All projects from the School of Engineering
-
Accessible Teaching in Higher Education
The project aims to improve the accessibility of teaching at Swiss universities and to guarantee it in the long term. One of the main problems is the lack of awareness among responsible faculty and staff of the diversity needs of their students, which is why the development of an online training and short films to ...
-
Accessible digital map and navigation for pedestrians with disabilities
The aim of this research is to develop concepts for accessible urban trip-planning and navigation for pedestrians with visual and mobility impairments, and to implement two proof-of-concept mobile application for accessible trip-planning and map exploration.
-
Automatic Data Selection for Machine Learning based Anomaly Detection
We develop and test a novel method for a fully unsupervised selection of appropriate training data for anomaly detection using machine learning methods.
-
Ecological and economic process optimization in cement production through machine learning
The goal of this Industry 4.0 project is to stabilize and optimize the clinker burning process in a cement plant using machine learning and improved process analytics. This significantly reduces emissions of carbon dioxide, ammonia and nitrogen oxides, improves clinker quality and reduces the consumption of thermal ...
-
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
-
Good practices for responsible development of AI-based applications in healthcare
This project will identify proven methods, practices and standards that support responsible research and development of AI systems for health. They will be tested in use cases from medical imaging and neurotechnology, publicly released and published as a guideline of recommended best practices. ...
-
Intelligent Diagnostics of Performance Degradation in Solar Power Plants
A new software module for intelligent performance analytics and fault diagnosis for photovoltaic power plants will be developed and integrated in the existing Nispera platform. The service includes diagnosing prominent under-performance factors, allowing for a cost-effective maintenance planning. ...
-
Investigation of the Train driver productivity and job satisfaction
The complex, internal relationship between rail schedules and staff rotation is here addressed for a complete analysis of the current performance of train drivers. The potential for performance improvement in relation to the constraints imposed by the timetable and the corresponding shift plans (e.g., use of buffer ...
-
Laboratory 4.0 – Digitization in applied materials research
Whereas digitization has penetrated the business world and thanks to the smartphone our every-day life, students and researchers starting in a lab receive a paper notebook with their lab coat. On the one hand, this might look outdated, on the other hand, one might ask the question whether digital assistance is ...
-
Machine Learning for Software User Interface Testing
In this project, various technical aspects for tracing functional/non-functional requirements within user interface test cases were investigated. Originally, this project aimed to detect bugs in user interfaces automatically by using machine learning algorithms. During the execution of the project, we decided to ...
-
Novel high-speed, low latency distributed data link for precision measurement systems in demanding environments
SPECS Zurich GmbH provides measurement systems for scanning probe microscopy and quantum transport applications. During this project, a new plug&play-capable high- speed serial interface with ultra low latency and optical transmission shall be developed, such that it can be used in demanding environments such as ...
-
Pilot study machine learning for injection molding processes
Researchers from the CAI and InES conduct a technical deep dive together to explore the possibilities of capturing process knowledge on injection molding in deep neural networks and transfer the results to novel usage scenarios.The groups of Prof. Stadelmann (Computer Vision, Perception & Cognition, ZHAW CAI) and ...
-
Square Kilometre Array: Mock-observations via generative deep learning
In this project we use generative deep learning methods (GANs and VAEs) to produce realistic astronomical mock-observations of numerically simulated astrophysical objects, as they will be obseved by the Square Kilometre Array Telescope (SKA). This project contributes to the Swiss-wide activities for SKA of the SKACH ...
-
Target Recognition using Artificial Intelligence (TRAI)
-
Win.Lab – Strategierevision des Reallabors der Stadt Winterthur
Winterthur wants to remain a progressive and efficient city in which infrastructures are closely networked with modern technologies and urban stakeholders - a Smart City (SC). To this end, the city council adopted the strategy on 14.3.2018, defined the programme organisation and decided to create a specialist unit. ...
-
Optimization of powder preparation in 3D printing using Laser Powder Bed Fusion
Optimization of powder preparation in 3D printing using Laser Powder Bed Fusion (PBFLB/ P)
-
Malicious node for the detection of lateral movement
-
Machine Learning Enhanced Process Simulation in Laser Powder Bed Fusion (LPBF)
The project aims to develop and implement dedicated calibration procedures and parts that are tailored to critical applications of ABB and Sauber, to improve the accuracy of distortion predictions for specific components. Machine learning is then used to enhance simulations also beyond the calibrated regime. This ...
-
ThermoPlaner3D
The decarbonisation of heating systems is a big challenge for the building economy. The project ThermoPlaner3D develops novel innovative products that allow energy suppliers to support the energy change in buildings in a profitable manner. ThermoPlaner3D provides detailed 3D building energy assessments over large ...
-
Novel manufacturing process for tools for the production of implants
-
Enhanced blood flow and pressure measurements with PhysioCath-microcatheter for reliable diagnosis of 'Ischemia with Non-Obstructive Coronary Artery' (INOCA)
The project aims to develop the next generation microcatheter for the full physiological study of epicardial and microvascular diseases, including vasomotion disorders. This will allow a more accurate and reliable diagnosis of currently 130 million patients suffering from angina pectoris. ...
-
GraphQueryML – Using Machine Learning to Optimize Queries in Graph Databases (SNSF/DFG)
Optimizing the brain of databases with machine learning:Query optimization is one of the hardest problems of database systems research. A query optimizer can be considered as the “brain” of the system that makes sure that queries are executed efficiently. Even after several decades of research, many sub-problems of ...
-
IR-cell for inline-monitoring of extractions with supercritical CO2
-
Machine Learning-Aided Startup Investing (MALASI)
-
Digital Services from the Building Cloud
This preliminary study shows how the spatial linking of IoT data can be realized in the three-dimensional building plan and how new insights into the building operating status can be gained using BIM metadata. Further research questions: How can, based on physical simulations, missing or faulty measurement data can ...