The research group Data Intensive Software Technologies and Applications (DISTA) studies data-driven approaches such as:
- Machine learning (ML) and artificial intelligence (AI) use (big) data to automate tasks such as reasoning, planning, deciding, and predicting.
- Software and information analysis consider the IT systems as data and reflects on their quality.
- Scalable computing technologies allow coping with the volume of big data sets and the velocity of big data streams.
Altogether, data-intensive technologies are enablers for turning data into information and actionable knowledge, that automate the implementation of smarter systems or even generate components of these systems.
Machine learning and artificial intelligence
With the concept of decision algebras, DISTA has suggested a unifying theory for classification approaches. With the concept of aggregation that condenses multi-dimensional, partially ordered data to a totally ordered score, DISTA has opened a new branch of unsupervised machine learning.
Our research also focuses on applying technologies such as statistical concepts, supervised and unsupervised learning, classification, regression, clustering, etc., to real-world problems in engineering, science, and society.
Software and information analysis ...
... assesses software engineering artifacts such as processes, specifications, documentation, and code. This may be estimating the effort of developing and maintaining software, getting new users to understand software structure and behavior, finding dependencies and changing impact of sub-systems, assessing the software quality, and finding the relevant components for re-engineering, etc.
DISTA pioneered the application of measurement and testing techniques to assure information quality (IQ). With our industry partners, Sigma Technology and Softwerk, DISTA have applied this quantitative approach to IQ to numerous real-world documentations.
Scalable computing technologies ...
... such as parallel computing, refers to technologies enabling scalability of systems to large problems or data sets, e.g., by executing a program on more than one processor or core. We are interested in high-performance computing, distributed computing, and stream processing as used in e.g. scientific and technical data mining.
With context-aware composition, a technique for self-optimizing software systems based on profiling data and ML, and with the first ever fully block-free garbage collector, we have significantly contributed to scalable computing.
Connection to Linnaeus University Centre for Data Intensive Sciences and Applications (DISA)
The Linnaeus University Centre for Data Intensive Sciences and Applications (DISA) is one of the university’s profiled research areas. DISA studies open questions in the collection, analysis, and use of large data sets. With its core in computer science, it takes a multidisciplinary approach and collaborates with researchers from e.g. forestry, mechanical engineering, and e-health. The DISTA research group contributes to the DISA core technologies enhancing e.g. machine learning and scalable computing.
We directly contribute to the DISA research areas of
- AdaptWise with context-aware composition,
- e-health with computer vision and deep learning for the analysis of human motions used in eldercare and high-performance sports, and with efficient data selection preprocessing methods for medical researchers,
- Forestry with computer vision and deep learning for the analysis of ancient remains to avoid forestry activities there, and for the identification of log fingerprints, and with deep learning for strength grading of sawn timber,
- Smart industry with data analysis and machine learning for predictive maintenance, and
- Digital humanities with the Nordic Tweet Stream providing high-quality data for research in the languages used in Scandinavia.
As an essential part of this research, we build and maintain the High-Performance Computing Center (HPCC) of DISA.
Connecting with industry and society's research needs, we have established and organized the industry graduate school Data Intensive Applications (DIA).
At DISA, we encourage and support seed projects. Seed projects are intended to promote and nurture excellent research, development, and innovation within data-intensive sciences and applications with cross-discipline collaboration.
Seed projects with DISTA contributions:
- Smart-Troubleshooting in the Connected Society (2018)
- Developing the Skeleton Avatar camera Technique (SAT) as a rapid, valid and sensitive measurement of mobility in COPD patients treated in primary care (2019, 2020)
- European spruce bark beetles; advanced predictive forecasting by means of machine learning (2019)
- Vibration-based strength grading of sawn timber using piezoceramic transducers and one-dimensional convolutional neural networks (2020)
- User performance data from a video-based application/platform to enhance mobility and integrated learning in physical activities of daily living amongst older adults (2020).
- Digitized ancient remains detection using computer vision and artificial intelligence (2021)
Connection to Smarter Systems
Smarter Systems is a complete knowledge environment focusing on systems and systems engineering. Engineering modern computing systems is complex and operates in uncertain and continuously changing environments. Both systems and the way we engineer them must become more intelligent. That is, they need to adapt and evolve through a perpetual process that continuously improves their capabilities, to deal with the uncertainties and change they face.
Humans learn from experience – machines from data. Hence, data-intensive technologies are core to make systems more intelligent. In addition to the contributions to these technologies, e.g. in machine learning and scalable computing, DISTA contributes to three challenges of Smarter Systems:
- Software technology processes and tools putting together data-driven technologies for smarter engineering of smarter systems.
- Verified guarantees of applications based on data-driven models regarding the accuracy, performance, response time, safety, etc., persisting over time.
- Understanding data-driven models for mastering data-driven applications and for turning artificial back into human intelligence.
Connection to education
DISTA is responsible for the following courses:
- 2DV516, Introduction to Machine Learning, 7,5 credits
- 2DV605, Parallel Computing, 7,5 credits
- 2DV50E, BSc Thesis, 15 credits
- 4DV507, Code transformation and interpretation, 5 credits
- 4DV652, Project in Data Intensive Systems, 10 credits
- 4DV657, Parallel Computing, 5 credits
- 4DV660, Statistical and Machine Learning, 5 credits
- 4DV661, Deep Machine Learning, 5 credits
- 4DV50E, MSc Thesis, 15 credits
- 5DV50E, MSc Thesis, 30 credits
Doctoral project: Advanced identification methods for the forest industry through CV/AI The project intends to create opportunities for continued digitalisation in the forest industry. This concerns…
Doctoral project: Big Data Exploitation for Insight into Electrolux Professional Products Lifecycle Management This doctoral project aims to use Big Data to map the life cycle of professional products…
Doctoral project: Digital twin developments within Volvo CE This doctoral project relates to develop a so-called digital twin platform. The aim is to understand customers' problems and support them…
Doctoral project: Ecosystems and smart cities Cities face major climate challenges. In my research, I investigate how digital transformation and ecosystems contribute to increased collaboration…
Doctoral project: Efficient detection of changes in software evolution and their operationalization for software maintenance This project aims at understanding and using changes detected in software…
Doctoral project: Machine Learning in Manufacturing Many manufacturing companies struggle with transitioning into the era of smart technologies, due to the fact that modern lab-grown methods and data…
Project: In-line visual inspection using unsupervised learning The purpose of this project is to introduce and improve machine learning- assessment of the quality of massproduced industrial (steel)…
Project: SciChallenge Using digital technologies and social media, the SciChallenge project will create a competition to engage more young people in Europe in the areas of natural science, technology…
Project: Software Technology for Self-Adaptive Systems The purpose of this project is to increase the engineering efficiency of self-adaptive systems. The development, maintenance and operation of…
- New revolutionary technology to discover problems in industrial production News
- Increased growth potential for companies in the Linnaeus region through new project using artificial intelligence and high-performance computer programs News
- Strengthen your company’s development journey with an externally-employed doctoral student in AI/Computer/IT News
- Industrial doctoral student conducts research from the factory floor News
- Anna Wingkvist Research advisor
- +46 470-70 89 93
- Daniel Toll Lecturer
- +46 480-49 77 09
- Felix Viberg
- Joel Cramsky
- Jonas Lundberg Senior lecturer
- +46 470-70 89 67
- Jonas Nordqvist Associate senior lecturer
- +46 470-70 84 13
- Manoranjan Kumar
- Mathias Hedenborg
- +46 470-70 86 38
- +46 76-760 36 65
- Morgan Ericsson Associate professor, head of department
- +46 470-76 78 72
- +46 72-594 17 48
- Rakhshanda Jabeen
- Sebastian Hönel Doctoral student
- Tobias Ohlsson Senior lecturer
- +46 480-49 77 08
- Welf Löwe Professor
- +46 470-70 84 95
- +46 76-760 36 62
External doctoral students
- Oleg Danylenko (Klarna)
- Erik Österlund (Oracle)