Research Centre of Cognitive Computing in Life Sciences
With Cognitive Computing, we offer new solutions for the life sciences that are based on the fundamental understanding of man and machine as a learning system.
The Centre for Cognitive Computing for Life Sciences deals with the development and use of computational methods and models for the field of life sciences, whose properties are inspired by the learning and adaptive abilities as well as self-organisation principles of natural systems. The solutions developed support demanding human activities and decision-making processes or can be used for process automation. The following general aspects are central to our research and development: learning ability/adaptability of the systems, context-bound solutions (application context in the life sciences), systemic consideration of the application and the context.
The centre is divided into different research groups, each of which focuses on certain methods or application domains.
The research group is methodologically specialised in the development and use of adaptive algorithms and nature-inspired methods (evolutionary algorithms, Physics methods). Furthermore, the specialisation also includes the use of neuromorphic technologies and the development of hybrid approaches that combine models of complex systems with data-driven solutions. The areas of application include all areas of the life sciences with a focus on the health domain as well as laboratories and production.
The research group is methodologically specialized in reinforcement learning, unsupervised and semi-supervised learning as well as human-in-the-loop machine learning. The methodology therefore also covers topics such as online learning and agent-based systems.
Applications span all areas of the life sciences. A specific focus is on the development of machine learning solutions for applications in biotechnology.
The research group's focus is on applied research in statistical modeling and machine learning for pattern discovery, as well as data mining, pattern recognition, and forecasting in life sciences. We have a proven track record in the areas of med-tech, personalized health and sports analytics.
The group's expertise lies in the fusion of heterogenous information sources and ensemble methods, in particular for time series and image/video analytics. In the context of Industry 4.0, the group conducts research in the area of predictive and prescriptive maintenance.
The research group focuses on the modeling of natural systems and their interaction with humans. This also includes sustainability topics in a more general context such as in view of social and economical questions. We have a data science, machine learning and modeling approach to our problems. A special methodological focus is on modeling with discrete systems such as cellular automata and on deep learning methods.
Predictive Analytics for Hospital Supply Chain Management
Preliminary/feasibility study for a comprehensive AI-based solution in hospitals for demand-oriented assortment and efficient inventory Management ordering with a focus on security of supply and cost Efficiency planning of reprocessing planning of personnel deployment cost and income planning ...
Detection of drone signals
Prototypes for the Sustainable Digitisation of University Teaching
The COVID-19 Pandemy has forced higher education into fast forwarding their digitisation across the board. This creates valuable and relevant information for the sustainable digitization beyond the crisis mode. The project structures evidence-based digital teaching exsperiences and digital competences at the ...
Food Waste Indicators and Data Monitoring Concept
The Sustainable Development Goals require halving food waste by 2030. The goal of this project is to develop indicators and a data monitoring concept for food waste in Switzerland. The goal is to measure food waste amounts annd environmental impacts periodically in order to evaluate if the reduction target is being ...
PiaBreed: Machine Learning for automated ovulation and birth monitoring in horses
The project comprises the tasks of a comprehensive data collection (Piavita/ University of Bern) and the development of a mobile, non-invasive system (Piavita/ZHAW) for veterinarians and breeders. The goal is to collect important vital data and to develop a new algorithm scheme with which - ovulation in mares can ...
Braschler, Martin; Stadelmann, Thilo; Stockinger, Kurt, eds.,
Applied data science : lessons learned for the data-driven business.
Available from: https://doi.org/10.1007/978-3-030-11821-1_20
Frontiers in Artificial Intelligence.
Available from: https://doi.org/10.3389/frai.2019.00020
The 26th Nonlinear Dynamics of Electronic Systems Conference, (NDES 2018), Acireale, 11-13 June 2018.
NDES 2018, 26th Nonlinear Dynamics of Electronic Systems Conference, Acireale, Italy, June, 11-13 2018.
Uwate, Yoko; Ott, Thomas; Nishio, Yoshifumi,
IEEE International Symposium on Circuits and Systems (ISCAS).
EEE International Symposium on Circuits and Systems (ISCAS), Florenz, Italy, 27-30 May 2018.
Available from: https://doi.org/10.1109/ISCAS.2018.8351665