Developing a Framework for Data Understanding in the Manufacturing Industry

  • Background

    In today's manufacturing processes, vast amounts of data are created with the goal to analyze and extract relevant information to human domain experts. Yet, inherent to the collected data still major challenges exist to make use of this data. An example of such a challenge is the high dimensionality of these datasets and resulting highly non-linear relationships between variables. So far, methods of the rising field of artificial intelligence (AI), have been used to tackle such challenges. However, practice has shown that such models often fail to capture the inherent complexities of the datasets and, thus, to deliver benefits when deployed in real-world environments. In contrast, recent research revealed that this can be caused by an insufficient understanding of the relevant characteristics of those datasets.

     

    Research Goal

    The goal of this thesis is to investigate ways to amplify the understanding of data in the context of manufacturing. One approach could be to tap the rich knowledge of domain experts and make use of their knowledge to aid machine learning experts in building more reliable and better performing models. Therefore, this thesis aims to develop a framework based on existing literature on the role of human experts in understanding the data to ultimately reach sufficient model performances in real-world environments. Doing so, you will apply established research methods (e.g., systematic literature review and inductive content analysis) to create novel insights in the emerging research field of data-centric AI and, specifically, data understanding. 

     

    We look forward to receiving your application because you:

    - You are interested in the field of data-centric artificial intelligence
    - You are highly motivated to work on recent real-world problems in a self-organized and goal-oriented working mode and you bring in own ideas
    - Very good English skills as the thesis will be written in English

     

    Details

     - Start: Immediately

     - Duration: 6 months

     

    We offer you a challenging research topic, close supervision, and the opportunity to develop practical and theoretical skills. If you are interested, send your CV, transcript of records, and a brief letter of motivation to philipp.spitzer@kit.edu and Joshua.holstein@kit.edu .