Projects

These are the projects Stephan Doerfel has mainly contributed to:

The project Abfragen, Verarbeiten und Auswerten von Prozessdaten im Spritzguss (AVAPS) — Query, Manage, and Evaluate Data from Injection Moulding Processes was funded by Innovationsförderung Hessen (LOEWE-Förderlinie 3). The project focussed on the automatic management of data created during moulding processes. In this world wide line of industry, tools and forms are moulded from synthetic material in large numbers. The product quality depends on various factors inside the machine and its environment. Determining the quality of each product individually is costly. Build-in sensors of injection moulding machines nowadays create high resolution time series data. Using the software created in AVAPS, it is possible to systematically collect and manage such data from various machines. Next to the creation of that software, the project also focusses on the exploitation of the data for the purpose of predicting product quality using machine learning methodology. Results have been published in the Polymers journal.

In the DFG funded project „Akademisches Publikationsmanagement“ (PUMA) — Academic Publication Management, we used and extended the publication management system BibSonomy to create a new web portal that is run locally at an institution (library, university, etc.) and that integrates there with the existing eco system by connecting to the local open access repository, the publication discovery service or the eLearning platform.

In the DFG funded Project „Informationelle Selbstbestimmung im Web 2.0“ (Info 2.0) — Informational self-determination in Web 2.0, we analyzed opportunities and risks in Web 2.0 systems, regarding issues of privacy. A second aspect that was investigated were consequences of user-generated ratings and reviews of products and particularly of scholarly publications. The project’s results have been published as a book.

BibSonomy

BibSonomy is a scholarly social bookmarking system where researchers manage their collections of publications and web pages. BibSonomy is an open source project, continously developed by researchers in Kassel, Würzburg, and Hannover. Functioning as a test bed for recommendation and ranking algorithms, as well as through the publicly available datasets, containing traces of user behavior on the Web, BibSonomy has been the subject of various scientific studies.