Rapid parameter estimation of discrete decaying signals using autoencoder networks

In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Visschers, Jim C, Budker, Dmitry, Bougas, Lykourgos
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Visschers, Jim C
Budker, Dmitry
Bougas, Lykourgos
description In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cram\'er-Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, we explore the limitations of our approach, demonstrating that analysis rates of $>$200 kHz are feasible with further optimization of the transfer rate between the data-acquisition system and data-analysis system.
doi_str_mv 10.48550/arxiv.2103.08663
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2103_08663</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2103_08663</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-5e2c30214624cdb5f4fc97bfdb1a4624ddf496faa06711a749e0e16e8a94da013</originalsourceid><addsrcrecordid>eNotj8tqwzAQRbXJoiT9gK6qH7AjWbJsL0NIHxAohOzNWBoF0UQyktI2f1877WqYw73DHEKeOCtlW9dsDfHHfZUVZ6JkrVLigRwOMDpDR4hwwYyRYsruAtkFT4OlxiUdJ04Narg5f6LJnTycE72meYNrDuh1MFPTY_4O8TOtyMJOCXz8n0tyfNkdt2_F_uP1fbvZF6AaUdRYacEqLlUltRlqK63umsGagcPMjLGyUxaAqYZzaGSHDLnCFjppgHGxJM9_Z-9S_Rint-Otn-X6u5z4BdFeS8w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Rapid parameter estimation of discrete decaying signals using autoencoder networks</title><source>arXiv.org</source><creator>Visschers, Jim C ; Budker, Dmitry ; Bougas, Lykourgos</creator><creatorcontrib>Visschers, Jim C ; Budker, Dmitry ; Bougas, Lykourgos</creatorcontrib><description>In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cram\'er-Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, we explore the limitations of our approach, demonstrating that analysis rates of $&gt;$200 kHz are feasible with further optimization of the transfer rate between the data-acquisition system and data-analysis system.</description><identifier>DOI: 10.48550/arxiv.2103.08663</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Neural and Evolutionary Computing ; Physics - Data Analysis, Statistics and Probability</subject><creationdate>2021-03</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2103.08663$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2103.08663$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Visschers, Jim C</creatorcontrib><creatorcontrib>Budker, Dmitry</creatorcontrib><creatorcontrib>Bougas, Lykourgos</creatorcontrib><title>Rapid parameter estimation of discrete decaying signals using autoencoder networks</title><description>In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cram\'er-Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, we explore the limitations of our approach, demonstrating that analysis rates of $&gt;$200 kHz are feasible with further optimization of the transfer rate between the data-acquisition system and data-analysis system.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Neural and Evolutionary Computing</subject><subject>Physics - Data Analysis, Statistics and Probability</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAQRbXJoiT9gK6qH7AjWbJsL0NIHxAohOzNWBoF0UQyktI2f1877WqYw73DHEKeOCtlW9dsDfHHfZUVZ6JkrVLigRwOMDpDR4hwwYyRYsruAtkFT4OlxiUdJ04Narg5f6LJnTycE72meYNrDuh1MFPTY_4O8TOtyMJOCXz8n0tyfNkdt2_F_uP1fbvZF6AaUdRYacEqLlUltRlqK63umsGagcPMjLGyUxaAqYZzaGSHDLnCFjppgHGxJM9_Z-9S_Rint-Otn-X6u5z4BdFeS8w</recordid><startdate>20210310</startdate><enddate>20210310</enddate><creator>Visschers, Jim C</creator><creator>Budker, Dmitry</creator><creator>Bougas, Lykourgos</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210310</creationdate><title>Rapid parameter estimation of discrete decaying signals using autoencoder networks</title><author>Visschers, Jim C ; Budker, Dmitry ; Bougas, Lykourgos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-5e2c30214624cdb5f4fc97bfdb1a4624ddf496faa06711a749e0e16e8a94da013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Neural and Evolutionary Computing</topic><topic>Physics - Data Analysis, Statistics and Probability</topic><toplevel>online_resources</toplevel><creatorcontrib>Visschers, Jim C</creatorcontrib><creatorcontrib>Budker, Dmitry</creatorcontrib><creatorcontrib>Bougas, Lykourgos</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Visschers, Jim C</au><au>Budker, Dmitry</au><au>Bougas, Lykourgos</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Rapid parameter estimation of discrete decaying signals using autoencoder networks</atitle><date>2021-03-10</date><risdate>2021</risdate><abstract>In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cram\'er-Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, we explore the limitations of our approach, demonstrating that analysis rates of $&gt;$200 kHz are feasible with further optimization of the transfer rate between the data-acquisition system and data-analysis system.</abstract><doi>10.48550/arxiv.2103.08663</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2103.08663
ispartof
issn
language eng
recordid cdi_arxiv_primary_2103_08663
source arXiv.org
subjects Computer Science - Learning
Computer Science - Neural and Evolutionary Computing
Physics - Data Analysis, Statistics and Probability
title Rapid parameter estimation of discrete decaying signals using autoencoder networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T16%3A45%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Rapid%20parameter%20estimation%20of%20discrete%20decaying%20signals%20using%20autoencoder%20networks&rft.au=Visschers,%20Jim%20C&rft.date=2021-03-10&rft_id=info:doi/10.48550/arxiv.2103.08663&rft_dat=%3Carxiv_GOX%3E2103_08663%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true