Datenanalyse und Wissensrepräsentation in der Produktion und Logistik

In this module, students learn the basics of data analysis in production logistics companies. The module covers the entire chain of knowledge discovery, from data storage in NOSQL databases to selected data mining methods and knowledge representation techniques, for example, via semantic networks. The various influencing factors and boundary conditions for knowledge discovery in production logistics are explained using selected process models. In the specific basics of data mining, methods from the field of cluster analysis, decision trees and nearest neighbor classification are introduced. The module places the introduced topics in the context of current production logistics topics such as Big Data and decentralization and shows various possible applications. Supporting concepts such as grid and cloud computing are also addressed. In addition, related areas such as data security and data migration are discussed.

The exercise is designed to be practice-oriented and, in addition to interactive discussion of selected topics from the course, covers a basic introduction to the design of various database systems. Another focus of the exercise is given by the application of previously introduced data mining methods, which are prototypically applied by the students in small groups.