M. Sc. Philipp Rigoll
- ESS/ Research Associate
- Group: Prof. Sax
- Phone: +49 721 9654-198
- philipp rigoll∂ fzi de
Forschungszentrum Informatik (FZI)
Haid- und Neu-Str. 10 - 14
Data analysis and data mining
Driven by digitalization, data is now central to a wide variety of areas of life and business. They appear in the most diverse forms and characteristics. Data is being collected, processed and stored in more and more places. Data analysis is concerned with extracting valuable information from this data. The focus of data mining is on using statistical methods to find and describe patterns and hidden relationships in the data. At FZI/ITIV, we are researching to perform these analyses as agnostically as possible. The primary goal is the comprehensibility of the analyses and, associated with this, an understandable presentation of the results.
Building on data analysis and data mining and the associated understanding of the data, machine learning goes one step further. Here, algorithms learn the regularities of the data as a statistical model and can generalize to further data after a learning phase. Especially in the form of artificial neural networks, machine learning has proven its worth and is used, for example, for the prediction of time series, the detection of anomalies and object detection. At FZI/ITIV, we develop and investigate these methods, for example, in the context of automated driving.
Augmentation with generating artificial neural networks.
Artificial neural networks, in addition to generalizing to unknown data, are capable of generating new data (the three images above were generated by text input using the stable diffusion architecture). In addition to purely artistic and creative creation, this approach also allows for the addition of missing data points in datasets. This data set augmentation is called augmentation. We at FZI/ITIV are researching the use of augmentation with generating artificial neural networks in the context of developing automated driving functions.
|Data Science with Artificial Intelligence Methods for the Development of Highly Automated Driving Functions||Maschinelles Lernen, Datenanalyse, Künstliche neuronale Netzwerke|
Supervised Student Works
- BA: "Configuration of a pipeline for the augmentation of street images using machine learning"
- BA: " Feature analysis of automotive images augmented with Generative Adversarial Networks to evaluate their use as sample data"
- MA: "Evaluation of the applicability of augmentation using Generative Adversarial Networks in closed-loop integration testing of highly automated driving functions"
- MA: "Object-Based Latent Space Analysis to Obtain New Contexts"
Rigoll, P.; Petersen, P.; Ries, L.; Langner, J.; Sax, E.
2022. Fahrerassistenzsysteme und automatisiertes Fahren, 41–48, VDI Verlag. doi:10.51202/9783181023945-41
Rigoll, P.; Petersen, P.; Langner, J.; Sax, E.
2022. Advances in Systems Engineering : Proceedings of the 28th International Conference on Systems Engineering, ICSEng 2021, December 14-16, Wrocław, Poland. Ed.: L. Borzemski, 403–417, Springer International Publishing. doi:10.1007/978-3-030-92604-5_36
Rigoll, P.; Ries, L.; Sax, E.
2022. 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), 3139–3145, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ITSC55140.2022.9921868
Petersen, P.; Stage, H.; Langner, J.; Ries, L.; Rigoll, P.; Philipp Hohl, C.; Sax, E.
2022. 2022 IEEE International Symposium on Systems Engineering (ISSE), 1–8, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ISSE54508.2022.10005441
Ries, L.; Rigoll, P.; Braun, T.; Schulik, T.; Daube, J.; Sax, E.
2021. 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 1251–1258, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/ITSC48978.2021.9564636