Categories
Explore project

Hardware/software Trade-off for the Reduction of Energy Consumption

Project type: Explore Project

Hardware/software Trade-off for the Reduction of Energy Consumption

Summary

Computing devices consume a considerable amount of energy. Within data centers this has an impact on climate change and in small embedded systems, i.e., battery powered devices, energy consumption influences battery life. Implementing an algorithm in hardware (in a chip) is more energy efficient than executing it in software in a processor. Up until recently processor performance and energy efficiency have been good enough to just use software on a standard processor or on a graphic processing unit. However, this performance increase comes to an end and energy-efficient computing systems need domain specific hardware accelerators.

However, the cost of producing a chip is very high. Between fixed hardware and software there is the technology of field-programmable gate arrays (FPGAs). FPGAs are programmable hardware, the algorithm can be changed at runtime. However, FPGAs are less energy efficient than chips. We expect that for some algorithms an FPGA will be more energy efficient than the implementation in software. The research question is whether and how it is possible to reduce energy consumption of IT systems by moving algorithms from software into hardware (FPGAs). We will do this by investigating classic sorting and path-finding algorithms and compare their energy-efficiency and, in addition, their performance. Such results are essential to both data centers as well as embedded systems. However, the hardware design of these accelerators is often complex, and their development is time-consuming and error-prone. Therefore, we need a tool and methodology that enables software engineers to design efficient hardware implementation of their algorithms. We will explore a modern hardware construction language, Chisel. Chisel is a Scala-embedded hardware construction language that allows to describe hardware in a more software-like high-level language. Chisel is the enabling technology to simplify the translation of a program from software into hardware. This project will furthermore investigate the efficiency of using the functional and object-oriented hardware description language Chisel to express algorithms efficiently for execution in FPGAs.

Programs running on a general-purpose computer consume a considerable amount of energy. Some programs can be translated into hardware and executed on an FPGA. This project will explore the trade-offs between executing a program in hardware and executing it in software relative to energy consumption.

Value Creation

Scientific Value
The FPGA and software implementations of path-finding algorithms have recently been evaluated in the lense of performance, e.g., [?], whereas sorting algorithms have also been evaluated on energy consumption, e.g., [2]. Here FPGAs performed better than CPU in many cases and with similar or reduced energy consumption. The language used for implementation is Verilog and C which is then translated to Verilog using Vivado HLS. In this project, we will implement the algorithms in hardware using Chiesl and evaluate their performance and energy consumption. DTU and RUC will advance the research in the design and testing of digital systems for energy saving. Our proposed approach provides a general software engineering procedure that we plan to validate with standard algorithms used in cloud applications. This research will drive the adaption of hardware design methods to the education curriculum towards modern tools and agile methods. 

Capacity Building
The project establish a new collaboration between two Danish Universities and is a first step towards building a more energy-aware profile of the Computer Science laboratory FlexLab, RUC. In return FlexLab make FPGAs available to the research assistants at RUC. Thus, this project will improve visibility of energy-aware design IT systems nationally and international. This project with the cooperation between researchers as DTU and RUC will allow Denmark to take the lead in digital research nd development for reduced energy consumption. The upcoming research positions at RUC will contribute to building RUC’s research capacity, and the project will also recruit new junior researchers directly and in future subsequent projects.

Business Value
The changes in the hardware industry indicates that the use of FPGAs will increase: A few years ago Intel bought Altera -one of the two largest FPGA production companies- to include FPGAs in future versions of their processors. Similar, AMD is aiming to buy Xilinx, the other big FPGA vendor. In addition, one can already rent a server in the cloud from Amazon that includes an FPGA. These changes all points towards that FPGAs are entering mainstream computing. Many mainstream programming languages like C# or Java already include functional features such as lambda expressions or higher-order functions. The more common languages for encoding FPGAs are Verilog, a C inspired language, and VHDL, a Pascal inspired language, Therefore, it may be efficient for mainstream software developers to use a functional language to efficiently implement algorithms in FPGAs and thus both increase performance and reduce the energy consumption. 

Societal Value
Currently ICT consumes approximately 10% of the global electricity and this is estimated to increase to 20% in 2030. Thus, reducing energy consumption of ICT is critical. If successful, this project has the potential to reduce the energy consumption via rephrasing the essential software programs in FPGA units.

Participants

Project Manager

Maja Hanne Kirkeby

Assistant Professor

Roskilde University
Department of People and Technology

E: majaht@ruc.dk

Martin Schoerberl

Associate Professor

Technical University of Denmark
DTU Compute

Mads Rosendahl

Associate Professor

Roskilde Universlty
Department of People and Technology

Thomas Krabben

FlexLab Manager

Roskilde University
Department of People and Technology

Categories
News

Meet Tijs Slaats, who just won a prize for best process mining algorithm

Meet Tijs Slaats, who just won a prize for best process mining algorithm

Tijs is Associate Professor at the Department of Computer Science at the University of Copenhagen and Head of the Business Process Modeling and Intelligence research group. In DIREC, he works on the Bridge project AI and Blockchains for Complex Business Processes.

Tijs’ research interests include declarative and hybrid process technologies, blockchain technologies, process mining, and information systems development.  

He co-invented the flagship declarative Dynamic Condition Response (DCR) Graphs process notation and was a primary driver in its early commercial adoption. In addition, he led the invention and development of the DisCoveR process miner, which was recognized as the best process discovery algorithm in 2021. 

Can you tell us briefly about your research and what value you expect to get from it?
We try to describe processes. It can be basic things that we do as human beings. It could be assembling a car at a factory, but it could also be treating patients at a hospital. If a patient is admitted to a hospital, they need help and treatment.

What it has in common for these examples is that you need to go through a number of steps and activities to reach your goal, and those activities are related to each other. It may be medication that needs to be taken in a certain order.

In our research, we have developed a mathematical method for describing these processes. The reason for doing this is because it gives you the tools to ensure that the process goes the way you want it to.

In the new DIREC project, we take one step further. We have observed that many companies and organizations have large amounts of data on how they have performed their jobs. And we can look at these data and analyze them to see how they actually perform their jobs, because the way many people do their jobs does not necessarily match the way they expect to do it. Maybe they take shortcuts unintentionally.

Our idea is to find these data and analyze them and on that basis we get a model.

It is important that such a model also is understandable to the users so that they can understand how they perform their work. We call this process mining, and it is a reasonably large academic area. Two years ago, I developed an algorithm, and it was in a contest, where you compare which algorithm is most accurate to describe these “logs of behaviour”, and we won the contest.

Read more

What results do you expect from your research?
Our cooperation with industry is particularly important. In the project, we collaborate with the company Gekkobrain https://gekkobrain.com, which works with DevOps, and they are interested in analyzing large ERP systems and in finding tools that can optimize a system and find abnormalities. These systems are quite complex, so it is important to be able to identify where things are going wrong.

Gekkobrain has a lot of data because they work with large companies that have huge amounts of log data, and these systems are so complex that it adds some extra challenges for our algorithms. To get access to such complex data is an important perspective.

How can your research make a difference to companies and society?
The biggest impact of our work and models is that you can gain insight into how you perform your work. It gives you an objective picture of what has been done.

Companies can use it to find out if there are places where work processes are performed in an inappropriate way and thus avoid the extra costs.

Can you tell us about your background and how you ended up working with this research area?
I initially got a Bachelor degree in Information & Communication Technology from Fontys University of Professional Education, then worked in industry where I led the webshop development team of a Dutch e-commerce provider and acted as project leader on the implementation of our product for two major customers; Ferrari and Hewlett Packard.

I decided to move to Denmark after meeting my (Danish) wife, at the time I was already considering pursuing further education, while my wife was fairly settled in Denmark, so it made sense for me to be the one to move.

I got my MSc and PhD degrees at the IT University of Copenhagen. There I became interested in the field of business process modeling because it allows me to combine foundational theoretical research with very concrete industrial applications. Process mining in particular provides really interesting challenges because it requires learned models to be understandable for business users, something that has only recently come into focus in the more general field of AI. 

After a short postdoc at ITU I accepted a tenure-track assistant professorship at DIKU, which was a very good opportunity because it offers a (near) permanent position for relatively junior researchers. At the time this was uncommon in Denmark.

Categories
News

Project will transfer AI from the cloud to the IoT device

13 December 2021

Project will transfer AI from the cloud to the IoT device

In a new DIREC project, computer science researchers collaborate with industry to develop artificial intelligence to let the IoT devices handle more things.

Photo: Kaare Smith, DTU

Digitization of society is one of the prerequisites for achieving the climate goal of 70 percent CO2 reduction by 2030. And there small sensors (IoT devices) installed in e.g. buildings, heating systems, and treatment plants will play an important role in managing energy consumption, heat, indoor climate, etc.

In a new project Embedded AI – supported by the national research center DIREC – researchers together with industry will investigate how to develop AI (artificial intelligence) that can be implemented in IoT devices so that they can do more themselves. Today, sensors are dependent on AI algorithms on cloud platforms or decentralized networks (Edge Computing), where data and commands are sent via internet / wireless networks.

“It is quite obvious that you will not be able to do the same as with the cloud and edge, but it will cost less, use less energy and be able to react faster. It will also increase security and privacy because data can be kept where it is collected. So there are many benefits to embedded AI, says the project manager, Professor, Section Manager, and Deputy Director at DTU Compute Jan Madsen.

In the project, DTU, Aarhus University, the University of Copenhagen, and CBS collaborate with the pump manufacturer Grundfos Holding, the engine and machine manufacturer MAN Energy Solution, the window manufacturer VELUX, and the technology company Indesmatech.

Move AI from large platforms to small ones
During the three years, the partners will work on specific issues within the four industry partners. They are strong representatives of companies that will be able to strengthen competitiveness by knowing the right tools and platforms to leverage embedded AI (eAI) in their products.

The project will examine the process of going from large platforms to small ones, explore suitable tool platforms, check what opportunities new types of chip provide for embedded AI and map out how embedded AI will be able to change the business models for companies.

Grundfos is experiencing a knowledge gap
The idea for the DIREC project has come through network meetings, where research institutions and industry talk about future competencies and technology needs. Here, Thorkild Kvisgaard, Head of Electronics, Director Technology Innovation at Grundfos, has participated.

He says the company sees a clear need to be able to move some of the artificial intelligence from the large platforms that run on mainframe computers, etc., down and run in more embedded devices (AIoT), even though it will be very resource-limited platforms to work on. Because you can save energy, and you avoid having to send data over the Internet and be dependent on the Internet and cloud solutions that run outside your own control.

“It will, of course, turn out that you can not do quite as much on platforms with limited resources, but we do not know those limits today. And maybe we can do a lot more than we think. If we work with something that is not time-critical, it does not matter that the embedded AI has to spend several minutes figuring something out if it is a slow and complex process,” says Thorkild Kvisgaard.

“At Grundfos, we have experimented with the technology ourselves, but we are experiencing a gap between what data science experts work with on large cloud platforms and what IoT programmers work with. So we hope that the project will also create a better understanding of each other’s work areas.”

Chip becomes crucial

The industry partner Indesmatech acts as both the local office for chip manufacturers, facilitates various development projects with new technology and helps companies to develop technology.

The company is looking forward to clarifying the possibilities when working with Embedded AI algorithms, explains Co-founder of Indesmatech Rune Domsten:

“What is interesting about the Embedded AI project, in addition to the software used for AI, is to investigate which chip and hardware platforms to execute on and use in the different situations. Because the battery consumption in sensors really depends on which chip you use, and it can be a question of whether the battery lasts for e.g. five or ten years.”

Although the industry partners in the DIREC project as large companies are already working on AI, the project could also have great significance for especially small companies that lag behind with artificial intelligence, says Project Manager Jan Madsen:

“While it may seem rather uninteresting in research to develop small AI algorithms, there are actually major research challenges in developing efficient architectures and methods that can be used in smaller and resource-limited sensors / IoT devices. It can also be what gets a small business started using AI for complex tasks and processes.”

About DIREC – Digital Research Centre Denmark

The purpose of the national research centre DIREC is to bring Denmark at the forefront of the latest digital technologies through world-class digital research. To meet the great demand for highly educated IT specialists, DIREC also works to expand the capacity within both research and education of computer scientists. The centre has a total budget of DKK 275 million and is supported by the Innovation Fund Denmark with DKK 100 million. The partnership consists of a unique collaboration across the computer science departments at Denmark’s eight universities and the Alexandra Institute.

The activities in DIREC are based on societal needs, where research is continuously translated into value-creating solutions in collaboration with the business community and the public sector. The projects operate across industries with focus on artificial intelligence, Internet of Things, algorithms and cybersecurity among others.

Read more at direc.dk

Embedded AI

Partners in Embedded AI:

  • DTU
  • Aarhus Universitet
  • Københavns Universitet
  • CBS
  • Grundfos Holding A/S
  • MAN Energy Solution
  • Indesmatech
  • VELUX

Contact 
Jan Madsen
DTU Compute
Technical University of Denmark
jama@dtu.dk

Categories
News

A new project will make it easier to design and certify IoT systems

8 December 2021

A new project will make it easier to design and certify IoT systems

IoT devices are blending into the infrastructure of both society and our personal lives. Many of these devices run in uncontrolled, potentially hostile environments, which makes them vulnerable to security attacks. Moreover, with the increasing number of safety critical IoT devices, such as medical and industrial IoT devices, IoT security is a public safety issue. Thus, the need for security in these systems has even been recognized at governmental and legislative level, e.g. in the EU, US and UK, resulting in a proposed legislation to enforce at least a minimum of security consideration in deployed IoT products.

Photo by Søren Kjeldgaard

Professor Jaco van de Pol will lead the DIREC project Secure IoT systems (SIoT), which aims to model security threats and countermeasures for IoT systems and services, to develop secure solutions, and to analyze residual security risks.

“Our goal with the SiOT project is to make it easier to design and certify secure IoT devices. Security and privacy are very important to many people and organizations that use IoT devices for measurements in smart cities, natural environments, logistics chains, and in their private homes. Engineering IoT devices is challenging, since they are physically small and must run on low power. Yet, they must perform accurate measurements and communicate with high efficiency. So how can one achieve security on top of that? We will provide new tools to model security threats, implement countermeasures, and analyze the final security risks”.

Jaco van de Pol continues: “I am happy to be able to work with a team that includes both academic researchers and industrial experts. This will ensure that the project addresses the right questions, and that we can find new solutions by combining the expertise from several disciplines. And we can evaluate the solutions in an industrial setting.”

The strategy is to use algorithms from automata theory and game theory to automate risk analysis and security strategy synthesis. The implementation of the security policies will consider both technical as well as social aspects, in particular usability in organizations and training of people.

For TERMA A/S, who are part of the project, their motivation is to be aware of the landscape in IoT systems in order to make them more cyber-resilient. Samant Khajuria, Chief Specialist Cybersecurity at TERMA A/S, explains:

“When we integrate IoT systems in our line of business, our main purpose is to provide safety for critical systems. Our systems go both to the defense and civilian sector such as Wind Farms, airports or harbors. We know that IoT devices sooner or later become obvious pieces of the puzzle in providing good systems in the future. And before integrating in systems like this we need to understand the threats and risks. Secondly, we would like to collaborate with universities in Denmark, because the researchers are working with this everyday. We are merely the users of the technology.”

Jørgen Hartig is Managing Director and Partner in SecurIOT, who are also part of the project. He hopes the project will help create the needed awareness on both sides of the “table” about the environment of industry 4.0. They often hear customers saying: “Why would the hackers go for us? We do not produce anything interesting…” or “the production has been for 25 years, and we haven’t had an issue” or “there are no connections between IT systems and OT systems.”

“The last statement will be challenged dramatically in the next 5-10 years. IoT and OT vendors will come out with new technology solutions that will utilize cloud-enabled applications and 5G connections to the factory floor, so there will be no “air-gap” in the future. I am not saying it is wrong, I am just saying that the consumers and IoT vendors need to work with the cyber threats and risks in a structured way.”

According to Gert Læssøe Mikkelsen, Head of Security Lab at the Alexandra Institute, there is a need for improved cyber security in IoT, which is also the reason why they participate in the project:

“We see a need for academic research in close collaboration with industry to deal with this. We hope that the tools and methodologies developed in this project will be deployed and improve the cybersecurity of IoT so we are all ready for the future, where we both expect an increase in the threats from cybercriminals and, as a consequence, an increase in requirements and regulation in this area that the industry must be ready to handle.”

About DIREC – Digital Research Centre Denmark

The purpose of the national research centre DIREC is to bring Denmark at the forefront of the latest digital technologies through world-class digital research. To meet the great demand for highly educated IT specialists, DIREC also works to expand the capacity within both research and education of computer scientists. The centre has a total budget of DKK 275 million and is supported by the Innovation Fund Denmark with DKK 100 million. The partnership consists of a unique collaboration across the computer science departments at Denmark’s eight universities and the Alexandra Institute.

The activities in DIREC are based on societal needs, where research is continuously translated into value-creating solutions in collaboration with the business community and the public sector. The projects operate across industries with focus on artificial intelligence, Internet of Things, algorithms and cybersecurity among others.

Read more at direc.dk

SIoT

In SIoT, the following parties will participate as collaborators:

  • Aarhus University
  • Aalborg University
  • DTU
  • Copenhagen Business School
  • Alexandra Institute
  • Terma
  • Grundfos
  • Develco Products
  • Beumer Group
  • Micro Technic
  • SecuriOT
  • Seluxit

Contact
Jaco van de Pol
Department of Computer Science
Aarhus University
jaco@cs.au.dk

Categories
News

Companies and researchers will develop digital artefacts to support the future hybrid workplace

1 December 2021

Companies and researchers will develop digital artefacts to support the future hybrid workplace

What should the next generation of Zoom and Teams look like? This question will be expored by researchers and companies in a new DIREC project led by Associate Professor Eve Hoggan. The project will gather researchers from universities all over Denmark, as well as several industrial collaborators. Hoggan will lead the project REWORK, which will re-think and develop the future of hybrid work forms.

Photo by Søren Kjeldgaard

There are a multitude of reasons to embrace remote and hybrid work. Climate concerns are increasing, borders are difficult to cross, work/life balance may be easier to attain, power distributions in society could potentially be redressed, to name a few. This means that the demand for systems that support hybrid work will increase significantly.

The recent COVID-19 pandemic, and the attendant lockdown, demonstrated the potential benefits and possibilities of remote work practices, as well as the glaring deficiencies such practices bring. Zoom fatigue, resulting from high cognitive loads and intense amounts of eye contact, is just the tip of an uncomfortable iceberg where the problem of embodied presence remains a stubborn limitation.

The research project REWORK: The Futures of Hybrid Work, led by associate professor Eve Hoggan, aims to enrich digital technologies for hybrid work. The goal is to design and develop artefacts and processes to support organizations in exploring and preparing for successful collaboration in the future.

Remote and hybrid work will certainly be part of the future of most work practices, but what should these future work practices look like?

“I think we need to aim higher than merely fixing the systems we already have,” says associate professor Eve Hoggan, and continues; “We need to be bolder and consider a different future for our workplace if we want to secure successful collaboration. And that is what REWORK is all about. We will, in particular, focus on representation of embodiment and physical surroundings in a digital/analog setting, as this is one of the most important obstacles for successful hybrid work.”

Bankdata is a company which needs such tools. To them it is crucial to be able to attract and retain the best employees. According to Peter Bering, Head of Digitalization at Bankdata, the workplace must be flexible with good opportunities for socializing, and in this regard the company’s digital products play an important role.

“The hybrid workplace is more than just a good video connection. It should also be characterized by a high level of commitment, creativity and cohesion, which is not easy to achieve with the technology we use today. But we are ambitious in this area, and therefore we have decided to engage in – and not least contribute to – the latest research in the field through a collaboration with DIREC,” says Peter Bering.

Lene Bach Graversen, Head of Facility at Arla, hopes that in the project will provide more digital tools that can support the agile collaboration at a distance.

“Like many other companies, we do not know exactly what will happen in the future. We hope that the feedback and knowledge we gain can direct our focus towards what tools are needed by the employees to optimize their online meetings, which have become a regular part of our work. Many of our employees work both at home and at the office, and we see that it offers advantages as well as disadvantages. We need to look at other available tools and how to develop them so that we can continue to support our employees. The strength of collaborating is that you learn from each other.”

Mads Troelsgaard, CEO and co-founder of SynergyXR, participates in the project to knowledge-share with the universities, but also because they want to make their AR/VR and Mixed Reality platform available for the project. For the past ten years, SynergyXR has developed AR/VR and Mixed Reality applications for some of the largest companies in the world.

On their platform, you can meet colleagues in Hololens, with VR glasses or in a room on a PC, and in this way explain complicated knowledge on a completely different level than is possible on Zoom or Teams. The companies may also upload videos, photos, pdf files or other, and in this way establish their own AR/VR setup. They build ‘the corporate metaverse’, where companies can build their own metaverse.

A lot of things appeal to us in this collaboration. We have a platform that is easy to access, and which provides the opportunity to meet in a completely new way, and which changes the way companies collaborate at a distance. In addition, we would like to contribute with our many years of experience as tech specialists within XR technology. In return, we hope to gain a lot of new knowledge both about what’s happening out there, but also to get feedback on our platform. We can also help train future employees to better understand the potential of XR technology which is another advantage. In this way, we see a lot of ‘wins’ from the collaboration”.

About DIREC – Digital Research Centre Denmark

The purpose of the national research centre DIREC is to bring Denmark at the forefront of the latest digital technologies through world-class digital research. To meet the great demand for highly educated IT specialists, DIREC also works to expand the capacity within both research and education of computer scientists. The centre has a total budget of DKK 275 million and is supported by the Innovation Fund Denmark with DKK 100 million. The partnership consists of a unique collaboration across the computer science departments at Denmark’s eight universities and the Alexandra Institute.

The activities in DIREC are based on societal needs, where research is continuously translated into value-creating solutions in collaboration with the business community and the public sector. The projects operate across industries with focus on artificial intelligence, Internet of Things, algorithms and cybersecurity among others.

Read more at direc.dk

REWORK

In ReWork, the following parties will participate as collaborators:

  • Aarhus University
  • Copenhagen University
  • IT University of Copenhagen
  • RUC
  • Alexandra Institute
  • Catch (Center for Art, Design, and Technology)
  • Microsoft Research, Cambridge UK
  • L&T InfoTech
  • Khora
  • Zimulate
  • KeyLoop
  • Studio Koh
  • Synergy XR
  • Lead
  • BEC
  • Cadpeople
  • Bankdata
  • Arla

Contact: 
Eve Hoggan
Department of Computer Science
Aarhus University
M: +45 93 50 85 56
eve.hoggan@cs.au.dk

Follow the project on cs.au.dk/rework or on Twitter @ReWork_Direc

Categories
Educational project

Software Infrastructures for Teaching at Scale

Project type: Educational Project

Software Infrastructures for Teaching at Scale

To teach many recent topics within digital technology at scale requires proper software infrastructures to support the teaching for lab exercises and projects. Some of these topics are data-driven systems, AI and cloud computing. Commercial providers are offering cloud computing and AI resources, however, in many situations these are ill fit for teaching activities as they are complex for early learners, are problematic due to GDPR, make teaching material obsolete by rapidly changing their UIs and when scaled add a significant cost. Therefore, there is an unmet need for better cloud-like infrastructures which can host sandbox software and datasets for teaching to improve onboarding and retention of students.

The universities have or are building new computing resources for research and teaching. So far, the primary focus has been on research in the form of e-science initiatives (e.g. SDU e-Science Center UCloud or AAU CLAUDIA) or e-infrastructure (e.g. DEIC) providing services with a general focus on all sciences. However, there is a need to complement or customise these services with offers for teaching in digital technologies. The aim is to improve the Danish software infrastructure for teaching in digital technologies by coordinating cross-institutional development of software infrastructure for teaching including software toolkits, access to data sandboxes and access to the Danish national DeiC Type1 HPC for educational cloud computing.

The aim is to improve onboarding and retention of students result in an ability to teach more students and lower dropout rates.

February 1, 2021 – January 31, 2023 – 2 years.

Total budget DKK 5,63 million / DIREC investment DKK 0,88 million

Participants

Project Manager

Ulrik Nyman

Associate Professor

Aalborg University
Department of Computer Science

E: ulrik@cs.aau.dk

Project Manager

Jakob Lykke Andersen

Associate Professor

University of Southern Denmark
Department ofMathematics and Computer Science

E: jlandersen@imada.sdu.dk

Partners

Categories
Educational project

Learning Technology for Improving Teaching Quality at Scale

Project type: Educational Project

Learning Technology for Improving Teaching Quality at Scale

Teaching quality and student feedback is negatively impacted by lack of teachers and many students. There is a need to consider how learning technologies can help improve teaching quality and student feedback both in physical and digital learning environments. The resources for teaching at universities are being reduced and we experience challenges in current technology such as MOOCs (which is at scale).

Within the educational programs digital learning tools have been developed and utilised for many years, e.g. for video lectures, automated correction of exercises, and automated multiple-choice exams etc. However, it does not substitute direct teacher-to-student supervision and the need for teachers to constantly develop existing and new courses to meet the standards.

Scale teaching methods for both physical and digital teaching environments to higher number of students via digital learning technology and a combination of face2face learning, student driven learning and digital learning technology.

Increasing the teaching quality at scale with learning technology will enable educational programs to educate more students and improve retention.

February 1, 2021 – January 31, 2023 – 2 years.

Total budget DKK 5,52 million / DIREC investment DKK 0,84 million

Participants

Project Manager

Md Saifuddin Khalid

Associate Professor

Technical University of Denmark
DTU Compute

E: skhalid@sdu.dk

Niels Aske Lundtorp Olsen

Assistant Professor

Technical University of Denmark
DTU Compute

Partners

Categories
Educational project

Supporting Diversity via inclusive Teaching/Learning Activities

Project type: Educational Project

Supporting Diversity via inclusive Teaching/Learning Activities

The mix of students in digital technology is low in diversity (e.g. female students). This is a problem on a societal level which also impacts the study environment.

The partners have already implemented a range of initiatives to address the problem. ITU has several initiatives targeting both recruitment, onboarding, and retention of female students. In the project “Øget diversitet på de teknisk-naturvidenskabelige it-uddannelser” lead by It-vest, the three universities AU, AAU, and SDU are collaborating to implement new initiatives.

Establish inclusive teaching/learning activities that support diversity; e.g., by supporting recruitment, onboarding, and retention of female students. The initiatives will take inspiration from established programs (e.g., Boot-IT & IT-Camp at ITU, Open Innovation X, HealthTech), but – as a unique element – favor scenarios and domains with a stronger appeal to women as well as emphasize inclusion, interaction, and collaboration over competition.

Increase the diversity of students in the educational programmes.

January 1, 2021 – January 31, 2023 – 2 years.

Total budget DKK 6,77 million / DIREC investment DKK 1,01 million

Participants

Project Manager

Claus Brabrand

Associate Professor

IT University of Copenhagen
Department of Computer Science

E: brabrand.itu.dk

Bjørn Hjort Westh

Research Assistant

IT University of Copenhagen
Department of Computer Science

Aisha Umair

Associate Professor

University of Southern Denmark
The Maersk Mc-Kinney Moller Institute

Partners

Categories
News

Explainable AI to increase hospitals’ use of AI

26 November 2021

Explainable AI to increase hospitals' use of AI

In a new DIREC project, AI researchers are collaborating with hospitals to create more useful AI and AI algorithms that are easier to understand.

AI (artificial intelligence) is gradually gaining ground in assistive medical technologies such as image-based diagnosis, where artificial intelligence analyzes CT scans with superhuman precision. AI, on the other hand, is rarely designed as a collaborator for healthcare professionels.

In a new human-AI project EXPLAIN-ME – supported by the national research center DIREC, AI researchers together with medical staff will develop explanatory artificial intelligence (Explainable AI – XAI) that can give clinicians feedback when training in hospitals training clinics.

“In the Western world, about one in ten diagnoses is judged to be incorrect, so patients do not get the right treatment. The explanation may be due to a lack of experience and training. Our XAI model will help the medical staff make decisions and act a bit like a mentor who gives advice and response when they train,” explains Professor at DTU Compute and Project Manager Aasa Feragen.

In the project, DTU, the University of Copenhagen, Aalborg University, and Roskilde University collaborate with doctors at the training and simulation center CAMES at Rigshospitalet, NordSim at Aalborg University Hospital, and oncologists at the Department of Urology at Zealand University Hospital in Roskilde.

Ultrasound scan of pregnant women


At CAMES, DTU and the University of Copenhagen will develop an XAI model that looks over the shoulder of doctors and midwives when they ultrasound scan ‘pregnant’ training dolls at the training clinic.

In the field of ultrasound scanning, clinicians work on the basis of specific ‘standard plans’, which show different parts of the fetus’ anatomy to make it easier to see and react in case of complications. The rules are implemented in the XAI model, which is integrated into a simulator that gives the doctor ongoing feedback.

“It would be great if XAI could help less trained doctors to do scans that are on a par with the highly trained doctors.”
Professor and Projekt Manager Aasa Feragen

The researchers train the artificial intelligence on real data from Rigshospitalet’s ultrasound scans from 2009 to 2018, and it is primarily images from the common nuchal scan and malformation scans that are offered to all Danish pregnant women approximately 12 and 20 weeks into the pregnancy. When the XAI models will be ready to use at the training clinic, first they have to check whether the model also works in the simulator, since the EAI model is trained on real data, while the training doll is artificial data.

According to doctors, the quality of ultrasound scans and the ability to make accurate diagnoses depends on how much training the doctors have received.

“If our model can tell the doctor during the scan that a foot is missing in the picture, the doctor may be able to learn faster. If we get the XAI model to tell us that the probe on the ultrasound device needs to be moved a bit to get everything in the picture, then maybe it can be used in medical practice as well. It would be great if XAI could help less trained doctors to do scans that are on a par with the highly trained doctors,” says Aasa Feragen.

Research associate professor and head of CAMES’ research team for artificial intelligence Martin Grønnebæk Tolsgaard emphasizes that many doctors are interested in getting help from AI technology to find the best treatment for patients. Here is explainable AI the way to go.

“Many of the AI models that exist today do not provide very good insight into why they come to a particular decision. It is important for us to become wiser on that. If the model does not explain why it comes to a given decision, then clinicians do not believe in the decision. So if you want to use AI to make clinicians better, then we need good explanations, like Explainable AI.”

Ongoing feedback on robotic surgery


Robotic surgery allows surgeons to perform their work with more precision and control than traditional surgical tools. It reduces errors and increases efficiency, and the expectation is that AI will be able to improve the results further.

In Aalborg, the researchers will develop an XAI model that supports the doctors in the training center NordSim, where both Danish and foreign doctors can train surgery and operations in simulators on e.g. pig hearts. The model must provide ongoing feedback to the clinicians while they are training an operation without interfering, says Mikael B. Skov, professor at Department of Computer Science at Aalborg University:

“Today, it is typically the case that you only get to know if you should have done something different when you have finished training an operation. We would like to look at how you can come up with this feedback more continuously to better understand whether we have done something right or wrong. The feedback should be done in such a way that the people learn faster and, at the same time, make fewer mistakes before they have to go out and do real operations. We, therefore, need to look at how to develop different types of feedback, such as warnings without interrupting too much”.

Image analysis in kidney cancer


Doctors often have to make decisions under time pressure, e.g. in connection with cancer diagnoses to prevent cancer from spreading. A false-positive diagnosis, therefore, could cause a healthy kidney removed and other complications to be inflicted. Although experience shows that AI methods are more accurate in assessments, clinicians need a good explanation of why the mathematical models classify a tumor as benign or malignant.

In the DIREC project, researchers from Roskilde University will develop methods in which artificial intelligence analyzes medical images for use in diagnosing kidney cancer. Clinicians will help them understand what feedback is needed from the AI models to balance what is technically possible and what is clinically necessary.

“It is important that the technology can be included in the hospitals’ practice, and therefore we focus in particular on designing these methods within ‘Explainable AI’ in direct collaboration with the doctors who actually use it in their decision-making. Here we draw in particular on our expertise in Participatory Design, which is a systematic approach to achieve the best synergy between what the AI researchers come up with in terms of technological innovations and what doctors need,” says Henning Christiansen, professor in computer science at the Department of People and Technology at Roskilde University.

About DIREC – Digital Research Centre Denmark

The purpose of the national research centre DIREC is to bring Denmark at the forefront of the latest digital technologies through world-class digital research. To meet the great demand for highly educated IT specialists, DIREC also works to expand the capacity within both research and education of computer scientists. The centre has a total budget of DKK 275 million and is supported by the Innovation Fund Denmark with DKK 100 million. The partnership consists of a unique collaboration across the computer science departments at Denmark’s eight universities and the Alexandra Institute.

The activities in DIREC are based on societal needs, where research is continuously translated into value-creating solutions in collaboration with the business community and the public sector. The projects operate across industries with focus on artificial intelligence, Internet of Things, algorithms and cybersecurity among others.

Read more at direc.dk

EXPLAIN-ME

Partners in the project EXPLAIN-ME: Learning to Collaborate via Explainable AI in Medical Education

  • DTU (DTU Compute – Department of Mathematics and Computer Science)
    University of Copenhagen
  • Aalborg University
  • Roskilde University
  • CAMES – Copenhagen Academy for Medical Education and Simulation at Rigshospitalet in Copenhagen
  • NordSim – Center for skills training and simulation at Aalborg University Hospital
  • Department of Urology at Zealand University Hospital in Roskilde

Project period: 1 October 2021 to 30 April 2025

Contact: 
Aasa Feragen
DTU Compute
M: +45 26 22 04 98
afhar@dtu.dk

Anders Nymark Christensen
DTU Compute
+45 45 25 52 58
anym@dtu.dk

Categories
Explore project

Verifiable and Robust AI

Project type: Explore Project

Verifiable and Robust AI

The challenge to the research community is how to extend existing verification technologies to cope with software systems comprising AI components (see report of the Dagstuhl Seminar “Machine Learning and Model Checking join Forces” 2018). This is an unchartered territory and one of the most pressing research challenges in AI. The industrial importance of this topic is closely related to the question of liability in case of malfunctioning products. Over a 4-month period the explore project will provide a state-of-the-art survey and identify research directions to be followed.

Participants

Project Manager

Kim Guldstrand Larsen

Professor

Aalborg Universlty
Department of Computer Science

E: kgl@cs.aau.dk

Thomas Dyhre Nielsen

Professor

Aalborg Universlty
Department of Computer Science

Manfred Jaeger

Associate Professor

Aalborg Universlty
Department of Computer Science

Andrzej Wasowski

Professor

IT University of Copenhagen
Department of Computer Science

Rune Møller Jensen

Associate Professor

IT University of Copenhagen
Department of Computer Science

Peter Schneider-Kamp

Professor

University of Southern Denmark
Department of Mathematics and Computer Science

Jaco van de Pol

Professor

Aarhus University
Department of Computer Science

Thomas Hildebrandt

Professor

University of Copenhagen
Department of Computer Science

Alberto Lluch Lafuente

Associate Professor

Technical University of Denmark
DTU Compute

Flemming Nielson

Professor

Technical University of Denmark
DTU Compute

Thomas Bolander

Professor

Technical University of Denmark
DTU Compute

Thomas Asger Hansen

Head of Analytics and AI

Grundfos

Christian Rasmussen

Senior Manager Data Analytics

Grundfos

Malte Skovby Ahm

Research and business lead

Aarhus Vand

Partners