Infrastructure
The Department of Computer and Systems Sciences has several infrastructures for research. Among other things, we have databases, GPUs and lab environments.
AI Compute Hub
The Department of Computer and Systems Sciences (DSV) maintains a growing and diverse Graphics Processing Unit (GPU) infrastructure. It supports a wide range of AI-related research and education.
The current environment includes several high-performance servers equipped with a total of 17 GPUs, including recent additions such as Mimer (delivered in 2023) featuring eight Nvidia A5500 cards, alongside other systems with Titan RTX and 2080Ti GPUs. These machines provide substantial computational capacity, backed by multi-core AMD processors, large memory configurations, and high-speed NVMe storage, to meet the demands of modern AI workloads.
The infrastructure is continuously monitored, maintained, and updated to ensure reliability and performance. It serves not only DSV’s AI research community, but also master’s students engaged in thesis projects and advanced courses in AI and Data Science, providing them with hands-on access to state-of-the-art computing resources.
Access to the infrastructure is available to DSV researchers as well as collaborators within Stockholm University. External researchers may also gain access through formal research collaborations or agreements, subject to resource availability and security guidelines.
The Department of Computer and Systems Sciences (DSV) hosts a digital forensics lab, connected to the research subject of cybersecurity.
Digital forensics involves collecting and analysing digital traces, for example from chats on a suspect’s phone. Digital evidence must be produced and handled in a way that is legally sound.
The lab includes equipment related to the internet of things (IoT). It also has tools for examining mobile phones. PhD students and researchers with expertise in the field can use the lab to study IoT devices and other embedded computer systems in detail, in order to identify traces of usage.
Contact professor Stefan Axelsson
Distributed Immersive Participation Lab
The Distributed Immersive Participation Lab is dedicated to advancing research, education, and industry collaboration in IoT, edge computing, distributed data processing, tiny machine learning, inclusive design, distributed edge intelligence and immersive participation. It is located to the Department of Computer and Systems Sciences (DSV), Campus Kista. The lab welcomes students, researchers, and industry professionals who would like to experiment, collaborate, and develop groundbreaking solutions that drive technological progress.
Swedish Health Record Research Bank
Swedish Health Record Research Bank (or “Health Bank” for short) is a unique research infrastructure containing large sets of electronic patient records. For example, the Stockholm EPR (Electronic Patient Record) Corpus. The corpus contains data from over 512 clinical units – more than two million patients – at Karolinska University Hospital.
Stockholm EPR Corpus stems from the TakeCare electronic patient records system that is used at the Karolinska University Hospital. All patient records are deidentified. This big data corpus contains both structured information and unstructured information. The structured information contains a serial number for each patient, age, gender, ICD-10 diagnosis codes, drugs but also lab and blood values as well as admission and discharge time and date. The unstructured data contains text written under different headings. The whole corpus contains over 3 227 million tokens.
Health Bank is used and has been used in a number of research projects carried out by the Natural Language Processing Research Group. The research is approved by the Regional Ethical Review Board in Stockholm (Regionala Etikprövningsnämnden i Stockholm) and the Swedish Ethical Review Authority (Etikprövningsmyndigheten) under various research plans.
Natural Language Processing Research Group
We have developed a number of clinical text mining tools based on the Stockholm EPR Corpus.
Clinical text mining tools
Contact: Hercules Dalianis, Professor, Director Health Bank
For reference to the Health Bank, please use: Dalianis, H., A. Henriksson, M. Kvist, S. Velupillai and R. Weegar. 2015. HEALTH BANK – A Workbench for Data Science Applications in Healthcare (pdf). Proceedings of the CAiSE-2015 Industry Track co-located with 27th Conference on Advanced Information Systems Engineering (CAiSE 2015), J. Krogstie, G. Juell-Skielse and V. Kabilan, (Eds.), Stockholm, Sweden, June 11, 2015, CEUR, Vol-1381, pp 1-18, urn:nbn:de:0074-1381-0.
Last updated: November 21, 2025
Source: Department of Computer and Systems Sciences, DSV