Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Autoencoder-Based Characterisation of Passive IEEE 802.11 Link Level Measurements

: Neuhaus, Priyanka; Henninger, Marcus; Frotzscher, Andreas; Wetzker, Ulf

Postprint urn:nbn:de:0011-n-6382202 (350 KByte PDF)
MD5 Fingerprint: b6349b911416647dde3f200891adf905
Erstellt am: 27.7.2021

Institute of Electrical and Electronics Engineers -IEEE-:
Joint European Conference On Networks and Communication and 6G Summit 2021 : Virtual Conference, 8 - 11 June 2021, Porto, Portugal
Piscataway, NJ: IEEE, 2021
ISBN: 978-1-6654-3021-0
ISBN: 978-1-6654-1525-5
ISBN: 978-1-6654-1526-2
European Conference on Networks and Communications (EuCNC) <30, 2021, Online>
6G Summit <3, 2021, Online>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IIS, Institutsteil Entwurfsautomatisierung (EAS) ()
Wireless Network Analysis; Industrial WirelessCommunications; Passive Monitoring; Anomaly Detection; Machine Learning

Wireless networks are indispensable in today’s industrial manufacturing and automation. Due to harsh signalpropagation conditions as well as co-existing wireless networks,transmission failures resulting in severe application malfunctionsare often difficult to diagnose. Remote wireless monitoring systems are extremely useful tools for troubleshooting such failures.However, the completeness of data captured by a remotewireless monitor is highly dependent on the temporal, e.g., shortterm interference, and spatial characteristics of its environment.It is necessary to first ensure that the data was completelycaptured at the remote monitor in order to maintain the integrityof the failure analysis, i.e., to avoid false positives. In this paper,we propose an autoencoder-based framework to evaluate thequality of wireless data captured at a remote wireless monitor.The algorithm is trained using data generated under controlledlaboratory conditions and validated on testbed as well as realworld measurement data.