Stage-oe-small.jpg

Thema4998: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Abschlussarbeit |Titel=Revolutionizing Wake Vortex Detection with AI: A Neural Network Approach |Abschlussarbeitstyp=Bachelor, Master |Betreuer=Shuzhou Yuan…“)
 
 
(Eine dazwischenliegende Version desselben Benutzers wird nicht angezeigt)
Zeile 3: Zeile 3:
 
|Abschlussarbeitstyp=Bachelor, Master
 
|Abschlussarbeitstyp=Bachelor, Master
 
|Betreuer=Shuzhou Yuan
 
|Betreuer=Shuzhou Yuan
|Partner=Das Deutsche Zentrum für Luft- und Raumfahrt
+
|Partner=DLR
 
|Forschungsgruppe=Web Science
 
|Forschungsgruppe=Web Science
 
|Abschlussarbeitsstatus=Offen
 
|Abschlussarbeitsstatus=Offen
Zeile 22: Zeile 22:
  
  
[1] https://opg.optica.org/directpdfaccess/2c598bbe-4298-468b-b153430b4a180650_471171/oe-30-8-13197.pdf?da=1&id=471171&seq=0&mobile=no
+
[1] https://opg.optica.org/directpdfaccess/fef64095-6589-4385-8815d97c2f3d2af8_471171/oe-30-8-13197.pdf?da=1&id=471171&seq=0&mobile=no
  
 
[2] https://elib.dlr.de/144976/1/2262567_Wartha_ENG5041P_Final_Report_20-21.pdf
 
[2] https://elib.dlr.de/144976/1/2262567_Wartha_ENG5041P_Final_Report_20-21.pdf
 
}}
 
}}

Aktuelle Version vom 3. Februar 2023, 14:31 Uhr



Revolutionizing Wake Vortex Detection with AI: A Neural Network Approach




Informationen zur Arbeit

Abschlussarbeitstyp: Bachelor, Master
Betreuer: Shuzhou Yuan
Forschungsgruppe: Web Science
Partner: DLR
Archivierungsnummer: 4998
Abschlussarbeitsstatus: Offen
Beginn: 02. Februar 2023
Abgabe: unbekannt

Weitere Informationen

Wake turbulence, created by aircraft during takeoff, can pose a significant safety risk for following aircraft during landing. To maintain stability and avoid destabilization, minimum separation distances between landing aircraft are established. To optimize airport capacity and promote environmental sustainability, we aim to develop a deep neural network capable of accurately detecting wake turbulence.

Join our team in collaboration with DLR (Deutsches Zentrum für Luft- und Raumfahrt) and be at the forefront of wake vortex detection. Building on previous work using con- volutional neural networks and state-of-the-art computer vision models like YOLO [1][2], you will have the opportunity to explore innovative approaches using cutting-edge tech- nologies like graph neural networks and transformers. Your work has the potential to be published as state-of-the-art research and will provide valuable hands-on experience in the field of artificial intelligence.


What prerequisites do you need?

• Solid programming skills (e.g. Python).

• Strong foundation in machine learning, deep learning or artifitial intelligence.

• Experience in LiDAR data or graph neural network is a plus.


[1] https://opg.optica.org/directpdfaccess/fef64095-6589-4385-8815d97c2f3d2af8_471171/oe-30-8-13197.pdf?da=1&id=471171&seq=0&mobile=no

[2] https://elib.dlr.de/144976/1/2262567_Wartha_ENG5041P_Final_Report_20-21.pdf


Ausschreibung: Download (pdf)