The ever-increasing integration of renewable energy sources within modern power systems has significant benefits from the economic and environmental point of view, but poses also some technological challenges that shall be addressed to guarantee a safe and continuous service. Distributed energy resources are ...

The proposed scientific exchange with the Oslo Metropolitan University in Norway addresses  the protection of sensitive elements against stress waves through designing smart wave guides and phononic cloaks using metamaterials.

The goal of this project is to lay the technological foundations for empowering various stakeholders to make fact-based decisions to achieve sustainable consumption and production. In particular, we will evaluate how various data science, machine learning and artificial intelligence methods can be used to extract ...

By optimizing production in the textile industry, digitalization can help to reduce power consumption and thus, emissionsof pollutants. Yet, digitalization itself creates emissions, e.g., by using powerful AI algorithms. There is currently no transparency for how digitalization investments can reduce emissions. The ...

The PRISM project focuses on detecting radicalization events in Social Media networks. Overall, we are interested in unveiling the mechanics that lead to the event of extremist ideology being transferred and incorporated into a social media user’s world view. Specifically, the proposed project aims to identify ...

The project enables a novel, combined, adaptive cancer therapy combining tumor treating field and radiation therapy due to significantly improved static (3D) and time-resolved (4D) low dose Cone Beam Computer Tomography images based on artificial intelligence image reconstruction algorithms.  ...

The use of plastic gears in drives is growing rapidly, especially in the module size range 0.5 to 1.5 mm and at maximum load cycles during the product life of 105 to 106. A key factor for reliability is the tooth root strength of the gears. Although injection moulding, which is the common production method for ...

Clean, reliable data is crucial to an increasingly digitized financial industry. We currently observe a lack of consistent, high-quality data across asset classes which requires costly and time-intensive human intervention. We propose an AI-driven solution to address this issue.

Current PdM approaches need large datasets, complex modelling and many sensors which do not scale to machines with little or no historical data. MaintAIn offers a new approach without prior data collection, as few sensors as possible and as simple analytical models as possible.

Raman spectroscopy is an established measurement method in process and quality control. One of the major challenges in achieving good signal-to-noise ratios due to the weakness of the Raman signal. Since the effective cross-section is very small, interfering signals (such as stray light and interference from ...

Monitoring diverse sensor signals of patients in intensive care can be key to detect potentially fatal emergencies. But in order to perform the monitoring automatically, the monitoring system has to know what is currently happening to the patient: if the patient is for example currently being moved by medical staff, ...

Feasibility testing of a wearable Bilirubin sensor.

Buildings are a major source of Swiss CO2 emission, and the existing stock will represent the overwhelming part of the sectorial energy demand for yet several decades to come. Challenges to massive and efficient retrofit are numerous, multifaceted, interrelated and transdisciplinary, from scientific as well as ...

To address the emerging threat of climate change, consumers must transition to sustainable transportation. The electrification of the transport sector through e-mobility poses new challenges and uncertainties for grid operators. Without efficient prior measures, grid development problems will inevitably arise, ...

A multi-imaging setup is developed for investigating lab-scale solar cells and for obtaining spatially resolved information about the cell quality. Machine learning is used to estimate parameters for a physical FEM model that serves as a digital twin for further optimization.

Children born without hands or fingers and children who were victims of accidents in which they lost fingers or hands are the focus of our project. The goal of this work is to give them better fingers at a lower cost. The disadvantages of traditional designs are the high cost, weight, high forces to hold objects, ...