@thesis{Volkan2024, author = {Volkan, Taylan Delil}, title = {Raytracing-based and phenomenological modelling of precipitation effects on automotive flash LiDAR sensors}, publisher = {Technische Hochschule Ingolstadt}, address = {Ingolstadt}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:573-50635}, pages = {79}, school = {Technische Hochschule Ingolstadt}, year = {2024}, abstract = {For the accurate environmental perception in simulation environments, high-quality sensor models are needed. This is especially the case for the simulation of adverse weather conditions. Traditional physics-based approaches appear to have limited scalability. Because of this, two phenomenological approaches have developed in this thesis, which model the adverse effects on a Flash LiDAR sensor in a generative manner. The main contributions are the following: 1. The development of a statistical model. For this model, a data extraction strategy has been developed. On the extracted data, the model can then be fitted. 2. The development of a generative adversarial network (GAN), which models the adverse weather effects on a LiDAR, by implicit distribution modelling. 3. The development of of validation strategies. Additionally the models are compared to a ray-tracing based model, which serves as a benchmark.}, language = {en} } @inproceedings{HartungHerygersKurlekaretal.2023, author = {Hartung, Kai and Herygers, Aaricia and Kurlekar, Shubham Vijay and Zakaria, Khabbab and Volkan, Taylan and Gr{\"o}ttrup, S{\"o}ren and Georges, Munir}, title = {Measuring Sentiment Bias in Machine Translation}, booktitle = {Text, Speech, and Dialogue: 26th International Conference: Proceedings}, editor = {Ekštein, Kamil and P{\´a}rtl, František and Konop{\´i}k, Miloslav}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-40498-6}, issn = {1611-3349}, doi = {https://doi.org/10.1007/978-3-031-40498-6_8}, pages = {82 -- 93}, year = {2023}, language = {en} }