to the surrounding ordinary epithelial cells, which have very thick fuzzy coatings on the apical surface.

Download Full-text

Scanning Electron Microscopy of Fish Scales as an Adjunctive Aid in Speciation

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100095236 ◽

1972 ◽

Vol 30 ◽

pp. 394-395

Author(s):

Edward D. DeLamater ◽

Walter R. Courtenay ◽

Cecil Whitaker

Keyword(s):

Electron Microscopy ◽

Scanning Electron Microscopy ◽

Lateral Line ◽

Species Differences ◽

Fish Scale ◽

Fish Scales ◽

Anterior Border ◽

The University ◽

Multiple Holes ◽

Scanning Electron

Comparative scanning electron microscopy studies of fish scales of different orders, families, genera and species within genera have demonstrated differences which warrant elaboration. These differences in detail appear to be sufficient to act as “fingerprints”, at least, for family differences. To date, the lateral line scales have been primarily studied. These demonstrate differences in the lateral line canals; the pattern of ridging with or without secondary protuberances along the edges; the pattern of spines or their absence on the anterior border of the scales; the presence or absence of single or multiple holes on the ventral and dorsal sides of the lateral line canal covers. The distances between the ridges in the pattern appear likewise to be important.A statement of fish scale structure and a comparison of family and species differences will be presented.The authors wish to thank Dr. Donald Marzalek and Mr. Wallace Charm of the Marine and Atmospheric Laboratory of the University of Miami and Dr. Sheldon Moll and Dr. Richard Turnage of AMR for their exhaustive help in these preliminary studies.

Download Full-text

Deep Learning

10.1017/cbo9780511780295 ◽

2009 ◽

Cited By ~ 94

Author(s):

Stellan Ohlsson

Keyword(s):

Deep Learning

Download Full-text

Lateral line system

AccessScience ◽

10.1036/1097-8542.757316 ◽

2015 ◽

Keyword(s):

Lateral Line ◽

Lateral Line System ◽

Line System

Download Full-text

Intercepting Moving Targets on Foot: Target Direction Change

PsycEXTRA Dataset ◽

10.1037/e537052012-351 ◽

2004 ◽

Author(s):

Justin M. Owens ◽

William H. Warren

Keyword(s):

Moving Targets ◽

Target Direction ◽

Direction Change

Download Full-text

Intelligence artificielle : le futur de l’Orthodontie ?

Revue d Orthopédie Dento-Faciale ◽

10.1051/odf/2019026 ◽

2019 ◽

Vol 53 (3) ◽

pp. 281-294

Author(s):

Jean-Michel Foucart ◽

Augustin Chavanne ◽

Jérôme Bourriau

Keyword(s):

Big Data ◽

Deep Learning ◽

Intelligence Artificielle ◽

Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Download Full-text