The company's platform leverages public open data sources for marketing campaign optimisation. The effectiveness of such a campaign depends crucially on external factors such as political opinion, weather, surrounding demographics and even district-level trends. Research questions are: How can data sources be classified, and thus the integration be ...

In this project, LUCY - a system for phishing awareness training - will be significantly extended in order to put such training on a scientific basis and to bring it to a new level of quality. The goal is to provide completely automated, effective and individualized phishing awareness training with measurable training effect. The project will last ...

Docker has become the de-facto standard for containerised application delivery. Hundreds of companies in Switzerland develop, deploy and operate Docker-packaged software regularly, often involving publicly available Docker images produced by third parties. For banks, insurances and other companies with high compliance requirements, this poses a ...

Project DIR3CT aims at improving the image quality of CBCT images by deep learning (DL) the 3D reconstruction from X-ray images end-to-end. This enables a novel CBCT product to be used during radiation therapy and will allow the use of these images for adaptive treatment.

This demonstration shows to the participants the exciting possibilities of machine learning applied to speech, showcasing their benefits in various scenarios like helping regain the voices of the speech-impaired and improvement of dubbing technologies.  Also, crucially, it helps demonstrate the evergrowing threats through misuse of such technology ...

The main ambition of TAILOR is to build the capacity of providing the scientific foundations for Trustworthy AI in Europe by developing a network of research excellence centers with a technical focus on combining research excellence in the areas of learning, optimisation and reasoning . The current scientific landscape is fragmented with many ...

This project extends Exeon Analytics' ExeonTrace product with HostDetective Next Generation (HD.ng), a tool to identify and mitigate Web-related data breaches. HD.ng implements a novel active and passive Web server assessment method to determine the type, purpose and risk score of a Web server. This project builds on the results of the ...

Data growth and availability as well as data democratization have radically changed data exploration in the last 10 years. Many different data sets, generated by users, systems and sensors, are continuously being collected. These data sets contain information about scientific experiments, health, energy, education etc., and they are highly ...

INSPIRE-5Gplus aims to make a revolutionary shift in the 5G and Beyond (B5G) security vision by progressing 5G Security and by devising a smart, trustworthy and liability-aware 5G security platform for future connected systems, while contributing to its realization. It will allow, for the first time, the advancement of security vision for B5G ...

Applied research and development in the area of “Computer Vision, Machine Learning and Augmented Reality” to foster data-driven improvements for the cultivation of vineyards.

An IoT system consists of hundreds of thousands of sensors, connectivity media, cloud analytics, and users. Building such a large and complex IoT system such as smart-city requires careful planning, selection of the right set of hardware and software technology and development of scalable computing infrastructure and applications which can handle ...

ScorePad’s sheet music scanning service works for high quality input; to scale up business, it should work as well for smartphone pictures, used sheets etc. Project RealScore enhances the successful predecessor project by making deep learning adapt to unseen data through unsupervised learning.

Highly information-sensitive domains such as banking, healthcare and government services have been reluctant to adopt cloud and distributed computing technologies since their wide-spread commercial inception over the past 12 years. In contrast, many other sectors such as telecommunications and shops have embraced diverse cloud strategies and are ...

A novel approach for a fully automated food waste management solution for commercial kitchens is investigated. Food waste is automatically detected using a new camera device, preprocessed in real-time and classified using machine learning algorithms.

There is a huge amount of valuable information hidden in a company's database which is not easily accessible to business people. To query these databases, end users need to know the technical query language SQL as well as the database structure. However, typical end users do not have enough SQL skills to formulate complex queries. Even more so, ...

In this project, a virtual reality environment will be created to bring concepts around smart mobility closer to a broad audience. These concepts include smart sharing offers (and thus a change of mentality from owning to using), automated driving (which could reduce the number of vehicles in cities to one tenth within the framework of a shared ...

Development and teaching of a course on various aspects of secure software development and hacking methods.

Muscle loss is a concomitant of various diseases (cachexia) and the usual aging process (sarcopenia). Limiting this reduction and, ideally, even reversing it makes medical and economic sense. In medicine, the metabolic function (in addition to the pure movement) of the muscles is increasingly understood and recognized in their therapeutic ...

scanmeter® is a service of a Swiss company that has already been launched on the market (scanmeter.io). scanmeter allows automated security analyses of IT systems. This significantly increases the efficiency of security analyses compared to manual methods. The automated security analyses can be used on their own or in addition to manual tests. In ...