Computer science and engineering

Computer science and engineering

The research in computer science and engineering includes both practical and theoretical aspects of data processing and applications, as well as implementation of such systems. We focus on two areas: data science and parallel computer systems.

We study and develop methods and technologies for collecting, representing, storing, processing, and analyzing data in the data science area. We are also interested in how data can be used for prediction, classification, and pattern recognition. Our research is primarily in machine learning, data mining, big data, planning and scheduling, as well as optimization. We apply our methods in the areas decision support, image processing, analysis of historic documents, the health sector, transport and logistics, as well as anomaly and intrusion detection.

In the area of parallel computer systems we study computer systems with multiple processing units (processors), e.g., multi-core systems, distributed systems, cloud based systems, GPUs, and heterogeneous systems. The area includes methods and technologies for design, implementation, and analysis of parallel systems, in order to achieve qualities such as correctness, performance, robustness, scalability, high resource utilization, low energy consumptions. The research includes hardware aspects, as well as system and application software, and the interaction between hardware and software. The application focus is primarily algorithms and methods from the data science area, e.g., algorithms for machine learning, data mining, pattern recognition, and large scale analysis of data images.

The research in computer science and engineering is mainly conducted at the Department of Computer Science and Engineering.



Intelligent transportation systems

Research in the field of intelligent transportation systems involves the integration of electronic road tolls and how rail traffic can be re-scheduled when disturbances occur. The focus lies on transportation policy analysis, simulations, development of search algorithms and finding sustainable transportation solutions.

Distributed systems

In the distributed systems field architecture of multiprocessors and data in the cloud (a technology based on the use of computers over the Internet) are studied. Another area is the artificial intelligence and human-machine interaction. The focus is on various cloud services and applications in social networks.


In the security research field machine learning techniques and anomaly detection (finding patterns in data that do not conform to an established “normal” behavior) are used to analyze irregularities in large sets of data. The focus is to identify and correct weaknesses in the police- and defense fields, industrial applications and among end users.

Example of projects

Big data

BigData@bth – Scalable resource-efficient systems for big data analytics

Data will be generated at an ever-increasing rate for the foreseeable future. Added value and cost savings can be obtained by analyzing big data streams. The analysis of large data sets requires scalable and high-performance computer systems. In order to stay competitive and to reduce consumption of energy and other resources, the next generation systems for scalable big data analytics need to be more resource-efficient. The research profile, Scalable resource-efficient systems for big data analytics, combines existing expertise in machine learning, data mining, and computer engineering to create new knowledge in the area of scalable resource-efficient systems for big data analytics. The value of the new knowledge will be demonstrated and evaluated in two application areas (decision support systems and image processing).

The needs and interests of our 9 industrial partners are grouped into industrial challenges. Based on these challenges and in cooperation with our partners we have defined initial sub-projects grouped into four research themes:

  • Research theme A: Big data analytics for decision support
  • Research theme B: Big data analytics for image processing
  • Research theme C: Core technologies (machine learning)
  • Research theme D: Foundations and enabling technologies

Funding: The Knowledge Foundation (KK-stiftelsen) 2014-2020

Partners: Arkiv Digital AD, Compuverde, Contribe, Ericsson, Indigo IPEX, Noda Intelligent Systems, Telenor Sverige, Sony Mobile Communications, and Maingate Enterprise Solutions

Contact person
: Håkan Grahn,


CLOUDTEST is a research project on the use of cloud technologies to reduce costs and energy consumption associated with the testing of large telecommunication systems. Today, hundreds of test servers, including at Ericsson, are used to test telecommunications systems. These servers are expensive to purchase and maintain, and consume a lot of energy. The goal of the project is to develop techniques and methods to enable the development of a “cloud” of virtual test servers. The idea is for multiple virtual test servers to share the same physical server and that the test cloud can be used by developers in different places all over the world. This technology will reduce both costs and energy consumption. The project is partly financed by the Swedish Knowledge Foundation (KKS).

BTH is working together with Ericsson Karlskrona and ILT Innovations AB on this CLOUDTEST project, funded by KKS.

Contact person: Lars Lundberg

Efficient rescheduling of train traffic (EOT)

The EOT project aims to develop and evaluate documented support for the traffic controller when rescheduling train traffic, using parallelisation of an optimisation-based search algorithm. In other words, the support aims to provide a number of efficient proposals on how the trains are to run, despite changing conditions.

An important part of the project is to analyse how the suitability of the proposals can be assessed and compared in order to facilitate selection and adjustment of the solution for the traffic controller.

Funder: The Swedish Transport Administration
Contact person: Johanna Törnquist

Computer-based support to increase knowledge about serial crimes

Computer-based support to increase knowledge about crimes of a serial nature.

Funder: The European Development Fund 2012–2014
Collaborative partner: The Swedish Police
Contact person: Niklas Lavesson