Projects

Inveel is developing large area sensory skins for robots. These skins are equipped with a vast array of sensors, has the potential to revolutionize the way robots perceive and interact with their environment. However, the challenge we face lies in managing the enormous amount of data generated by these sensors. A simplified data management strategy would allow us to offer more advanced and sophisticated robotic skins that provide real-time, actionable insights. This will make our products more attractive to industries requiring high precision and reliability, such as healthcare, manufacturing, and logistics. Reducing the complexity of data output and improving integration will streamline the hardware development process, lowering production costs and enabling faster time to-market. This efficiency gain will allow us to price our products more competitively, making them accessible to a broader customer base.

Duration: Oct 2024 – Nov 2024

Partners: Inveel and FHNW

We aim to develop an innovative mobile app that measures the active Range of Motion (ROM) of the cervical spine using the phone’s camera and advanced machine learning algorithms. This solution provides a non-invasive, sensor-free method to assess cervical spine mobility in patients with acute or chronic neck pain, typically measured by physiotherapists or medical doctors. Our goal is to enhance patient self-assessment and monitoring, enabling frequent and accurate data collection without the need for clinical supervision.

Duration: Sep 2024 – Nov 2024

Partners: SourceWay Sagl and SUPSI

Following the shaping work, we aim to launch the National AI Maturity Monitor to understand and anticipate how artificial intelligence applications and technologies can create value for businesses, society, and consumers. The outcome of this project seeks to educate both managerial and political stakeholders involved in investment decisions related to AI applications and technologies.

Duration: Sep 2024 – Dec 2024

Partners: sminds and ETHZ

The Frauenklinik at LUKS faces a growing challenge in efficiently handling and responding to patient inquiries. Most patient requests are directed through the telephone hotline, while email usage for inquiries remains relatively low. The hotline serves as the primary contact point for patients, especially for questions that are not purely administrative but often medically or organizationally complex. Currently, the clinic operates a digital assistant called “Lisa” chatbot, which is capable of handling only simple administrative tasks, such as providing basic information (e.g., clinic hours). The hotline itself is staffed by assistant doctors or, at times, senior physicians, who are already fully engaged in their clinical duties. Balancing their medical responsibilities with the additional task of responding to patient calls places a significant burden on these professionals. This dual workload interrupts their core medical duties, such as patient consultations, examinations, and surgeries, creating inefficiencies in their workflow.

The clinic thus faces the urgent need for a solution that can relieve physicians of these duties while ensuring prompt and accurate responses to patient inquiries.To address these challenges, the Frauenklinik plans to adopt an innovative solution using a digital assistant powered by Large Language Model (LLM) technology. The proposed system aims to act as a “Copilot” for medical practice assistants (MPAs) and will be implemented in a phased approach.

Duration: Sep 2024 – Dec 2024

Partners: Luzerner Kantonsspital, Eraneos and HSLU

With its cloud platform infra3D, iNovitas AG is providing city- to state-wide high-precision street-level imagery services across Europe. These services are used by numerous government agencies, engineering and transportation companies. Infra3D services allow to manage infrastructure assets, visualize and digitize geodata and have become an important part in the development towards smart cities and digital twins. The foundation of infra3D, the high-precision street-level imagery, has the potential to enable completely new applications. A revolutionary new application would be a universal and ubiquitous high-precision Visual Positioning Services (VPS). A VPS delivers position and orientation information at the accuracy level of the underlying reference imagery and could be used with any consumer device featuring a camera. Unlike GNSS-based positioning, which provides position information only and has a limited accuracy of a few to dozens of meters in urban areas, VPS operates in any environment and enables seamless transition between outdoor and indoor scenarios.

Duration: Sep 2024 – Nov 2024

Partners: iNovitas and FHNW

We are addressing the enhancement of human-robot interaction in healthcare settings, specifically using large language models (LLMs) to facilitate conversations and task management. A key area where this innovation can provide significant value is in the context of spontaneous transportation tasks in elderly care homes where robots have been deployed. These tasks are among the most critical, as they require the robot to respond promptly to real-time needs. For instance, a caregiver might need to quickly send a robot to transport an item or assist a resident without delay. Currently, the process of sending such orders is hindered by the limited physical buttons and interfaces on the robot, making it cumbersome for caregivers to interact with the robot efficiently. By using LLM-powered voice interaction, we enable the robot to understand and execute oral orders given by caregivers on the spot. This allows for a more natural and intuitive interaction, significantly improving the ease of use, acceptability, and effectiveness of the robots in these settings.

Duration: Sep 2024 – Nov 2024

Partners: FP Robotics and Idiap Research Institute

Existing RAI frameworks typically define broad ethical principles like fairness, transparency, and accountability but fall short in providing practical tools and procedures for effective implementation in business contexts. This gap leaves companies struggling to put these principles into practice and consultancies trying to interpret multiple high-level frameworks without clear direction. The project aims at getting a clearer understanding of the needs of clients and consultancies and laying the ground for developing practical solutions addressing their pains and gains in implementing RAI.

Duration: Aug 2024 – Okt 2024

Partners: UZH, FHGR, SBB, Unit8, EY, AIEthica and Modulos

The project, centred around the creation of a digital simulation tool for actual rail construction and maintenance sites, aims to create a new standard for railway sites by focusing on the environmental impact of construction practices, particularly the CO2 footprint. As articulated in stakeholder feedback, there is a pressing industry need to evaluate construction methods not only on cost, time, and feasibility but also on climate change. The project will create an additional criterion for evaluating construction measures that motivates construction companies to pay more attention to their environmental footprint, in terms of fleet choices, direct construction activities, as well as supply-chain, and provides railway operators with a transparent tool to achieve and demonstrate their sustainability goals.

Duration: Aug 2024 – Nov 2024

Partners: Rhomberg Sersa and HSLU

Ferag AG is developing intralogistics systems to sort and buffer products that belong to an order in a warehouse, called a pouch sorter. To control such a system, reinforcement learning could be used to dynamically manage resources, enabling it to adapt to fluctuations in demand and reduce bottlenecks. This adaptive control strategy would allow the pouch sorter to achieve cost-effective operation and setup without the need for cumbersome customer-specific control strategies

Duration: Aug 2024 – Nov 2024

Partners: Ferag and CSEM

Cardiac rehabilitation is a long and challenging process. Many patients lose  confidence, leading to decreased physical activity, anxiety, and inconsistent adherence to the recovery program. As a result, patients are at risk of another cardiac event. Carity aims to improve cardiac rehabilitation outcomes with a blended therapy approach. This approach combines in-person patient-provider collaboration with smartphone-based patient support and monitoring. Carity and many digital  health startups are navigating two worlds simultaneously: 1) the slower-paced, rigorous world of clinical studies and 2) the fast-paced world of software development. Deciding on a strategy that combines the two worlds is a crucial endeavor. Hybrid effectiveness-implementation trials are an innovative concept that can address both challenges in a cost-effective manner to allow Carity to remain in a reimbursement scheme once authorized and can further develop its product to  increase its effectiveness and usability. This project aims to adapt the concept of hybrid effectiveness-implementation trials to the specific case of Carity.

Duration: Aug 2024 – Sep 2024

Partners: Carity and HSLU

The goal of this research is to develop an automated system for extracting and structuring data from PubMed papers using a Large Language Model. The aim is to create a database that compiles medical records—such as studies on diseases, drugs, therapies, medical groups, and their outcomes—in a structured format suitable e.g. for meta-analyses. This system leverages the advanced capabilities of LLMs, including zero-shot classification and prompt engineering, to automate the extraction process without requiring extensive fine-tuning or domain-specific training data. The ultimate objective is to enhance the efficiency of biomedical research and clinical decision-making by providing a centralized and accessible resource for researchers, clinicians, and the pharmaceutical industry, thus facilitating more robust meta-analyses and accelerating the development of new medical treatments and therapies.

Duration: Aug 2024 – Dez 2024

Partners: Bellevue Medical Group, OST and rewoso

Heating systems in buildings should be continuously optimised to account for changes in the environment, changes in occupancy, or changes of the system itself. There are substantial and proven benefits of doing so. Owners are willing to pay between 400 and 1’500 francs per year for mid-sized buildings. This includes almost 500’000 multi-family homes in Switzerland. Why aren’t we seeing operational energy optimisations performed at scale? Many different partners are involved in planning and installing a heating system, where each partner specializes in their skills and competencies. We need the same skills and competencies to provide the continuous optimisation of the operation of heating systems. The Shaping aims at defining the requirements for a comprehensive service model through interviews with various customers and providers in this ecosystem, and documenting the state-of-the-art. This will help us quickly assess the desirability of such a service.

Duration: Jul 2024 – Nov 2024

Partners: Plutinsus and HSLU

LMVZ’s portfolio is aimed at primary and secondary teachers and pupils in Swiss German and Italian speaking cantons. The development of teaching materials is complex, while the need for teaching support is increasing. Advances in artificial intelligence offer new opportunities and risks for the creation and use of teaching materials, which significantly influences the core business of the LMVZ. While there are big innovations happening in second and third level education (i.e. Berufsbildung, Matura, and university) primary school teaching is still very hands-on and analogue and is expected to remain like this. The aim is to achieve a good balance between analogue and digital use. Nevertheless, AI has great potential in the creation process of teaching materials as well as in generic, reusable AI-extensions tightly connected to the teaching materials of LMVZ. In this regard, AI can lead to innovative incremental improvements.

Duration: Jul 2024 – Nov 2024

Partners: Lehrmittelverlag Zürich, FHGR and adesso

Das Ziel unserer Innovation ist es, mithilfe fortschrittlicher künstlicher Intelligenz (KI) frühzeitig Krankheiten bei Haustieren und Nutztieren zu erkennen. Durch die Analyse von Foto- und Videomaterial sowie der Auswertung von Sensordaten können wir Anomalien in der Gesundheit der Tiere identifizieren, bevor diese für den Besitzer sichtbar werden. Dies ermöglicht eine frühzeitige Intervention, reduziert das Tierleid und senkt die Tierarztkosten für die Besitzer. Unser langfristiges Ziel ist es, die Lebensqualität von Haus- und Nutztieren zu verbessern und ihren Besitzern ein höheres Mass an Sicherheit und Ruhe zu bieten. Derzeit gibt es nur wenige Technologien, die es Tierhaltern ermöglichen, gesundheitliche Probleme frühzeitig zu erkennen. Diese sind dazu oft sperrig, teuer und schwer zu bedienen. Eine nahtlose Integration von KI-gestützter Bild- und Videoerkennung und Sensorik in bestehende Infrastrukturen und Routinen könnte hier eine entscheidende Lücke schliessen.

Duration: Jul 2024 – Aug 2024

Partners: AI-Tails and Renuo AG

An increasing number of Swiss SMEs seek to measure, control, and transparently report their sustainability performance. The dynamic development of EU regulations and Swiss law, which potentially impact Swiss companies, leads to increased clarification needs and reporting requirements. While larger companies might possess the necessary resources, Swiss SMEs face the challenge of efficiently measuring sustainability within their operations / supply chains and determining which standards, frameworks, or principles to follow for sustainability reporting. The goal of the innovation project is to develop together with Abacus Research AG an integrated and largely automated IT tool – the “Sustainability Management Navigator” – that enables Swiss SMEs to efficiently measure, assess and report on sustainability. The tool aims to align with recognized standards (e.g. FER guidelines, GRI- or ESR-Standard) and accommodate varying regulatory requirements across companies, providing scalable content tailored to the needs of SMEs, including industry-specific adaptations and potential full coverage up to a comprehensive report.

Duration: Jul 2024 – Nov 2024

Partners: OST and Abacus Research

LaGrand GmbH leverages methodologies from the publication form Zohu2018 to monitor over 900 steel mills globally, which account for about 98% of the worldwide steel production. Multinational companies like Zehnder, which purchase steel, often face challenges due to a lack of information of global and regional market situations. Their reliance on data is primarily through indices like PMI, derived from frequent interviews that may not accurately reflect the current market state. The major drawbacks include the low frequency of updates and the potential for inaccuracies due to misrepresented facts in the interviews. Steel purchasers would benefit from an index independent of interviews because the reduced risk of misrepresented facts could lead to less volatile and more fairly assessed steel prices, leading to greater planning security. This could be reflected in reduced purchasing and inventory costs, which would directly impact the profits of our customers. With the successful completion of this project industrial companies as Zehnder and other would profit with a new service from space in their procurement.

Duration: Jun 2024 – Sep 2024

Partners: Zehnder, LaGrand and CSEM

Smilamind aims to develop an evidence-based digital mental care solution through the use of a companion app, that allows to provide the right type of help for the right child or adolescent, at the right moment. It can cover several innovation gaps in mental health care like scalability of care, continuous support, data-driven personalization and early detection. 

Duration: Jun 2024 – Sep 2024

Partners: Smilamind, SUPSI and ZHAW

The overarching goal is to work out with the industry partners what a digital solution should look like to capture, measure and monitor the relevant success-oriented compliance-related key performance indicators (CKPIs). In a collaborative effort we wanted to gather input from all our industry partners. We have seen a strong interest from compliance professionals from different industries to participate in the Shaping Workshop to clarify the requirements and expectations of the planned Innosuisse project to develop such a CKPI-centered digital tool. Now we had the opportunity to collect the valuable input from our project partners to further shape our very promising project idea. Having successfully modeled the relationships between the factors of effective compliance, compliance efficiency and business success, we were able to rely on a reliable statistical model to discuss the pains and gains of such an outcome-oriented CKPI monitoring tool.

Duration: Jun 2024 – Sep 2024

Partners: HSLU, Axpo, FHGR and Tecan Group

The goal of the Digital Medication Box is to make medication intake safer, easier and more efficient for patients. By integrating digital technologies, we aim to ensure that patients take their medication at the right time and in the right dosage. This is not only intended to increase treatment adherence, but also to reduce the risk of intake errors and improve the overall well-being of patients. The digital medication box is intended to relieve patients, relatives and caregivers by automating the management and monitoring of medication intake.

Duration: Jun 2024 – Aug 2024

Partners: ein-fach and FHNW

In-GeoForge aims to improve geospatial data analysis by integrating Geospatial and Generative AI to provide near real-time geospatial insights for the insurance industry. Initially, we focused on the authorities, government, and NGO sectors. However, to achieve greater scalability and impact, we are now tailoring our solution specifically for the insurance industry. To accomplish this, we have to meet the unique needs of this sector, ensuring it can address the challenges faced by insurance companies. The goal is to develop a feasibility study and proof of concept for leveraging GeoForge in remote inspection, impact assessment, and incident management use cases.

Duration: Jun 2024 – Sep 2024

Partners: Ageospatial and University of Geneva

The primary goal of our innovation was to harness the potential of modern VR technologies to enhance therapeutic treatment for adolescents and young adults with borderline personality disorder (BPD). Specifically, we aimed to explore VR’s applicability within psychiatric therapy, focusing on both its practical implementation and its potential to transform traditional approaches for BPD. Our project results reveal strong opportunities to enhance and scale VR-based therapeutic approaches. Within the clinical environment, VR therapy allows patients to continue therapeutic exercises independently in their rooms, reinforcing skills practiced in sessions. At later stages, VR devices could also be provided for follow-up care, enabling patients to maintain a connection with the clinic via a dedicated platform that integrates data from VR session activities. This approach addresses the growing disparity between available therapeutic staff and the rising demand for treatment by offering continuous support.

Duration: May 2024 – Sep 2024

Partners: Privatklinik Meiringen and OST

Our idea is to create an AI-driven assistant for legal contract negotiations, reducing inefficiencies and improving accuracy by leveraging data libraries of common law, law firms’ best practices, and end customers’ standards. The problem is relevant because current contract negotiations are time-consuming and inefficient. Lawyers often spend significant time on details, creating a back-and-forth “ping pong” dynamic. This inefficiency reduces scalability and hinders the services provided by law firms. Small firms, in particular, must hire additional workforce to manage personal bottlenecks, further straining resources. A more efficient solution is needed to streamline contract negotiations, improve scalability, and better utilize lawyers’ expertise and time.

Duration: May 2024 – Jul 2024

Partners: Connect AI, CG Innovation, Codelaw, Digital Republic Solutions and FHNW

Sewer survey and cleaning companies used robot and other devices to inspect pipes and sewages. The video is reviewed in a traditional, legacy windows-based software whereby incidents are manually logged and documented. The goal of the innovation project is to implement deep learning AI models to detect, log and qualify the incidents so that a report with all geo-localised occurrences can be created right after the inspection. An AI model will work with any type of video footage captured from industrial grade robot or drone.

Duration: Apr 2024 – Aug 2024

Partners: PrecisionFly and Yololab

REGDATA’s existing data protection platform, RegData Protection Suite (RPS), is designed to protect confidential and personal data. However, this platform faces limitations when it comes to protecting sensitive information within unstructured data. Consequently, there is a pressing need to develop a solution that can dynamically identify to anonymise this type of data. Our project leverages cutting-edge Named Entity Recognition (NER) technology to detect sensitive information within unstructured data automatically. This enables the secure transmission of protected data to Large Language Models and cloud databases. This ensures that sensitive information is never exposed or mishandled. In a previous innosuisse project , the academic partner has applied NER to enhance data accessibility in the crop commodity Sector. This experience underpins our approach, enabling the secure and efficient handling of sensitive data.

Duration: Apr 2024 – Nov 2024

Partners: REGDATA and HES-SO

The innovative optical computer design proposed by OptoPC is specifically crafted for arithmetic computations and matrix manipulations, leveraging light as the medium for information processing. This approach utilizes Spatial Light Modulators (SLMs) for phase shifting and integrated detectors for result analysis, enabling massive parallel computing and efficient matrix-to-vector operations while maintaining low power consumption. Currently, no optical processors are commercially available, as the technology remains in the research phase.

Duration: Apr 2024 – Nov 2024

Partners: OptoPC and SUPSI

Future Food Solutions is pioneering the development of an online marketplace specifically designed for sourcing sustainable raw materials in the food industry. Currently, the industry relies heavily on analog interactions between suppliers and buyers, with no digitized solution to streamline the sourcing and procurement processes. Our platform revolutionizes this by providing manufacturers direct access to the full market, eliminating the need for intermediaries and significantly reducing the resources required to identify suitable ingredients. Future Food Solutions is poised to transform the industry by making the procurement of raw materials more efficient, transparent, and accessible.

Duration: Apr 2024 – Aug 2024

Partners: Future Food Solutions and ZHAW

Our innovation idea aims to create a planification tool platform that helps wheelchair users to plan ahead their trips in Switzerland. Currently, there are platforms that propose accessible activities but none are taking into consideration yet how to reach this place. Our goal is to offer a tool that proposes accessible itineraries according to the user’s mobility constraints.

Duration: Mar 2024 – Nov 2024

Partners: Slowlution and HES-SO

Kistler’s objective is to create a new product for bridge Structural Health Monitoring (SHM) that enhances maintenance schedules, boosts bridge reliability, and ensures safety. The herein funded project supports this objective by developing a cutting-edge machine learning algorithm for damage detection in operating bridges. In particular, it addresses the complexity of modern monitoring systems. These comprise sensors with diverse modalities generating large volumes of heterogeneous data with complex relations, making it cumbersome to process and extract the relevant information.

Duration: Mar 2024 – Aug 2024

Partners: Kistler and EPFL

QOYO was initially founded and launched as a platform that allows SMEs in Switzerland to conveniently create a marketing strategy for their business – completely for free. If they wanted to, they could then get help in realising the strategy from professionals, which is where the monetization would kick in. However that business model did fail to prove itself profitable and we started to get back to the drawing board. With the help of the Databooster we built a concept for an online buying advisor as a blueprint that would be applicable in many industries rather than just for online marketing strategies.

Duration: Dec 2023 – May 2024

Partners: QOYO, HSLU and ZHAW

To survive and grow, SMEs need to harness the power of AI but struggle to implement it (costs, expertise, incompatibility with used system, data management, data privacy). The most critical issue is how to manage increasing amounts of data, while guaranteeing the security and availability of this data while the existing solutions are costly, complex to use and do not allow easy scalability. By adding ANTS to the existing system, it will grow automatically, without any human intervention. It will deploy business applications and on premise cloud solutions. It is fully automated, takes care of its own maintenance and offers a built-in assistant that will learn from company data and process answers on premise.

Duration: Dec 2023 – Aug 2024

Partners: ANTS and HES-SO

Based on processing and analytics of data accrued along specific supply chains, the actors contributing to the chain shall be aligned and synchronized with the goal to optimize the utilization of resources (energy or material) and maximize the economic output against this background. This is achieved by collecting the relevant data in a platform-based approach and analyzing and interpreting it by advanced analytics in close co-creation of the supply chain actors. The methodology will be elaborated at given supply chain case together with the involved companies and will then be generalized to a replicable design approach that can be used by consultancies of a multitude of their future projects.

Duration: Nov 2023 – Dec 2023

Partners: Staufen.Inova, artificialy and ZHAW

Proper nursing documentation is essential in long-term care facilities. It provides information about the details of the care provided each day, the medication, safety requirements, allergies and diagnoses. However it is time-consuming, taking up to 30% of working hours, error prone and many nurses perceive it as a burden. To accelerate the process and make work easier, a speech recognition software for capturing information in real-time, converting it into text and generating summaries with the help of a chatbot powered by a large language model is being developed.

Duration: Nov 2023 – Jan 2024

Partners: Curaviva, Pflegeheim Sonnhalden and OST

In order to achieve compliance with artificial intelligence regulations for global corporations, we strive to enable these organizations to evaluate their data quality and the trustworthiness of their AI models, with a focus on the upcoming EU AI Act requirements. Currently there is no clarity on how this can be done in a way to not only evaluate biases, but also taking efficient and effective measures to mitigate them. We foresee to design a software platform that encapsulates a holistic framework to deal with data quality and algorithmic fairness.

Duration: Oct 2023 – Nov 2023

Partners: Modulus and ZHAW

SkyScan aimed at detecting objects from aerial platforms (drones or other embedded systems) by scanning the sky for objects with constrained data resources. The objective of this project is to enhance machine vision of pilot assistant computers for air and land vehicles. These systems are collecting, visualizing, and analyzing information related to the surrounding environment in real-time to facilitate surveillance, safety, and increasing autonomous operations operational effectiveness.

Duration: Sep 2023 – Aug 2024

Partners: Elix Systems and HES-SO

The operation of thermal solar panels (TSP) is an issue because they are often not properly maintained. The deterioration of the installation is not apparent to the owner as TSP is only a supporting system. In fact, domestic hot water is still available, but the required heating energy rises because the inflow of (cold) water is not pre-heated by the solar system. The idea is to install a low cost sensor-based system and define a business case around condition based maintenance.

Duration: Sep 2023 – Dec 2023

Partners: SG Energies, HSLU and ZHAW

Forbo manufactures homogenous vinyl tiles derived from the additives present in the stamped raw material mix. Therefore even if the textures share the same dimensions, they are still always different. Currently the inspection is made in-line by an operator that checks the tiles passing under special lights, a process which is prone to leaving unspotted defects. Quality control automation is key to enhance manufacturing efficiency and reliability, but the type and features of the tiles are very difficult to spot with current solutions. In this Deep Dive we aim to get a fully automated quality control on our production lines, allowing us to strongly reduce unspotted defects.

Duration: Sep 2023 – Dec 2023

Partners: Forbo, Artificialy and SUPSI

Lack of time is omnipresent in healthcare. Doctors, physiotherapists and sport scientists seem overwhelmed with their current schedules. They do not have the capacity to implement novel solutions in their practices or clinics. Testing and rollout of digital therapy tools like Carity in rehabilitation centres can be challenging. For healthcare providers every opportunity to increase the services and reduce time spent is vital. Charity provides a data-supported workflow template that can assess the effectiveness of remote-patient monitoring and as a result make it easier to introduce new products to existing services.

Duration: Sep 2023 – Okt 2023

Partners: Carity and HSLU

Industrial companies use ineffective training methods and have difficulty managing the codification, creation and sharing of knowledge among their employees and subcontractors. “Tacit” knowledge acquired through years of experience and hands-on learning is difficult to document and share in a structured way, which can result in valuable knowledge being lost when experienced employees leave the company or retire – significantly impacting the profitability of many industries. Organizations, challenged to meet their skill-needs and individuals who need support in learning specific skills are the focus of our project, by using AI supported processes and tools to preserve knowledge and support innovative learning processes.

Duration: Aug 2023 – Dec 2023

Partners: edisconet and Florence University

The Building Information Modelling (BIM) process is gaining a foothold in the Swiss construction sector. However the stumbling block of the production of specifications remains, slowing the existing digital process and generating rework of documents and transcription errors. The project aims to develop an AI based tool supporting the conversion of construction projects into specifications compatible with current CRB standards according to the Catalogue of Normalized Positions (CPN).

Duration: Aug 2023 – Dec 2023

Partners: MTF Business Solutions and OST

Sitting in front of the screen in the correct positions and keeping minimum distance between your eyes and screen are crucial in staying healthy and avoiding developing short-sightedness. The problem is that a lot of people, especially children, don’t follow these rules. Intelec is developing a software which observes our sitting position and distance using an on-screen camera and notifies us if we do it wrong. This way the technology can help us build good screen habits and protect our health.

Duration: Aug 2023 – Apr 2024

Partner: Intelec and SUPSI

Heated tungsten filaments are used as thermal electron emitters in x-ray tubes. For open microfocus x-ray tubes, the filaments are especially heavily strained and replaceable due to a short lifetime. The goal of the project is assessing the possibility to predict the remaining useful life of filaments.

Duration: Jul 2023 – Nov 2023

Partners: Comet AG and ZHAW

Mobility as a Service (MaaS) wird momentan nur für Städte aufgebaut. Allerdings kämpfen auch ländliche touristische Regionen mit Verkehrs- und Umweltproblemen. Die offene Frage ist, wie die notwendigen Daten erfasst und an eine Verarbeitungszentrale weitergeleitet werden können. Über neue digitale Technologien und mobile Angebotsformen können die eigenen Fahrzeuge sukzessive reduziert und ersetzt werden. Für den Tourismus gilt, dass ein autofreier Urlaub gewährleistet werden kann und alle Destinationen mit dem öffentlichen Verkehr einfach, umweltfreundlich und komfortabel zu erreichen sind.

Duration: Jul 2023 – Aug 2023

Partners: Hunziker, OST, ZHAW, ASTRA and adesso

High-quality data on building products are central to the design of sustainable energy- and cost-efficient buildings. Today, this data has to be compiled  manually from a variety of sources by the individual players in a team, which leads to intransparency and inconsistency, redundant work and frustration. The OpenMaterialData project proposes an open data approach to address the problems of discoverability and usability of product data in the construction industry. This will be achieved by providing an open data environment that is aligned with regulatory demands and the information needs of software tools to facilitate the data exchange between data providers and data consumers.

Duration: Jun 2023 – Jul 2023

Partners: opensource.construction and SUPSI

In Modellen stehen neu Informationen von Materialien und Produkten direkt zur Verfügung. Alle Informationen dazu sowie die Umgebung des Einbauortes sind bekannt. Diese können zur Prüfung der Kompatibilität von am vorgesehenen Einsatzort verwendet werden und kann zukünftig auch mehrstufig erfolgen, indem die im Prozess entstandenen Prüfregeln Baustoffgruppen und -kategorien zugeordnet werden und eine automatisierte Qualitätsprüfung ermöglichen. Mit den Ergebnissen aus diesem Projekt soll ein neuer Standard mit dem Fokus modellbasierter Qualitätssicherung ermöglicht werden. Mit diesem Ansatz können bereits zu einem frühen Zeitpunkt Fehlplanungen eliminiert, bei der Auftragsvergabe valide Produkte ausgewählt und in der Bauausführung Fehlbestellungen vermieden werden.

Duration: Jun 2023 – Nov 2023

Partners: CRB, OST and ZHAW

Methanology develops a state-of-the-art power to liquid energy storage solution that enables the storage of renewable electricity into renewable e-methanol, thus reducing our dependence on fossil resources. A revolutionary process called “willpower energy” (WPE systems) transforms CO2 and water into e-methanol through an electro-biocatalytic reduction. This happens while specifically designed enzymes are located on selective electrodes that are electro-chemical controlled according to the demands of the process. The control algorithm and power delivery of this “enzyme-electrolysis” will have great impact on the performance, efficiency and lifespan of the enzymes. For this reason Methanology is developing a virtual model of the process and run a machine experiment on a digital twin using machine learning to optimise the system.

Duration: Jun 2023 – Feb 2024

Partners: Methanology and ZHAW

Trafag ist ein Sensorhersteller mit hoher selbstentwickelter technologischer Wertschöpfung. Die Anwendung von AI-Technologien hat ein grosses Potenzial, den Einsatz von Mitteln und Ressourcen zu optimieren und hochpräzise Sensoren mit heute nicht erreichbarer Lebensdauer in rauen Anwendungen zu entwickeln. Um ihre Ideen weiterzuentwickeln und zu schärfen, will Trafag mit diesem Projekt das offenliegende Potential nutzen, um seine Produkte noch stärker zu verbessern.

Duration: Jun 2023 – Jul 2023

Partners: Trafag and OST Rapperswil

The global polymer trading production has outgrown most other man-made materials. Of the seven billion tons of plastic waste generated so far, an estimated 10% were recycled, 14% were incinerated, while the remaining 76% are in landfills, dumps or the natural environment. Beyond the organizational aspects, the reuse potential for polymers is to a large degree an informational challenge. While this information is partially available to the recyclers, it does not find its way to the processors due to the lack of an information infrastructure and integrated data supply chains. The innovation challenge of developing such information infrastructure to increase the reuse of polymer materials is addressed through the vision of a Polymer Materials Data Cloud. This data cloud will become the backbone for the polymer trading supply chain with regards to material and quality data.

Duration: May 2023 – Sep 2023

Partners: Meraxis and BFH

Chronic tinnitus is the perception of a phantom sound in the absence of any physical source. Approximately 10-15% of the Swiss population suffer from it. In severe cases, the affected people suffer from sleep disorders, anxiety and depression. Tebokan® is a pharmaceutical product by the Schwabe Gruppe. A clinical study showed that the intake over a longer period of time leads to a significant reduction of tinnitus. The temporal dynamics of this health improvement over time however are completely unclear. The aim of this project is to model this process of health improvement over time, understand the process and optimize it.

Duration: Apr 2023 – Feb 2024

Partners: Schwabe Pharma and OST

Precision livestock farming allows the automatic monitoring of animal health and welfare. Its potential has been proven particularly in the dairy sector. Not so much attention has been paid to the digital monitoring of equine welfare, although the well-being of horses is of great concern to their owners and of public interest. The aim of this project is to implement digital technologies to automatically monitor equine welfare by applying multiple existing algorithms for equine remote monitoring in an integrated device.

Duration: Apr 2023 – Apr 2024

Partners: Agroscope and Identitas

The European aviation industry faces a persistent challenge in accommodating the growth of passenger numbers, as airports require increased space and resources to reduce waiting times and enhance the passenger experience. Conventional solutions such as developing new infrastructure are time-consuming and must allow for reactively addressing the mentioned challenge. In light of this opportunity, a deep-learning forecasting engine, known as Clouds™ is being developed as part of an OpenAOP (Airport Operational Plan) research project. The primary objective is to accurately forecast passenger flow at critical touchpoints using real-time and historical crowd flow data.

Duration: Mar 2023 – Sep 2023

Partners: Thinkgate and SUPSI

Unfortunately it is common in industrial operation and maintenance to quickly change parts and sub-systems, “fighting” appearing symptoms instead of analysing the real root cause, which requires an overall system overview and lots of experience. The aimed software development implements a highly innovative method for automated root cause analysis based on standard event logs from industrial assets and processes. This should support operators and maintainers in identifying the underlying problems and will therefore improve reliability by acting faster on process deviations and lower costs in maintaining failing assets.

Duration: Jan 2023 – Jun 2023

Partners: Scentech and CSEM

Young women often demonstrate lower self-esteem than men which has a detrimental impact on their wellbeing and psychological health. While there are many sources of information and programs to build self-esteem available on the market, most of them fail to reach out to young women in a meaningful way. With this project our team will develop a new solution to first improve women’s self-esteem and secondly to improve the user’s overall psychological wellbeing. The solution will take the form of a gamified and intelligent application which provides knowledge and strategies to cope with the major factors.

Duration: Jan 2023 – Jul 2023

Partners: Fireflai and University of Geneva

Conventional soil survey is time consuming and suffers from a large shortage of skilled staff. Soil sample logistics and preparation are laborious and prone to errors and subsequent laboratory measurements are costly. To alleviate these issues, solutions need to be developed to directly record the required data in the field. It has already been shown under laboratory conditions that spectral sensors can complement wet chemical analyses. Therefore the planned innovation project will optimize the image processing work flow to optimally match the requirements and evaluate the gain predictive accuracy by deep learning-based computer vision methods.

Duration: Jan 2023 – Jul 2023

Partners: bodenproben.ag, ZHAW and BFH

Auxiliary batteries are installed at each train but only rarely used. They are used for short time windows such as the start and end of each train operation and in emergencies. Due to strict regulations, it is seen as highly critical to ensure that battery capacities are in line with these requirements. This is traditionally ensured with extensive maintenance. Our objective is to develop an online state of health monitoring for these batteries in order to replace the present preventive maintenance approach by a condition-based maintenance (CBM) scheme.

Duration: Jan 2023 – Jul 2023

Partners: Stadler Services and ZHAW

Fluence Energy would like to offer a new software module for predictive maintenance of grid scale storage systems. To this end the company would like to use its domain knowledge about the physics of degradation and fault mechanism in batteries and combine it with advanced data analytical methods in order to achieve high performance automated detection of anomalies and risk factors on one hand, and to perform a continuous monitoring and prediction of remaining useful battery life on the other hand.

Duration: Jan 2023 – Jul 2023

Partners: Fluence Energy and ZHAW

It is a well known fact that most AI projects don’t make it to production. This is due to various risks associated with people, process and technology aspects of development and productization. Our goal is to create a new business process automation and optimization tool that helps organizations quantify, measure and manage value and risks associated with their data projects. Such a product does not yet exist although similar tools are commonly used in other business processes within organizations, e.g. financial and business automation. With our software solution companies can extract significantly more value from their data initiatives.

Duration: Dec 2022 – Mar 2023

Partners: Xurce, aibridge, ti&m, Artifact and ZHAW

The European job market is broken: While millions of young talents face unemployment in Southern Europe, there is a significant labor shortage facing many industries in Central and Northern Europe. At the same time obsolete recruiting practices bar talent with diversity backgrounds just because of their picture, gender, age or origin.

We believe that the market is ready for disruptive AI-based innovations to overcome the challenges that both sides of the market face.Thus we propose the Unbiased CV Check: A novel candidate focussed job opportunity discovery & matching architecture that leverages AI for multiple innovations. After improving the CV, which will then be checked against thousands of open job opportunities, it then offers the candidate the option to engage only with relevant companies and recruiters in an opt-in only approach. On the other hand, recruiters benefit from an an AI-based matching architecture that allows the fast identification of relevant candidates.

Duration: Dec 2022 – Jan 2023

Partners: Rockstar Recruiting AG and ETH Zurich

Availability of patient data collected through patients and doctors has increased significantly over the past decade. However consumers of said data do not yet exploit the full potential for converting this information into improved quality of care. The volume of data can be overwhelming for clinicians. Furthermore, many important data are generated by patients but are currently not leveraged in health care because they cannot be integrated into standard medical information systems and workflows. We propose to investigate what data selection paired with the right visualization design optimizes the quality of care. This new feature is the basis for the development of new versions of decision support platforms to be used for doctors and chronically ill patients during their clinical routine.

Duration: Dec 2022 – Mar 2023

Partners: rewoso and University of Zurich

The project aims to develop bikes with minimal embedded sensor technology in combination with advanced AI-based data prediction and processing. The technology is widely spread in the automotive industry but still lags behind significantly in the fast growing bicycle sector. This lets the bike predict real-world and live riding data and process them into valuable information for riders, brands, engineers and manufacturers. The technology stack will enable us to offer new products to the market and establish a complementary business model for the bike industry.

Duration: Dec 2022 – Feb 2023

Partners: Radiate Engineering, Scott Sports and ZHAW

According to organization science research, increasing market complexity requires greater technology-driven structural complexity to remain performant. Yet many practices are outdated and inefficient. Peerdom is a HR platform where organizations move beyond rigid charts towards flexible collaboration. By developing AI technology to assist human HR specialists, we can generate insights by using existing customer data and fed back to the customer. As the models improve over time with more data, the innovation will constantly grow in value for our customers.

Duration: Dec 2022 – Jan 2023

Partners: Peerdom and ZHAW

Maxon produces a couple thousand variants of motor, gearbox, cables and controllers. To plan investments into new products or to determine the adequate stock size, a rough estimation of the sales forecast is essential. Unfortunately only a share of the actual forecast can be allocated to the necessary production. Today’s forecast is driven by financial considerations rather than production requirements. With delivery times of more than 18 months the investment planning is getting very tricky. With the power of neural networks and historical data we plan to exploit this black box and uncover the potential of data analytics towards a production planning forecast.

Duration: Dec 2022 – Jan 2023

Partners: Maxon Group and CSEM

The normative requirements for traceability are becoming increasingly stringent for a foundry in the drinking water business. We sell our products worldwide, expanding in new countries with new regulations, while requirements in existing markets are increasing as well. Until now the traceability has been limited mainly to batch information and production data only. Especially in Nordic countries, due to the widespread use of timber construction, people are looking for systems with a high level of security but also sustainable and transparent. The recent introduction of the data matrix creates new possibilities towards digital traceability.

Duration: Dec 2022 – Jan 2023

Partners: Georg Fischer JRG AG and ZHAW

The separate companies in the BKW network cover services in the areas of energy, buildings and infrastructure. The goal of this initiative is to connect the three areas through the use of technology and data to improve existing services and discover new business models. After determining which combination of services in which phase of the cycle creates the most value for the provider, new services can be developed which will enable BKW to enter new markets on the basis of new and innovative services.

Duration: Dec 2022 – Jan 2023

Partners: BKW, endaprime and ZHAW

Agriculture commodities are mostly driven by supply shocks. Droughts are the most known weather event but floods, lack of snow coverage or hurricanes can also impact productivity drastically. Crop monitoring based on official statistics is often too late as statistics are often delayed by several months if not years whereas monitoring weather is not sufficient enough. To get predictions as accurately as possible, remote sensing is a must. With a combination of remote expertise, weather forecasts, historical data, crop masks and ground truth, our model will provide customers with much earlier and more precise information, allowing them to reduce exposure risks and anticipate market evolution.

Duration: Nov 2022 – Jan 2023

Partners: DNEXT, HES-SO and UniGE

Early detection of plant drought stress is crucial to minimize damage to the plant, yield loss and optimize water management. It is difficult to detect the onset of mild stress prior to any visual symptoms and commercially available sensors are poor substitutes for plant-specific information. With our solution it will be possible to perform real time predictions of drought stress in high value crops. There is no other algorithm on the market which has been trained from electrophysiological signals directly from the plant. This will allow us to provide customers with alerts on the status of their crops with plenty of lead time for them to manage irrigation.

Duration: Oct 2022 – Nov 2022

Partners: Vivent, FFHS and SUPSI

Media professionals, politicians, activists and the general public struggle with disinformation and fake news. Such information impacts opinion formation and ultimately decision-making as well. The scientific experts have technological and socio-psychological expertise to address the problem, but need a deeper understanding of how to tackle the practical side. With the development of a fake news detection algorithm that takes linguistic and cultural aspects of Switzerland into account, the potential dangers could be mitigated.

Duration: Oct 2022 – Nov 2022

Partners: Tamedia, NZZ, HSLU and ZHAW

As software and data are becoming the most valuable assets for many sectors, several Swiss organizations are struggling to maintain software development activities in Switzerland due to data secrecy and lack of scale which force the organizations to build their own local solutions. Swiss Digital Network (SDN) is a network of IT consulting and architecture entities, supporting customers in designing and building their “digital highway”. Their experts can already assist with a wide range of activities but need to consider and adopt a holistic approach which covers multiple automation use cases together. With this project opportunity, SDN can reach out to new segments in finance and public administration through their IT departments.

Duration: Oct 2022 – Dec 2022

Partners: SDN, HEPIA and ZHAW

Fitting orthopedic devices today takes up to ten weeks as it’s a manual process in artisan workshops. In some cases orthopedic devices are supplied too late so that symptoms already worsen or the product injures patients due to poor fitting. The goal of the project is to leverage AI and ML algorithms that can fit orthopedic products to the patients rapidly. If this proves to be doable then we could offer this intelligent fitting mechanism through an app or software module for clinicians right in their clinics.

Duration: Oct 2022 – Apr 2023

Partners: Leg&Airy Gmbh and ZHAW

cropled is developing a smart lighting system for the horticultural and vertical farming industry which is able to adapt characteristics such as its light spectrum to enhance the growth and various traits such as secondary components of plants. By understanding the ecosystem and the relationship between the actors, the value proposition to different actors can be improved and new value propositions that will enhance the business will be identified.

Duration: Oct 2022 – Nov 2022

Partners: cropled, CSEM, HSLU and ZHAW

The project aims at tackling the problem with an easy to use software implementation which is already available on demand. The solution helps to prevent waste, which corresponds directly to saving on material expenses. Since raw material is one of the driving cost factors, the potential is very high. The end customer will see a reduction in waste material as well as logistics operations for handling said material. Furthermore the algorithm is able to adapt to the specific customer or manufacturing needs.

Duration: Oct 2022 – Nov 2022, Jun 2023 – Jul 2023

Partners: Bystronic, CSEM and ZHAW

Facial recognition technology used by the state is one of the most controversial applications of AI. At the same time there are a number of potential and impactful benefits. Law enforcement agencies as well as politicians and civil society are increasingly aware of this risk-benefit tradeoff. AWK wants to develop a structured way for applications using facial recognition technology in such a way that the benefit is harvested as much as possible while addressing ethical and social requirements.

Duration: Oct 2022 – Nov 2022

Partners: AWK and ZHAW

One of the leading performance indicators of passenger service quality is the waiting time during various airport processes, such as check-in, immigration or security controls. Allocating extra human resources across the board is one sure way to reduce bottlenecks and improve passenger experience. This method however results in additional costs. Thinkgate’s Door-to-Door information flow platform (FLOW) aims to design and establish an integrated mobility information system into existing apps which helps passengers optimize travel time. It reduces the overall time needed for a typical air journey and therefore increases passenger comfort significantly.

Duration: Sep 2022 – Oct 2022

Partners: Thinkgate AG, Flughafen Zurich, HSLU and SUPSI

Psychological assessment and intervention are as of today based on analog self-reported measures captured in closed environments. In order to digitize these, users need to be motivated to go through a set of gamified interventions and to allow them to assess themselves. Furthermore to add to this user-driven engagement, we would surround this data with behavioral physiological data of the patient to create the first technology to assess and predict psychological outcomes using active and passive sensing data.

Duration: Sep 2022 – Oct 2022

Partners: Soleil Health, BFH, CSEM, FHNW, and UniGE

The Building Information Modelling (BIM) methodology is well established in the industry, but still faces major challenges in consistent information management. With the Use Case Management, buildingSMART has developed a service to capture, specify and exchange industry best practices. However the foundation for structured data is still missing. The project focuses on improving the creation, application and maintenance of continuous digital workflows for the AEC industry by facilitating the management of model-based data exchanges on an openBIM level.

Duration: Sep 2022 – Nov 2022

Partners: Bauen digital Schweiz, EPFL and HSLU

A current problem of health insurers is that they are running into one of two problems: 1) too little test data or 2) using production-like test data with high risks. Adcubum wants to mitigate these issues by using AI-powered synthetic data instead of sensitive real-world test data. With a deep dive the company aims to enhance its current product and thus offer an added-value to the healthcare insurance industry by enhancing existing data with synthetic data at scale.

Duration: Aug 2022 – Jan 2023

Partners: Adcubum, Syntheticus and ZHAW

The involved firms aim to have a scalable deployment of Industry 4.0 in their factory environments. This deep dive will allow them to collaborate together, share experiences and work with MES/ERP-based solutions. The expected outcome of the project is to innovate faster within the smart factory environment, better use of data to support decision making, reductions in inventory and more reliable deliveries.

Duration: Jul 2022 – Aug 2022

Partners: Sulzer, Oerlikon, Veriset and HSLU

The total rooftop surface in Switzerland, free or occupied, is currently unknown. Having a better understanding of the current rooftop uses would allow the authorities to better estimate potential left for solar panels, vegetated roofs and potential sources of noise, like air conditioner outlets and radiation from antennas. A defined methodology to partition roof spaces based on remote sensing and deep learning would let executives better plan their strategy for sustainable development and better monitoring.

Duration: Jul 2022 – Sep 2022

Partners: SwissTopo, HESGE, ZHAW and ZKB

In order to identify potential weaknesses in the existing insurance system and enable a standardized comparison between different insurance companies, this study aims to generate added value along legal entities as well as ecological and social standards, create more transparency in the industry and apply tried and tested analyzes to insurance for the first time.

Duration: Jul 2022 – Aug 2022

Partners: NMS AG, BFH and ZHAW

Ziel ist eine automatisierte Rekonstruktion von Fassaden aus Geodaten. Hierzu gibt es bereits verschiedene Forschungsarbeiten, jedoch auch noch viele offene Fragestellungen. Um herauszufinden, welche Probleme bei der automatisierten Rekonstruktion noch unklar sind und welches mögliche Geo-Datenquellen sind, beziehungsweise ob diese überhaupt bestehen, wird eine Roadmap erstellt, auf der die Realisierung einer automatisierten Fassadenrekonstruktion aufgebaut wird.

Duration: Jul 2022 – Okt 2022

Partners: Circular Solutions, Litix, BFH, ETH and OST

Swiss Re’s digital landscape is highly diversified and specialisted to support costing, pricing and contractual processes. The goal of this project is to develop a future proof landscape across tools, data and analytics. This will be made possible through an innovative composite architecture of data management with a learning based risk assessment kernel as the core engine.

Duration: May 2022 – June 2022

Partners: SwissRe and ZHAW

Digital services are becoming more and more customized. However with physical production of good this is often not possible or only within a very limited scope. With additive manufacturing, customizations are easier to realize but require accompanying processes and digital links between customer and production. The project aims to idenfity digital and analogue pathways in production or processes to integrate customer-specific requirements for medtech devices.

Duration: Apr 2022 – May 2022

Partners: Paoluzzo, HSLU and BFH

Vebego möchte einen Service aufbauen, um ins Geschäftsmodell “Workspace as a Service” einzutreten unter spezieller Berücksichtigung von Prozessen in der Büromöbel-Logistik. Die damit verbundenen Herausforderungen sollen mit diesem Projekt geschärft und entsprechende Lösungen entworfen werden.

Duration: Mar 2022 – Apr 2022

Partners: Vebego and ZHAW

Mettler Toledo currently has the footprint of a very traditional engineering company. Most of the hardware products are connected to either PC-based applications, manufacturing execution systems or programmable logic controllers. However more and more customers have cloud solutions on their roadmap. To convert the existing solutions to new platforms, the project is targeted towards identifying potential market fields while keeping a pragmatic approach to map this on existing systems and our huge sales force.

Duration: Apr 2022 – May 2022

Partners: Mettler Toledo, Unit8 and ZHAW

SSM produces machines for textile industry. The company aims to develop a product/service solution and with this to generate additional revenue and strengthen its market position. The company does not actively sell spare parts but customers often work under the assumption that free service is included as part of the higher Swiss price and/or buy pirated spare parts.

SSM aims to develop a service bundle consisting of a software on machine level providing relevant condition and maintenance information, fleet management which allows to plan maintenance ahead as well as spare parts management.

Duration: Schärer Schweiter Mettler AG and ZHAW

Partners: Jan 2022 – Feb 2022

Companies are increasingly required by their stakeholders to measure, report and improve their ESG (environmental, social, governance) performance. Since ESG is a rather new field, it covers a broad range of topics which are difficult to assess even for specialists and virtually impossible for non-experts. The goal of this project is to build a software prototype that allows companies of all sizes to quickly and accurately assess their ESG performance.

Duration: Dec 2021 – Jan 2022

Partners: Ascentys, BFH and SUPSI

The physical stores need to be supported by a digital channel to ensure longer-term sustainability and a new approach to in-city shopping. By redesigning the traditional supply chain and morphing it into a service ecosystem, we can identify new value propositions and business models.

Duration: Nov 2021 – Dec 2021

Partners: Zubischuhe, HSLU and EPFL

Media professionals and the general public likewise struggle with disinformation and fake news. Such information impacts opinion formation and ultimately decision making. The technology to detect the problem already exists, but needs a deeper understanding of how the task should be solved from a practical point of view.

Duration: Nov 2021 – Dec 2021

Partners: NZZ, SRF and ZHAW

The company aims to develop an algorithm with which it can produce a clearer picture of when spare parts fail and are exchanged by customers. This enables them to provide Service Level Agreements and product packages tailored to customer needs and machine usage behavior.

Duration: Nov 2021 – Dec 2021

Partners: Schärer Schweiter Mettler AG, FHGR and ZHAW

Enexan’s approach to E-Car charging is to allow the intelligent mixing of fast and slow charging, taking advantage of the two approaches while removing their downsides. This is made possible by using their innovative technology to form an AI operated network with other charging outlets, that optimally schedules power flows to satisfy customer needs.

Duration: Nov 2021 – Dec 2021

Partners: ENEXAN and HSLU

Krämer AG needs to improve their existing dedusting due to shrinking base revenue with their base model, customer migration to competitors with better maintenance services who have copied and advanced the dedusting technology. Thus they are looking for a solution that enables them to improve their current approach and open up increasing market shares in a market heavily distorted by EU subsidies.

Duration: Oct 2021 – Nov 2021

Partners: Krämer AG, OST and ZHAW

Injection molding is the state-of-the-art process to produce plastic parts for various applications. Cavity pressure has proven to be a powerful parameter for characterizing the quality of the resulting parts. But even with powerful measurement tools, the operator’s intuition and know-how are still critical factors, therefore limiting the the field of customers to those who already have this deep knowledge.

The aim of this project is to develop a smart automated solution which would make the process much more attractive to a variety of customers and open a new user group connected to an increased market share.

Duration: Oct 2021 – Jan 2022

Partners: Kistler and ZHAW

The goal of the innovation idea is to create a confidential data room permitting the agriculture trading firms to participate in the creation of a cash price index for agriculture commodities.

To achieve this goal, we used the decentriq platform to validate its capabilities to:

• Ensure the confidentiality of the data
• Encuse the encryption of the information
• Give participants the ability to load the information using APIs
• Give DNext the ability to configure and validate the reporting within the data room

Duration: Oct 2021 – Jan 2022

Partners: Decentriq, DNext Intelligence SA

Infrastructure assets require a periodical inspection. In order to solve or reduce the human difficulty in carrying out those checks, especially in areas that are difficult to access, an automated defect detection in combination with drone flights is employed. This can eliminate subjective judgement and massively reduce maintenance costs.

Duration: Sept 2021 – Oct 2021

Partners: LeanBI and ZHAW

Ein Aufzug ist eine komplexe technische Einrichtung mit unzähligen Elementen. Damit er störungsfrei funktioniert, ist eine regelmässige Wartung zwingend notwendig. Durch voraus-schauende Wartung können die Aufzugsver-fügbarkeit erhöht, Ausfallzeiten reduziert, Defekte verhindert und die Verschleissrate der Komponenten verringert werden.

Duration: Aug 2021 – Dec 2022

Partners: Lift AG, HSLU

Die Kommunikation zwischen Kunde und Anbieter ist häufig sehr unstrukturiert hinterlegt. Dadurch ist ein eventueller Mehrwert nur schwer zu generieren.  Mit diesem Projekt soll der Prozess effizienter und für den Kunden spürbar angenehmer werden.

Duration: May 2021 – June 2021

Partners: PAX and FHGR

 The preprocessing of spatial data sets is part of almost every spatial data analysis. In order to cover this for many projects simultaneously, we aim to compile Swiss Open Government Data (OGD) into a scalable data cube for all of Switzerland alongside a deep learning network trained directly on the cube.

Duration: May 2021 – June 2021

Partners: HES-SO, Litix

URMA entwickelt und fertigt Präzionswerkzeugsysteme, die weltweit bei Bohrungsarbeiten eingesetzt werden. Die perfekte Qualität ist dabei ein entscheidender Wettbewerbsvorteil. Dabei wird jede Schneide von Hand kontrolliert. Dies hat jedoch mehrere Nachteile, da es kaum skalierbar ist und auch die besten Experten Fehler machen können.  Das Hauptziel dieses Projektes ist die Verbesserung des Prozesses und der Übergang von händischer zu vollautomatisierter Kontrolle.

Duration: Jan 2021 – Nov 2021

Partners: URMA and CSEM

Comparis and ZHAW develop a dialogue system that can support online brokering of loans, mortgages and insurances. It will initiate calls to potential clients, aggregate missing data and answer user questions. Main objective is to generate fluent and trustworthy interactions. (see link)

Duration: Jun 2018 – Mar 2021

Partner: Decisis Services and ZHAW

QualitAI provides research and development towards a machine for automatic quality control of industrial goods like balloon cathethers. This is enabled by recent innovations in the area of artificial intelligence (AI), specifically the analyis of images via so-called deep learning. (see link)

Duration: Jul 2017 – Feb 2020

Partners: BW-TEC and ZHAW

Points-of-Interest (POI) sind Geodaten mit hohem Marktwert, die für räumliche Datenanalysen benötigt werden. Diese Location Intelligence ergänzt Artificial Intelligence und Big Data in Branchen von Marketing, Security (Crime Prediction), Immobilien (Investment) bis zur Logistik (Standortwahl, Supply Chain Management). POI-Daten wurden bisher von Grossunternehmen wie Google oder Hexagon/TomTom kommerziell angeboten. Mit den offenen Daten des Projekts OpenStreetMap (OSM) ist jüngst eine Alternative dazu entstanden, die teilweise quantitativ gar besser ist als die kommerziellen Angebote.

Eine Herausforderung der OSM Daten ist deren schwer bestimmbare Qualität, insbesondere die Vollständigkeit. Die innovative Idee des vorliegenden Projekts ist, die Qualität der POIs in OSM mittels eine Kombination moderner statistischer Verfahren zu bestimmen. Der Ansatz, POI aus OSM mit vorhandenen (z.B. amtlichen) Daten zu vergleichen, kommt oft mangels verfügbarer amtlicher Daten nicht in Frage. Daher wurde eine intrinsische Datenanalyse entwickelt: In Phase eins werden Trainingsdaten mit automatischer, nicht-überwachter Daten-Generierung erzeugt. Anschliessend werden in Phase zwei Neuronale Netze trainiert, die die Vollständigkeit eines bestimmten Gebiets abschätzen.

Dieses Verfahren wird es über POI hinaus erlauben, Charakteristika von Geodaten zu validieren und Mängel zu beheben. Wir sehen eine direkte Weiterentwicklung zu Naturgefahren und Risikoanalyse für Energienetze und Immobilien vor. (see link)

Duration: Jan 2020 – Jul 2020

Partners: HSR and Data Ahead Analytics

With technologies of data science, Skillue develops a digital marketplace, which makes, based on the demanded and offered skills, the benchmarking of talents, jobs and companies possible. Skillue creates a new encounter zone for candidates and companies. (see link)

Duration: Jun 2018 – Jun 2020

Partner: Skillue AG, ZHAW

The goal is the development of an application that enables the statistical comparison of risk and insurance profiles. This allows the users of the e-Broker platform to compare themselves with other customers (peers) and to automatically identify coverage gaps and overinsurance. (see link)

Duration: Mar 2018 – May 2020

Partner: Optimatis and ZHAW

Introduction
The Swiss elections 2019 have shown that the trend towards sustainable food production will increase. In Switzerland, many regional labels aim at promoting regional production and aiding local producers through an optimal and innovative use of their resources. For example, Pro Zürcher Berggebiete (PZP) awards regional products with the label natürli® to foster regional production. These regional networks encompass producers of meat, cheese, fish and wood. The goal of the labels is to strengthen the regional value chains. PZB plans together with the ZHAW a research project to increase the efficiency of the certification process and create opportunities for new business models.

Problem Formulation
Currently, the certification of products is a tedious and costly process: PZB needs to register new products and collect paper-based documentation from the producers. To obtain the natürli®-label, producers are checked by external certification institutions. This involves visiting the producers, manually examining documents and recording this data. Once registered, the control of the PZB guidelines needs to be repeated every four years. The whole process is expensive and offers only limited transparency on the product’s origin. A high fraction of the work is done manually and redundantly. In Switzerland, there are countless regional labels similar to PZB suffering from similar inefficiencies.

Solution Approach
The project aims at tackling the beforementioned problems by the development of a shared blockchain-based platform connecting all the stakeholders. This platform should lead to a digitalization and automation of the certification process.

Expected Benefit
– Digitisation of paper-based documents
– End-to-end information flow
– Automation of certification process
– Remote certification
– Transparency for end-consumer
– Reduction of redundancies for labels 

(see link)

Duration: Aug 2019 – Feb 2020

Partner: Pro Zürcher Berggebiet, ZHAW

Complex global systems, like water cycles, agriculture, forestry, and many others, affect billions but are still poorly understood. Understanding these systems is crucial not only for the well-being of humanity, but also for companies that need to adapt to a changing environment. For decades, Earth observation (EO) satellites have been collecting data about our planet – providing valuable information on the impact of climate change on our environment. In particular, agriculture it is highly susceptible to environmental changes, as rising temperatures and reduced precipitation, for example, have a major impact on yields. Within SAMBA we assess the value of operational EO data for monitoring and assessing crop resources. In this proof-of-concept, the added value of the synergistic use of multiple satellite missions as base for an operational and scalable monitoring of agricultural areas at the national level (using Brazil as an example) is demonstrated. Within the framework of classification, up-to-date methods of data mining and machine learning are used. The results are maps of agricultural areas in a spatial and temporal resolution that had hardly been achieved up to then. SAMBA is implemented based on a cloud infrastructure using Amazon Web Services as well as a stand-alone application for internal use, which allows to demonstrate transferability and robustness of the methods developed in SAMBA.

Duration: 2019

Partners: ExoLabs and SwissRe

Im Rahmen des Innovationsschecks sollen die Machbarkeit und die Belastbarkeit von Methoden zur virtuellen Bemusterung empirisch nachgewiesen werden. Konkret wird die Güte von Entscheidungen in einem realen Setting mit derjenigen in einem virtuellen Setting verglichen. Die Ergebnisse der Studie dienen dazu, die Potenziale und Risiken einer Bemusterung in VR Räumen auf Basis experimentell ermittelter Daten fundiert einschätzen zu können. Im Zentrum steht der Nachweis von Nutzenpotenzialen und Einsatzmöglichkeiten virtueller Methoden zur Bemusterung. (see link)

Duration: Aug 2018 – Nov 2019

Partners: HEFTI. HESS. MARTIGNONI. Aarau and APS FHNW

DAA operates in industrial data logistics. We provide digital accessibility of industrial data to com-panies and realize multi-stakeholder use cases such as real-time risk assessment for insurers of industrial assets. In course of the business, we establish an API-based platform for inter-company data exchange or direct data monetization. An important and growing risk for insurers of commercial property and assets are natural hazards. geo7 is a leading geospatial analytics office, focused on natural hazard modelling and quantifica-tion in Switzerland and abroad. As part of the business, geo7 collects, cleans and augments geo-spatial data from various sources. These activities result in higher-value data sets than the raw data sourced, in terms of information content and in-house accessibility. This project aims on making geo7’s natural hazard data sets available to external customers through DAA’s APIs and a standardized ontology. This requires scalable harmonization of the data, the integration into DAA’s knowledge graph and the provisioning of an API. The project brings the following, not exhaustive, added value to the participating organizations: • geo7: Possibility to provide natural hazard data sets for direct monetization (pay-per-use sale) and for business development activities. Possibility to add more data in a cost-efficient way, once this project delivered an initial infrastructure. • DAA: Possibility to upgrade the existing data base with new, high-quality data to augment own modeling capacity. Possibility to increase the existing API pool and data ontology by the very topic of Swiss natural hazards data.

Duration: Q2 2019

Partners: dataaheadanalytics and geo7

Im Rahmen des Innovationsschecks wird untersucht, mittels welchem Verhaltensrepertoire und welchen Features humanoide soziale Roboter der Klasse Nao/Pepper die Kontaktaufnahme sowie den Start in ein Gespräch erfolgreich und mit sozialer Akzeptanz durch die menschlichen lnteraktionspartner bewältigen können. Die Firma Avatarion ist ein von Saftbank Ltd. (Hersteller der Roboter Nao und Pepper) lizensierter Distributor der humanoiden Nao- und Pepperroboter für die Schweiz. Avatarion stellt mit der Yeo-Suite eine Programmier-schnittstelle bereit und bietet Programmierdienstleistungen an. Avatarion beobachtet immer wieder, dass der Start einer Interaktion mit einem sozialen Roboter für viele Kunden eine kritische Herausforderung darstellt. Dies weil der Roboter überschätzt wird oder weil zu wenig Wissen über die Funktionsweise existiert. In der Folge kommt es auf Seiten von Usern zu Frustration und zu ablehnendem Verhalten. Ein sozial akzeptiertes, proaktives Annäherungs- und Kontaktaufnahmeverhalten von Nao und Pepper stellt einen notwendigen Grundbaustein dar, auf den weitergehende Nutzungsszenarien aufsetzen wie z.B. in Rezeptions-, und Guidanceanwendungen. (see link)

Duration: Oct 2018 – Oct 2019

Partners: Avatarion Technology and FHNW

Leveraging data and analytics is essential for companies to keep up with competition, in particular for manufacturing companies. For small organizations, building up the appropriate resources as well as the knowledge and skills represents a major challenge. Specific approaches are required. This project investigates this topic.

Duration: Jan 2018 – June 2019

Partner: Several SMEs and FH St. Gallen, FH Vorarlberg and HTWG Konstanz

Ada – the Artificial Data Analyst – raises the productivity of data science endeavours by applying data science to itself: we apply empirical optimization also to algorithm and feature selection. Recent developments, e.g. from the MIT, are thus made available as a data product for Swiss industry. (see link)

Duration: Oct 2017 – Apr 2019

Partners: PwC and Datalab, ZHAW

No abstract. (see link)

Duration: Jul 2020 – Jan 2021

Partners: FHNW and MDR Beratung

Wir entwickeln ein neues System zur aktiven Einbindung von Nutzern im Freefloating-Carsharing. Nutzer werden zu Co-Produzenten, indem sie mithelfen, die Autos optimal zu positionieren. Dies wird realisiert durch ein neuartiges intelligentes Anreizsystem. (see link)

Duration: Jun 2020 – Dec 2022

Partners: ZHAW and Mobility

The project aims at creating a Total Audience Rating framework, an innovative solution based on Human Behavioural Analysis and Machine Learning by producing a matching criteria between data representing what and when a complete population watches on television, and who is actually watching. (see link)

Duration: May 2020 – May 2022

Partners: SUPSI and Nielsen TV Audience Measurement

Development of a technology capable of estimating the risk of shallow landslide events, based on numeric soil models and water saturation maps. The latter are obtained from a sparse network of automated soil moisture profile sensors and data spatialization by machine learning techniques. (see link)

Duration: Sep 2020 – Sep 2022

Partners: SUPSI DTI and Geoalps Engineering

No abstract. (see link)

Duration: Aug 2020 – Feb 2021

Partners: ZHAW and Next Insights

The MAPEC project offers an innovative and powerful analysis method for planning where, when and how to shed light while proposing an economic optimization of actions. (see link)

Duration: Jun 2020 – Dec 2021

Partners: HES-SO and Navitas Consilium

Das Projekt soll die Potentiale der Digitalisierung für das Abfallwirtschafts-Ökosystem der Schweiz nutzbar machen. Dazu werden ein Sensor- und Konnektivitätsmodul für Abfallbehältnisse und entsprechende Datenanalyse- und Serviceprozesse angeschlossener Systeme entwickelt und validiert. (see link)

Duration: Jul – 2020 – Apr 2022

Partners: ZHAW and Anta Swiss

This project will leverage cutting-edge Natural Language Processing techniques for document classification and information extraction to automatically initiate specific tasks based on the content of documents in electronic repositories. (see link)

Duration: Jul 2020 – Jul 2022

Partners: SUPSI and Karakun

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. (see link)

Duration: Feb 2020 – May 2022

Partners: ZHAW and Varian Medical Systems Imaging Laboratory

It is the objective to develop a smart connected product system as well as associated digital services and business models for the industrial piping business. Such a product system enables suppliers and operators of piping systems to continuously monitoring, controlling, and improving the system. (see link)

Duration: Jan 2020 – Jul 2021

Partners: ZHAW and GF Piping Systems

In Deep Snow, we apply deep machine learning on Earth observation data to monitor the extent and amount of snow in high-resolution and near real-time for the Swiss Alps. This quantitative information is important for tourism, hydropower, and risk assessment (floods and snow avalanches). (see link)

Duration: Oct 2020 – Oct 2022

Partners: ETH Zürich and ExoLabs

A machine learning engine able to predict and evaluate the plausibility of Swiss Customs clearance numbers based on good descriptions as well as providing all necessary information associated with those customs clearance numbers.

Since the volume of e-commerce business’ is steadily increasing over the last years, AAS, as a customs agency, faces the challenge to perform thousands of customs clearances a day for import or export.

Currently AAS is facing several challenges, which are  expect to be solved with the mentioned engine:

• Customers not able to classify their goods: Prediction is needed  to derive customs clearance numbers automatically.
• Customers able to deliver customs clearance numbers: Plausibility evaluation is needed to check the correctness of the data and be customs compliant.
• Time constraints: manual verification of customs data is very time consuming and restricts heavily the growing capacity of AAS in terms of numbers of customs clearances that can be accepted per day. On this matter, an engine which provides and automatically verifies most of good’s customs related data, would improve the efficiency and compliance giving AAS the chance to grow in volume and concentrate only on difficult cases which could not be solved automatically.

(see link)

Duration: May 2020 – Nov 2020

Partners: FFHS and AAS Freight

Currently there is an unmet need for trust and privacy in multi-party data analytics (e.g. in cloud computing). A new solution approach using hardware-based trusted execution environments is called Confidential Computing. The Zurich-based and investor-backed startup decentriq is a provider of confidential analytics software using Confidential Computing and, together with Microsoft, Intel and Google, founding member of the Confidential Computing Consortium. In this project decentriq will be supported by researchers from ZHAW in the design and validation of four software prototypes in cooperation with SIX Group, Swisscom, Intel and two other industry partners. The prototypes form the basis for the Confidential Data Analytics Platform of decentriq, a software solution enabling confidentiality for multi-party data analytics. Furthermore, the goal is to understand adoption factors and barriers of Confidential Data Analytics in enterprises and develop a generic Confidential Analytics Canvas, a strategic template to identify new opportunities for the use of Confidential Data Analytics. (see link)

Duration: Jun 2020 – Dec 2020

Partners: dq technologies and ZHAW

The goal of this project is to boost the Quality of Experience of Lifelike’s existing leadership training product SkillGym by developing a novel technological solution based on cutting-edge Natural Language Understanding techniques. (see link)

Duration: Jan 2020 – Jan 2022

Partners: Lifelike SA, SUPSI ISIN

Provide a platform to enable candidates to register their profile, request references and automatically validate their skills and expertise certification so that they can be saved for further use within the application and recruiting process. (see link)

Duration: Sep 2020 – Mar 2022

Partners:  FFHS and Skills Finder

No abstract. (see link)

Duration: Jun 2020 – Dec 2020

Partners: FHSG and Sedimentum

This project aims at developing a Value-Based Marketing & Sales method for Smart Services. The holistic method bases its four dimensions on advanced analytics of operational and market data. Thereby, it opens revenue opportunities for manufacturing companies in Switzerland through Smart Services. (see link)

Duration: May 2019 – Nov 2020

Partners: Siemens Mobility and HSG

More and more manufacturing companies are switching from product to service revenue and evaluating with new, outcome-based, business models. Many of these companies, however, are struggling to establish a clear business case in order to justify the investments in IoT . This project aims to identify the most attractive business models with regards to anticipated added value and implementation efforts, with focus on industrial companies within the MEM industry. In addition, we want to identify the main drivers to increase customer’s willingness-to-share data, as a basis for developing new data-based services. (see link)

Duration: April 2019 – April 2021

Partners: Ferrum and SML ZHAW

MEDInA will enable the creation of low cost IoT self-adaptive Machine Learning based applications by developing an Intelligence as Service (InaaS) framework. InaaS will provide a shareable edge/cloud platform that supports ML Modules running on edges, improved by cloud, able to self-adapt locally. (see link)

Duration: Jul 2019 – Jul 2021

Partners: HEPIA Genève and SixSq

ScorePad’s sheet music scanning service works for highquality 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. (see link)

Duration: Sep 2019 – Mar 2022

Partners: ScorePad and InIT ZHAW

QU4LITY aims at developing a smart, fully automated, and modular cell for quality control (initially for bearing and shaft testing for INTERROLL SA, the main implementation partner) empowered by a pervasive use of key digital technologies towards Industrie4.0 paradigm full implementation. (see link)

Duration: Nov 2019 – Apr 2021

Partners: Interroll SA and SUPSI

Datenerhebung und Entwicklung eines mobilen, nicht-invasiven Systems für Tierärzte und Züchter zur Erhebung wichtiger Vitaldaten mit dem Ziel, die Ovulation bei Stuten ohne Rektalkontrolle zuverlässig festzustellen sowie eine Fohlengeburt rechtzeitig vorherzusagen und deren Verlauf zu überwachen. (see link)

Duration: Nov 2019 – Dec 2021

Partners: Piavita and University of Bern

Dienstpläne sind das Bindeglied zwischen Personal, Bewohnern und den betrieblichen Abläufen in  Pflegeeinrichtungen. In den Dienstplänen müssen persönliche Umstände der Pflegefachpersonen und Präferenzen der Bewohner ebenso sorgsam berücksichtigt werden, wie wirtschaftliche und  rechtliche Rahmenbedingungen. Studien haben gezeigt, dass ein gut gestalteter Dienstplan die  Betreuungsqualität aber auch die Zufriedenheit der Pflegefachpersonen erhöht. 

Das Forschungsprojekt «Optimierung von Personaleinsätzen in der stationären Langzeit-pflege (CareOpt)» wird als Projektmanager und Implementierungspartner von Dr. Alexander Grimm (CEO Aspaara) und Dr. Kevin Zemmer (CTO Aspaara) geleitet. Von Seiten des Forschungspartners ZHAW übernehmen Frau Prof. Dr. Maria Schubert von der School of Health Professions und Dr. Thomas Herrmann vom Institut für Datenanalyse und Prozess-design die Leitung. Das Forschungsprojekt wird von der Schweizer Innovationsagentur Innosuisse aus Bundesmitteln über ein Jahr gefördert, um wissenschaftsbasierte Innovation im Interesse von Wirtschaft und Gesellschaft zu fördern. (see link)

Duration: Sep 2019 – Mar 2021

Partners: Aspaara and ZHAW

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, higher-level analytics, e.g. “trend analysis over last month” or “detect outliers in the price fluctuation of product X over the last year” are hard to formulate even for SQL experts. Hence, the majority of non-expert users are basically not able to explore the available knowledge of their company.

Veezoo currently provides a system that can answer natural language queries against databases, with the goal of empowering all users inside a company to become data-driven and benefit from the available information. However, feedback from existing users shows that a wide range of customers completely lack familiarity with their own company’s databases. In practice, this leads to a severely limited adoption of systems that provide a natural language interface for databases, given that most users are not aware apriori which questions to ask or on which regions of data to focus, in order to get the most added value from the large amounts of knowledge made available to them. Therefore, in the lack of proactive suggestions, recommended insights, as well as data exploration guidance, only translating natural language questions to equivalent database queries is simply not enough.

In this project we tackle this important open issue to make natural language interfaces to databases more suitable for widespread adoption by designing novel algorithms on top of the current Veezoo system, through a service that proactively guides users in exploring the data and augmenting the company’s knowledge base. The service, called NQuest, will provide analytics mechanisms that empower a wide range of users to discover new insights in existing databases. (see link)

Duration: Jul 2019 – Jul 2021

Partners: Veezoo and ZHAW

In Zusammenarbeit mit der Zürcher Hochschule für angewandte Wissenschaft (ZHAW) und der Hochschule Luzern (HSLU) hat die IDEE SEETAL für die Seetaler KMUs das Projekt «InnoEco» entwickelt. Das Projekt zielt darauf hin, die Unternehmen in der Entwicklung digitaler kundenzentrierter Dienstleistungen zu befähigen, unterstützen und zu fördern. Das Projekt will für Seetaler-KMU anwendbare Möglichkeiten und Instrumente schaffen, die Digitalisierung für innovative Dienstleistungen für Ihre Kunden zu nutzen. Das Projekt stärkt die Position der KMU im Standortwettbewerb.

Duration: 2019 – 2021

Partners: IDEE SEETAL and IDP ZHAW

The project aims to prototype Digital Twins in six different industrial environments to explore how the Digital Twins can designed to improve business outcomes over the whole lifecycle. The lessons learnt will be shared openly with all partners from the innovation approach taken, and business models. (see link)

Duration: May 2019 – Mar 2021

Partners: Siemens Mobility, ZHAW

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. (see link)

Duration: Jul 2019 – Sep 2021

Partners: KITRO SA and Datalab ZHAW

Eine nachaltige Umsetzung datenbasierter Dienstleistungen bedingt die Optimierung des soziotechnischen Systems. Ziel ist die Erarbeitung einer Vorgehensweise und eines Methodensets, welche die Massnahmen beim Mensch, der Technik und der Organisation berücksichtigt und aufeinander abstimmt. (see link)

Duration: Feb 2019 – Feb 2022

Partners: Procomm IT Concepts and FHGR

In der interdisziplinären Studie werden Chancen und Risiken von neuen Anwendungen der Roboter, die Empathie simulieren und Emotionen wecken, abgeschätzt, insbesondere in den Bereichen Einsatzpotenziale, Akzeptanz, Ethik, Recht und Volkswirtschaft. Der Untersuchungsgegenstand der Studie umfasst vor allem psycho-soziale, ethische, rechtliche, volkswirtschaftliche Auswirkungen und politischen Aspekte dieser Technologie. Die Ergebnisse sind in einem Bericht darzustellen, der wissenschaftlichen Anforderungen genügt und der auch als Basis zur Information einer breiteren Öffentlichkeit dient. Die Situation soll auf Grund der in der Studie gewonnen Erkenntnisse in einer Gesamtbeurteilung bewertet werden. Der Bericht soll Empfehlungen zum weiteren Umgang mit dieser Thematik enthalten, die an Entscheidungsträger insbesondere in der Politik und an Stakeholder in den erwähnten Anwendungsbereichen gerichtet sind.

Duration: Sep 2019 – Mar 2021

Partners: F&P Robotics and APS FHNW

Die dynamische Differenzialkalorimetrie misst die aufgenommene bzw. abgegebene Wärmemenge einer Probe, während diese aufgeheizt bzw. abgekühlt wird. Die Auswertung solcher Messkurven von unbekannten Materialien soll durch Deep Learning und statistische Methoden automatisiert werden. (see link)

Duration: Dec 2019 – Dec 2021

Partners: Mettler Toledo and CSEM

Today, in the field of personal damage law, legal case files consist of 400-5000 PDF-pages to be analysed manually by experts, a very time-consuming and costly task. Instead, our machine learning-based solution will extract relevant data and will thus empower an innovative case management software. (see link)

Duration: Oct 2019 – Apr 2022

Partners: legal.i and BFH

Adaptive scheduling algorithms for sheet metal shop production planning are devised with unprecedented level of detail to support operations and to quickly answer requests for quotations, thus increasing reliability and competitiveness. (see link)

Duration: May 2019 – May 2021

Partners: Bystronic and IDP ZHAW

Entwicklung einer “Lifestyle Change Toolbox”, die die Dienstleistungsqualität von Interventionsprogrammen zur Prävention oder Behandlung von metabolischem Syndrom, Diabetes und Cholesterin verbessert. Dies wird durch personalisierte Interventionen und die Vernetzung der Leistungsanbieter erreicht. (see link)

Duration: Dec 2018 – Jul 2021

Partners: Lucullinary and HSLU

We develop and implement a cloud-based revenue optimization system for wind plant operators. By combining data analysis of real-time plant data with revenue schemes, revenue losses due to failures and sub-optimum control can be avoided, and profit can be increased by improved bidding strategies. (see link)

Duration: Oct 2018 – Jan 2021

Partner: WinJi AG, ZHAW

Partial discharge (PD) is the most reliable monitoring for generator stator insulation health status, and has been applied in industry since the 1990’s. This project aims to merge experience and knowledge from GE with state of the art methods in machine learning to improve the data analysis of PD. (see link)

Duration: Feb 2018 – Apr 2021

Partners: GE and ETH Zurich