Projects
Institute of Computational Life Sciences
-
AI for colorectal cancer: towards the improved CMS classification and interpretability
Access to large complex biomedical data today allows scientists to take full advantage of AI-driven approaches in a variety of applications with high societal impact. One such application is precision medicine, which is gradually becoming reality for some cancers. Unfortunately, for colorectal cancer (CRC) ...
-
Investor and Stakeholder Tools for Tracking Companies’ Climate Commitments, Greenwashing and ESG Trends
In this project, we are developing science-based methods to systematically identify potential greenwashing in corporate communications as well as signals of green innovations and technologies. By applying advanced AI methods to thousands of stocks, we aim to develop novel, ESG-compliant financial products. ...
-
Feature Learning for Bayesian Inference
The goal of this project is to use interpretable Machine Learning (ML) to find low-dimensional features in high-dimensional noisy data generated by (i) stochastic models or (ii) real systems. In both cases, the problem is to disentangle the effect of high-dimensional disturbances, such as noise or unobserved inputs, ...
-
OSR4H – Open Set Recognition for Hematology
Development of a Proof of Concept for visual Open Set Recognition (OSR) algorithms applied to a Hematology task, the classification of white blood cells.
-
An experimental framework to allow evidence-based sustainability policymaking
This research project evaluates the feasibility of using a mathematical decision framework (based on the 2019 Nobel laureates in Economy who developed an experimental approach for improving policy in poverty through field experiments) in sustainability policy, and achieving a software-supported and data-driven ...
-
Drone Alarm
-
Food Chain Model for sustainable food chains and food waste prevention
The main product of this project includes five modules (toolboxes), which together form the Sustainable Food Chain Model (FCM) and enable the modeling of the environmental effects of entire food value chains. This makes it possible to model scenarios of value chains with their impact on the environment, which is ...
-
AWARE
The project AWARE aims to build a platform together with students and colleagues of the ICLS on the topics of sustainable studying in Wädenswil: everyday life design, use of resources, nutrition, housing and living. The contents of the platform are to be developed independently by students of the master course Food ...
-
Deep Brain Vessel Profiler
The architecture of the supplying brain blood vessels is believed to impact the occurrence and severity of common cerebrovascular diseases such as ischemic strokes or intracranial aneurysms. In this project, we study methods to efficiently quantify the variability in human cerebral vasculature and how this ...
-
Reinforcement Learning Analysis Framework
The aim of this project is to implement a framework that facilitates the development of RL solutions for real-world applications. This is necessary since the academic literature usually focuses on specific algorithms and approaches differ widely for different regions in the highly complex RL problem space. ...
-
Smart Hospital – Integrated Framework, Tools & Solutions (SHIFT)
-
AWACS – Animal Welfare Assessment and Control System for Fish Farms
Urban Blue offers software solutions for land-based aquaculture farms, which include technical and operational aspects. With this innovation project, fish-based aspects are developed to complete the software. This way Urban Blue can provide a comprehensive farm management system that incorporated fish health and ...
-
Optimizing plant health in indoor farming using reinforcement learning
The research question we tackle in this project is "How can we automatically optimize the growth path of indoor-farming plants?". To achieve this goal, we develop new algorithms to measure plant health and growth. We then evaluate reinforcement learning based approaches to optimize these metrics. ...
-
Transformer Networks for Drone Signals
-
Shapescience – AI for morpholigcally based fruit variety recognition
Pomological and molecular genetic methods have been the tools of choice to describe fruit varieties and their characteristics. Thanks to the possibility of using 3D scanning technology and machine learning, there is a revival of phenotyping, i.e. the typification of fruits based on their appearance. The Shapescience ...
-
Optimization of online education systems with reinforcement learning
The research question we tackle in this project is "Can we simultaneously increase student engagement and retainment by optimizing the order of exercises in online education courses?". To achieve this goal, we develop new algorithms to measure student engagement and retainment. We then evaluate reinforcement ...
-
Automated Release Testing System (ARTS)
Acthera Therapeutics AG and ZHAW propose to build an Automated Release Testing System(ARTS) for mechanotherapeutic drugs. The device is important for Acthera for testing new drugliposome formulations, controlling quality, keeping an edge over competition and collaborating with regulatory bodies. ...
-
Employing Natural Language Processing to identify inconsistencies in companies’ non-financial communication
NLP &ML tools for Swiss asset managers and owners for identifying inconsistencies in companies’ financial and non-financial communication
-
Simulation-based comparison of an end-to-end and a platform configuration for injection molding line
The project partner received two layout proposals for a new production line and wanted to compare them in terms of their suitability and performance. In the injection molding process, failure of individual injection molding cavities can occur, which leads to systematic or random missing parts. The system's modules ...
-
PE(K)O Sustain – Physically modified oils as sustainable alternative to tropical fats for the baking and sweet goods industry