Objectives of the project: Establish a systematic dialogue between the technology developers and researchers and the elderly/healthcare institution stakeholders (including medical, care, and service personnel, management, patients, and their families) in both regions and develop a suitable international community ...

We are developing a cutting-edge Deep Learning model tailored to efficiently classify Orthoptera (grasshoppers) sounds captured by smartphones in outdoor settings. This advancement promisesrapid and sustainable biodiversity monitoring through citizen science initiatives.

Automation in dynamic environments - in agriculture, healthcare, or small-scale production - is limited. Rigid industrial robots fail in these complex environments. The key towards more flexible, adaptive, and safe automation is better perception. Robots need to assess their environment visually fast enough to track ...

Utilizing AI for the classification of insect sounds, particularly those of grasshoppers, is a promising method to monitor biodiversity non-invasively in the field. Our project focuses on the development and implementation of a sustainable TinyML model. This model aims to efficiently classify grasshopper species ...

Clinical physicians spend about 40% of their work time for reading and writing patient documentation. We will employ NLP, SNOMED CT, and Large Language Models (LLM) to generate concise, accurate, and interoperable summaries of patients’ records, thus saving time, effort, and resources.    ...

Boosting the Development of Plant Cell Cultures with Deep Learning Through Literature Mining.

Manufacturers struggle to provide customers context-and user-specific knowledge due to laborshortages and skill gaps in maintenance. Thus, an Autonomous Maintenance Service (AMS) will  leverage Large Language Models to systemize & provide manufacturers' existing expert knowledge as a service.  ...

In the Oasis project, we demonstrate how neuromorphic technology -- Intel's research chip Loihi 2’s -- can be used for assistive humanoid robot used in a smart city environment. Neuromorphic hardware and software  support development of applications featuring low-latency real-time sensory processing that ...

Planning, promotion and realisation of the 3rd ZHAW HealthTech Summer School according to the Stanford Biodesign innovation approach: 2.5 weeks in July with clinical immersions in three different medical application areas to develop disruptive Digital Health, DTx and MedTech solutions.

This Erasmus+ project aims to identify, develop and implement a new common methodology for the application of computational thinking (CT) in a variety of educational settings with a focus on teacher professionalisation and student empowerment. Special attention will be paid to inclusion criteria, special ...

We recently released "A Theory of Natural Intelligence", proposing a possible key to the emergence of intelligence in biological learners. Goal of this fellowship is to develop a technical implementation of the concept of self-organizing netfragments within contemporary deep artificial neural nets.  ...

The project aims at assessing the use of soil enzymatic activity to improve the use efficiency of nitrogen in agriculture to fulfill environmental goals and climate targets. We work together with ETH spin-off Digit Soil who already developed a device measuring on-site biological activity, an important soil process ...

Creation of a proof of concept for innovative analytics for aerospace compliance using machine learning.

Stroke DynamiX explores data-driven stroke management using machine-learning techniques in a consortium of statistics researchers, translational enablers, and clinical partners. We implement statistical tools to dynamically model stroke epidemiologically and predict real-time sepsis onset in the clinic.  ...