Information Processing, FHNW School of Computer Science

The Information Processing research group focuses on the automated extraction and processing of information from diverse types of data. To achieve this, we employ techniques from machine learning, natural language processing, data mining, and statistics.

Our objective is to analyse existing data as precisely as possible in order to generate new insights. End users benefit from accurate estimates and predictions for unseen data, as well as from products that can learn from individual user behaviour.

• Modelling, simulation, and optimisation of processes and organisations
• Implementation of methods that compare plans with their execution to support decision-making processes
• Development and evaluation of algorithms for the optimal generation of information
• Data collection, modelling, and interpretation of social networks
  

• Machine Learning
• Natural Language Processing
• Algorithmic and combinatorial optimisation methods
• Social network analysis
• Data Mining
• Information Retrieval / Ontologies

Using optimisation techniques, for example, the lifecycle of a building or the behaviour of a construction company can be simulated and optimised in a computational environment. Process modelling enables the comparison of planned versus actual performance, enhances process control, and supports informed decision-making.

The use of social networks on the internet has become part of everyday life for many people. In recent years, numerous applications have emerged that enable easy publishing and networking online.

Social network analysis helps to better understand complex relationships between actors. The insights gained from such analyses enable organisations to receive targeted advice, improve organisational development processes, and generate forecasts.