Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning

As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Groß, Janek, Kläs, Michael, Jöckel, Lisa, Gerber, Pascal
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 Groß, Janek
Kläs, Michael
Jöckel, Lisa
Gerber, Pascal
description As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work,we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.
doi_str_mv 10.48550/arxiv.2305.14872
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2305_14872</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2305_14872</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-83cef2cd4ac2b987277cbf83eb6f3bbd79cade117a91675cf8282489c80c292d3</originalsourceid><addsrcrecordid>eNpVkM1OwzAQhH3hgAoPwAm_QELi_Ng5VlULkVIhpCCO0dpeU0uNE9kp0CfgtUkDF06j0eysNB8hd2kS56IokgfwX_YjZllSxGkuOLsm363tMaC3GCL4BI_01Sn0E1g3nembh3FEH6gZ_L_g5QRussYqmOzg6GBo7eabfrHR7hQusnUHmDuarmu6HzQeA5UQZj839qAO1iFtELyz7v2GXBk4Brz90xVpd9t28xQ1z4_1Zt1EUHIWiUyhYUrnoJis5gGcK2lEhrI0mZSaVwo0pimHKi15oYxgguWiUiJRrGI6W5H737cLiW70tgd_7i5EuoVI9gMyNV8j</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning</title><source>arXiv.org</source><creator>Groß, Janek ; Kläs, Michael ; Jöckel, Lisa ; Gerber, Pascal</creator><creatorcontrib>Groß, Janek ; Kläs, Michael ; Jöckel, Lisa ; Gerber, Pascal</creatorcontrib><description>As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work,we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.</description><identifier>DOI: 10.48550/arxiv.2305.14872</identifier><language>eng</language><subject>Computer Science - Learning ; Computer Science - Software Engineering</subject><creationdate>2023-05</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/2305.14872$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2305.14872$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Groß, Janek</creatorcontrib><creatorcontrib>Kläs, Michael</creatorcontrib><creatorcontrib>Jöckel, Lisa</creatorcontrib><creatorcontrib>Gerber, Pascal</creatorcontrib><title>Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning</title><description>As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work,we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.</description><subject>Computer Science - Learning</subject><subject>Computer Science - Software Engineering</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpVkM1OwzAQhH3hgAoPwAm_QELi_Ng5VlULkVIhpCCO0dpeU0uNE9kp0CfgtUkDF06j0eysNB8hd2kS56IokgfwX_YjZllSxGkuOLsm363tMaC3GCL4BI_01Sn0E1g3nembh3FEH6gZ_L_g5QRussYqmOzg6GBo7eabfrHR7hQusnUHmDuarmu6HzQeA5UQZj839qAO1iFtELyz7v2GXBk4Brz90xVpd9t28xQ1z4_1Zt1EUHIWiUyhYUrnoJis5gGcK2lEhrI0mZSaVwo0pimHKi15oYxgguWiUiJRrGI6W5H737cLiW70tgd_7i5EuoVI9gMyNV8j</recordid><startdate>20230524</startdate><enddate>20230524</enddate><creator>Groß, Janek</creator><creator>Kläs, Michael</creator><creator>Jöckel, Lisa</creator><creator>Gerber, Pascal</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230524</creationdate><title>Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning</title><author>Groß, Janek ; Kläs, Michael ; Jöckel, Lisa ; Gerber, Pascal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-83cef2cd4ac2b987277cbf83eb6f3bbd79cade117a91675cf8282489c80c292d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Computer Science - Software Engineering</topic><toplevel>online_resources</toplevel><creatorcontrib>Groß, Janek</creatorcontrib><creatorcontrib>Kläs, Michael</creatorcontrib><creatorcontrib>Jöckel, Lisa</creatorcontrib><creatorcontrib>Gerber, Pascal</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Groß, Janek</au><au>Kläs, Michael</au><au>Jöckel, Lisa</au><au>Gerber, Pascal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning</atitle><date>2023-05-24</date><risdate>2023</risdate><abstract>As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work,we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.</abstract><doi>10.48550/arxiv.2305.14872</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2305.14872
ispartof
issn
language eng
recordid cdi_arxiv_primary_2305_14872
source arXiv.org
subjects Computer Science - Learning
Computer Science - Software Engineering
title Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T02%3A29%3A25IST&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=Timeseries-aware%20Uncertainty%20Wrappers%20for%20Uncertainty%20Quantification%20of%20Information-Fusion-Enhanced%20AI%20Models%20based%20on%20Machine%20Learning&rft.au=Gro%C3%9F,%20Janek&rft.date=2023-05-24&rft_id=info:doi/10.48550/arxiv.2305.14872&rft_dat=%3Carxiv_GOX%3E2305_14872%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