Computer science and engineering

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

Specialisations

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.

Security

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.

Research environment

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, hakan.grahn@bth.se

Example of projects

Bonseyes

The Bonseyes project aims to develop a platform consisting of a Data Marketplace, Deep Learning Toolbox, and Developer Reference Platforms for organizations wanting to adopt Artificial Intelligence in low power IoT devices (“edge computing”), embedded computing systems, or data center servers (“cloud computing”). It will bring about orders of magnitude improvements in efficiency, performance, reliability, security, and productivity in the design and programming of Systems of Artificial Intelligence that incorporate Smart Cyber Physical Systems while solving a chicken-egg problem for organizations who lack access to Data and Models. It’s open software architecture will facilitate adoption of the whole concept on a wider scale.

Read more about the project

AgileSec – Agile Development of Security Critical Software

Today, the software industry is moving to agile development processes. One of the main ideas is that an agile team has sufficient skills to get the job done, and does not have to rely on external experts. In traditional software development, security issues are handled by experts. However, in agile development, security issues should be handled by the team. The agile process must, therefore, be extended with security related quality control and support. Rigorous quality control may, however, reduce productivity. The level of security expertise may differ significantly from one agile team to another, and it is, therefore, important to adapt security related quality control to the security maturity level of the team. In this application, we argue that an accurate estimate of a team's security maturity would be helpful in many ways.

Read more about the project

TRANS-FORM – Smart transfers through unraveling urban form and travel flow dynamics

Smart cities and communities rely on efficient, reliable and robust transport systems. Managing urban public transport systems is becoming increasingly challenging with a pronounced shift towards multiply actors operating in a multi-modal multi-level networks. This calls for the development of an integrated passenger-focused management approach which takes advantage of multiple data sources and state-of-the-art scheduling support.

TRANS-FORM, a cooperation between universities, industrial partners, public authorities and private operators, will develop, implement and test a data driven decision making tool that will support smart planning and proactive and adaptive operations. The tool will integrate new concepts and methods of behavioural modelling, passenger flow forecasting and network state predictions into real-time operations.

Read more about the project

FLOAT: Real-time decision support for railway traffic management

This project is financed by Trafikverket and is a continuation of the previous research projects OAT+ and EOT (both financed by Trafikverket). Researchers working in the project are currently Ph D student Sai Prashanth Josyula, Post-Doc Omid Gholami and Associate Professor Johanna Törnquist Krasemann, BTH.

Read more about the project

CCC – Center for Computational Criminology

Within the Center for Computational Criminology (CCC) at Blekinge Tekniska Högskola (BTH), research and collaboration have been conducted with law enforcement agencies, mainly the police since 2012. The work was funded by the Swedish Agency for Growth between 2012-2014, by Blekinge Region in 2015 and by Vinnova in 2016 . The purpose of the work of the CCC is to investigate, develop and evaluate automated methods to simplify criminal investigations within law enforcement agencies.

Read more about the project

CONVINcE

CONVINcE addresses the challenge of reducing the power consumption in IPbased video networks with an end-to-end approach, from the Head End where contents are encoded and streamed to the terminals where they are consumed, embracing the Content Delivery Networks (CDN) and the core and access networks. Energy saving is a key challenge for the European Union and the CONVINcE project contributes to win this challenge. CONVINcE helps the European industry to develop new solutions and products reducing the energy footprint of video delivery networks. The double effect gained is to reduce the energy consumption in Europe and to boost the competiveness of the European industry in the area addressed by the CONVINcE project.

Read more about the project

Computer science and engineering