Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning

Ultrasound is employed in, e.g., non-destructive testing and environmental sensing. Unfortunately, conventional single-element ultrasound probes have a limited acoustic aperture. To overcome this limitation, we employ a modern method to increase the field-of-view of a commercial transducer and to te...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tom Sillanpää, Krista Longi, Joni Mäkinen, Timo Rauhala, Arto Klami, Ari Salmi, Edward Hæggström
Formato:	article
Lenguaje:	EN
Publicado:	AIP Publishing LLC 2021
Materias:	Physics QC1-999
Acceso en línea:	https://doaj.org/article/d7a116cc0e8c4851af0b56ddf3e01310
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d7a116cc0e8c4851af0b56ddf3e01310
record_format	dspace
spelling	oai:doaj.org-article:d7a116cc0e8c4851af0b56ddf3e013102021-12-01T18:52:06ZLocalizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning2158-322610.1063/5.0068803https://doaj.org/article/d7a116cc0e8c4851af0b56ddf3e013102021-11-01T00:00:00Zhttp://dx.doi.org/10.1063/5.0068803https://doaj.org/toc/2158-3226Ultrasound is employed in, e.g., non-destructive testing and environmental sensing. Unfortunately, conventional single-element ultrasound probes have a limited acoustic aperture. To overcome this limitation, we employ a modern method to increase the field-of-view of a commercial transducer and to test the approach by localizing a target. In practice, we merge the transducer with a chaotic cavity to increase the effective aperture of the transducer. In conventional pulse-echo ultrasound signal analysis, location estimation is based on determining the time-of-flight with known propagation speed in the medium. In the present case, the dispersing field induces complexity to this inverse problem, also in 2D. To tackle this issue, we use a convolutional neural network-based machine learning approach to study the feasibility of employing one single chaotic cavity transducer to localize an object in 2D. We show that we indeed can localize an inclusion inside a water-filled cylinder. The localization accuracy is one diameter of the inclusion. The area that we can infer increases by 49% in comparison to using the same transducer without applying the proposed chaotic cavity method.Tom SillanpääKrista LongiJoni MäkinenTimo RauhalaArto KlamiAri SalmiEdward HæggströmAIP Publishing LLCarticlePhysicsQC1-999ENAIP Advances, Vol 11, Iss 11, Pp 115104-115104-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Physics QC1-999
spellingShingle	Physics QC1-999 Tom Sillanpää Krista Longi Joni Mäkinen Timo Rauhala Arto Klami Ari Salmi Edward Hæggström Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
description	Ultrasound is employed in, e.g., non-destructive testing and environmental sensing. Unfortunately, conventional single-element ultrasound probes have a limited acoustic aperture. To overcome this limitation, we employ a modern method to increase the field-of-view of a commercial transducer and to test the approach by localizing a target. In practice, we merge the transducer with a chaotic cavity to increase the effective aperture of the transducer. In conventional pulse-echo ultrasound signal analysis, location estimation is based on determining the time-of-flight with known propagation speed in the medium. In the present case, the dispersing field induces complexity to this inverse problem, also in 2D. To tackle this issue, we use a convolutional neural network-based machine learning approach to study the feasibility of employing one single chaotic cavity transducer to localize an object in 2D. We show that we indeed can localize an inclusion inside a water-filled cylinder. The localization accuracy is one diameter of the inclusion. The area that we can infer increases by 49% in comparison to using the same transducer without applying the proposed chaotic cavity method.
format	article
author	Tom Sillanpää Krista Longi Joni Mäkinen Timo Rauhala Arto Klami Ari Salmi Edward Hæggström
author_facet	Tom Sillanpää Krista Longi Joni Mäkinen Timo Rauhala Arto Klami Ari Salmi Edward Hæggström
author_sort	Tom Sillanpää
title	Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
title_short	Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
title_full	Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
title_fullStr	Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
title_full_unstemmed	Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
title_sort	localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning
publisher	AIP Publishing LLC
publishDate	2021
url	https://doaj.org/article/d7a116cc0e8c4851af0b56ddf3e01310
work_keys_str_mv	AT tomsillanpaa localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT kristalongi localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT jonimakinen localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT timorauhala localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT artoklami localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT arisalmi localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning AT edwardhæggstrom localizingatargetinsideanenclosedcylinderwithasinglechaoticcavitytransduceraugmentedwithsupervisedmachinelearning
_version_	1718404659447595008

Localizing a target inside an enclosed cylinder with a single chaotic cavity transducer augmented with supervised machine learning

Ejemplares similares