Information Engineering
We Derive Value from Data and Information
- How to leverage information?
- How to find new topics and trends?
- How to derive insight from heterogeneous/unstructured data and information?
- How to predict events?
- How can software learn from past events?
These are but a few of the questions that the Information Engineering (IE) group is working to answer. While the “data and information flood” is often discussed negatively, we see a great opportunity to leverage data and information using the right approaches – both at search-time, as well as during analysis.
The group transfers insights derived from research and development into teaching for students of the computer science curricula. It offers modules such as “Information Engineering 1 (Information Retrieval)”, “Information Engineering 2 (Data Warehousing & Big Data)”, “Artificial Intelligence 1”, “Artificial Intelligence 2”, and “Machine Learning”. The group is active in both national and international research projects of the EU framework programs.
Research Topics
The group is concerned with fundamental sub-disciplines of the field Data Science and is founding member of ZHAW Datalab.
Information Retrieval
Information Retrieval (IR) is concerned with all facets of search relating to unstructured and semi-structured data. In particular, aspects from related Natural Language Processing sub-disciplines intersect with IR, leading to research areas such as cross-language retrieval. Further topics include multimedia retrieval, categorization, recommender services, question answering and topic/trend/event detection.
Databases and Information Systems
Databases, information systems and data warehousing are a range of areas that focus on processing of structured data/information and Big Data. Interesting aspects include efficient storage, administration and querying of this data, with the goal of supporting decision-making processes. A key line of investigation centres on the construction of natural-language interfaces to databases, thus enabling a natural, “human” dialog with such systems. Other topics include the application of machine learning algorithms to data management problems such as query optimization or data fusion.
Artificial Intelligence
Artificial Intelligence and Machine Learning are concerned with the design and analysis of smart systems through the use of machine learning methods, notably deep learning and reinforcement learning approaches. An important focus area is the successful handling of pattern recognition problems, e.g. in areas such as predictive maintenance, document analysis, object classification and detection in computer vision or speaker recognition. A common research thread across these diverse problem areas is the investigation of applicability and robustness of algorithms across different scales of data, as well as the interpretability of results.
Projects
-
Synthetic data generation of CoVID-19 CT/X-rays images for enabling fast triage of healthy vs. unhealthy patients
The automatic analysis of X-ray/CT images through artificial intelligence models can be useful to automate the clinical scanning procedure. Nonetheless, the limited access to real COVID patient data leads to the need of synthesizing image samples. The goal of this project is to use existing CT/X-ray image datasets ...
-
Predictive replenishment of urban distribution centres for the decentralised food supply
-
DIR3CT: Deep Image Reconstruction through X-Ray Projection-based 3D Learning of Computed Tomography Volumes
Project DIR3CT aims at improving the image quality of CBCT images by deep learning (DL) the 3D reconstruction from X-ray images end-to-end. This enables a novel CBCT product to be used during radiation therapy and will allow the use of these images for adaptive treatment.
Publications
-
Liang, Shiqi; Stockinger, Kurt; de Farias, Tarcisio Mendes; Anisimova, Maria; Gil, Manuel,
2021.
Querying knowledge graphs in natural language.
Journal of Big Data.
8(3).
Available from: https://doi.org/10.1186/s40537-020-00383-w
-
Stadelmann, Thilo; Würsch, Christoph,
2020.
Maps for an uncertain future : teaching AI and machine learning using the ATLAS concept.
Winterthur:
ZHAW Zürcher Hochschule für Angewandte Wissenschaften.
Available from: https://doi.org/10.21256/zhaw-20885
-
Tuggener, Lukas; Amirian, Mohammadreza; Benites de Azevedo e Souza, Fernando; von Däniken, Pius; Gupta, Prakhar; Schilling, Frank-Peter; Stadelmann, Thilo,
2020.
Design patterns for resource-constrained automated deep-learning methods.
AI.
1(4),
pp.510-538.
Available from: https://doi.org/10.3390/ai1040031
-
Tuggener, Lukas; Satyawan, Yvan Putra; Pacha, Alexander; Schmidhuber, Jürgen; Stadelmann, Thilo,
2020.
The DeepScoresV2 dataset and benchmark for music object detection [paper].
In:
Proceedings of the 25th International Conference on Pattern Recognition 2020 (ICPR’20).
25th International Conference on Pattern Recognition 2020 (ICPR’20), Online, 10-15 January 2021.
IAPR.
Available from: https://doi.org/10.21256/zhaw-20647
-
Glüge, Stefan; Amirian, Mohammadreza; Flumini, Dandolo; Stadelmann, Thilo,
2020.
How (not) to measure bias in face recognition networks [paper].
In:
Schilling, Frank-Peter; Stadelmann, Thilo, eds.,
Artificial Neural Networks in Pattern Recognition.
9th IAPR TC 3 Workshop on Artificial Neural Networks for Pattern Recognition (ANNPR'20), Winterthur, Switzerland, 2-4 September 2020.
Cham:
Springer.
Lecture Notes in Computer Science ; 12294.
Available from: https://doi.org/10.1007/978-3-030-58309-5_10