DC ElementWertSprache
dc.contributor.authorShoushtari, Hossein-
dc.contributor.authorKassawat, Firas-
dc.contributor.authorHarder, Dorian-
dc.contributor.authorVenzke, Korvin-
dc.contributor.authorMüller-Lietzkow, Jörg-
dc.contributor.authorSternberg, Harald-
dc.date.accessioned2022-12-09T14:31:39Z-
dc.date.available2022-12-09T14:31:39Z-
dc.date.issued2022-
dc.identifier.citationIPIN-WiP 2022 : Indoor Positioning and Indoor Navigation - Work-in-Progress Papers 2022en_US
dc.identifier.urihttps://repos.hcu-hamburg.de/handle/hcu/843-
dc.description.abstractFifth generation of mobile communications (5G) and Deep Neural Networks (DNN) are two important technologies, which will enable new functions in the field of indoor positioning. This could be seen as the second major development after the innovation of smartphones, as a GNSS/INS alternative for indoor, location based applications. Optimization methods which work as a corrector, and as the uncertainty assessment for real life applications, guided us through the next level of challenges. In this paper, we have opened a novel interpretation of a deep network for inertial odometry which is robust to noisy labelled data that was detected from a 5G network. We also designed and developed analytical platform, which is considered a data collector and cellular positioning simulation. This platform was used to provide the input for the learning and optimization algorithms. The simulation website is implemented and available online under simulation2evaluation.herokuapp.com for researchers to generate ground truth trajectories and simulated cellular measurements with assigned quality and exact error values. We have proposed two approaches: (1) deep inertial odometry based on predicting velocity vector elements or relative positions and (2) Kalman Filtering to use, combine and test the absolute positions with the relative ones from the first approach. We finally provide numerical results of our experiments and a discussion of the effectiveness of our approaches.en
dc.language.isoenen_US
dc.publisherCEUR-WS-
dc.subjectIndoor Localizationen
dc.subject5G Simulationen
dc.subject5G Correctionen
dc.subjectDeep Neural Networksen
dc.subjectKalman Filteren
dc.subjectSmartphoneen
dc.subject.ddc004: Informatik-
dc.titleL5IN+: From an Analytical Platform to Optimization of Deep Inertial Odometryen
dc.typeconferencePaperen_US
dc.relation.conference12th International Conference on Indoor Positioning and Indoor Navigation - Work-in-Progress Papers (IPIN-WiP 2022), 5-7 September 2022, Beijing, China.en_US
dc.type.diniConferencePaper-
dc.type.driverconferenceObject-
dc.rights.cchttps://creativecommons.org/licenses/by/4.0/en_US
dc.type.casraiConference Paper-
dcterms.DCMITypeText-
tuhh.identifier.urnurn:nbn:de:gbv:1373-repos-10729-
tuhh.oai.showtrueen_US
tuhh.publication.instituteHydrographie und Geodäsieen_US
tuhh.publication.instituteÖkonomie und Digitalisierungen_US
tuhh.type.opusInProceedings (Aufsatz / Paper einer Konferenz etc.)-
tuhh.relation.ispartofseriesnumber3248en_US
tuhh.relation.ispartofseriesCEUR workshop proceedingsen_US
tuhh.type.rdmfalse-
openaire.rightsinfo:eu-repo/semantics/openAccessen_US
item.grantfulltextopen-
item.creatorOrcidShoushtari, Hossein-
item.creatorOrcidKassawat, Firas-
item.creatorOrcidHarder, Dorian-
item.creatorOrcidVenzke, Korvin-
item.creatorOrcidMüller-Lietzkow, Jörg-
item.creatorOrcidSternberg, Harald-
item.fulltextWith Fulltext-
item.seriesrefCEUR workshop proceedings;3248-
item.languageiso639-1en-
item.tuhhseriesidCEUR workshop proceedings-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.creatorGNDShoushtari, Hossein-
item.creatorGNDKassawat, Firas-
item.creatorGNDHarder, Dorian-
item.creatorGNDVenzke, Korvin-
item.creatorGNDMüller-Lietzkow, Jörg-
item.creatorGNDSternberg, Harald-
item.openairetypeconferencePaper-
crisitem.author.deptGeodäsie und Geoinformatik-
crisitem.author.deptGeodäsie und Geoinformatik-
crisitem.author.deptÖkonomie und Digitalisierung-
crisitem.author.deptHydrographie und Geodäsie-
Enthalten in der SammlungPublikationen (mit Volltext)
Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat
paper24.pdf2.9 MBAdobe PDFÖffnen/Anzeigen
Zur Kurzanzeige

Seitenansichten

468
checked on 23.12.2024

Download(s)

87
checked on 23.12.2024

Google ScholarTM

Prüfe

Export

Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons