Big Data Fusion (BISON)
The project addresses societal and industrial problems in achieving value through improved decision-making from the rapidly increasing volume of digital data. It employs information fusion as the governing decision technology and the principal application areas are bio-informatics and telecommunications. The four-year work programme, examines the research question: How can big data fusion enable reliable exploratory and predictive modelling on big data for the purpose of decision support?
The underlying decision support model (problematisation, big data fusion, exploratory analysis, predictive modelling, and interpretation) underpins three scientific sub-projects in Bioinformatics, Business Intelligence and Operational Decision Support. The collaborating partners are the University of Skövde, Takara Bio Europe, AstraZeneca, Advectas and Huawei.
The Knowledge Foundation, industrial partners and the University of Skövde funded the project with 29.8 million SEK during 2015–2019.
Picking the Winners: Forecasting Emergent Technology
This project brings together a unique combination of techniques from the research fields of Information fusion, bibliometrics/altmetrics, and topic modeling/text analytics in order to further advance the state-of-the-art within trend analytics / forecasting.
Information Fusion Research Program
Information fusion is the synergistic integration of information from different sources about the behavior of a particular system, to support decisions and actions relating to the system. Information fusion includes theory, techniques and tools for exploiting the synergy in the information acquired from multiple sources, for example sensors observing system behavior, databases storing knowledge about previous behavior, simulations predicting future behavior and information gathered by humans.
Within the Information Fusion Research Program, SAIL was responsible for the Ground Situation Awareness scenario (GSA), consisting of four projects, involving six PhD students and five senior researchers from both academia and industry.
Uncertainty Management in Information Fusion (UMIF)
Building on the Information Fusion research program, the goals of UMIF were to explore, compare and develop existing uncertainty management methods in high-level information fusion. UMIF focused on three research areas: Uncertainty management methods, Impact analysis and anomaly detection, and Visualization and user interaction. Six researchers from SAIL were involved in all three research areas, leading six of the eight work packages of the project.
The Knowledge Foundation, industrial partners and the University of Skövde funded the project with 16.64 million SEK during 2011–2013.
Information Fusion for Decision Support and Human System Interaction in Future Platforms
The project studied how information fusion, i.e. synergetic integration of available data and information, could be used to offer advanced decision support for tactical air unit cooperation in future aircraft platforms. The project addressed two main issues: Human System Interaction and Tactical support with situation analysis. The project involved two senior researchers and two PhD students at SAIL.
The Swedish Governmental Agency for Innovation Systems (VINNOVA), Saab Aeronautics (coordinator) and the University of Skövde funded the project with 17.7 million SEK during 2009–2013.
Pragmatic Patterns for Clinical Knowledge Management
Building on the SOMWeb project, the overall goal of this project was to obtain further knowledge of how pragmatic patterns for clinical knowledge management that support evidence-based health care should be modeled, implemented, and introduced into clinical practice. More specifically, the project addressed the question of how to design clinical computer-supported tools in which the use of information and the context of knowledge processes are in focus, while a solid foundation in formal knowledge representation and reasoning is maintained. The project consisted of two sub-projects: 1) Web-based knowledge sharing and dissemination based on techniques from the Semantic Web and 2) Decision-support for oral medicine based on formalization of clinical examination data and clinical knowledge processes.
The project was a collaboration between the University of Skövde (coordinator), University of Gothenburg (GU), the Sahlgrenska Academy at GU and Chalmers University of Technology (CTH). One senior researcher and one PhD student at SAIL participated in the project together with two senior researchers, one PhD student and two project assistants at GU/CTH.
The Swedish Governmental Agency for Innovation Systems (VINNOVA) and the three universities funded the project with 6.6 million SEK in total (2.6 million SEK and 4 million SEK, respectively) during 2006–2009.
SOMWeb – Net-based Knowledge Management as Support for Clinical Practice and Knowledge Sharing
SOMWeb aimed to obtain further knowledge about how interactive, user-centred knowledge-based systems supporting evidence-based medicine should be designed, implemented and introduced in the daily clinical work. The work on achieving the this aim was divided into three partially overlapping objectives: 1) The formalisation of clinical processes and knowledge, 2) the development of web services for medicine, and 3) the construction of an intelligent web-based community of practice, CoP. The formalisation and development of services used ontology engineering and techniques from the Semantic Web. To provide rapid prototyping and deployment of applications in daily clinical work, and to support the harmonisation of clinical processes and knowledge within medicine, the project was carried out in close collaboration with clinicians. The project was a collaboration between Chalmers University of Technology (CTH, coordinator), the University of Skövde, University of Gothenburg (GU) and the Sahlgrenska Academy at GU. One senior researcher and one PhD student at SAIL participated in the project together with two senior researchers and two project assistants at GU/CTH.
The Swedish Governmental Agency for Innovation Systems (VINNOVA) funded the project with 2.9 million SEK during 2003–2006.
NOVA – New Opportunities through Visual Analytics for Big Data
In many occasions, decision-makers have to analyze large amounts of data. Intelligent support systems try to aid analysts to reach effective decisions, while handling large amounts of data. However, in complex cases, the users have difficulties reasoning about the system behavior, leading to mistrust and misuse of such systems. To mitigate the lack of intelligibility, explanations and representations of the inner workings and outcomes of the data-mining modules can be used. But, how do we present the inferences made by intelligent support systems and their inner workings to users? Is it actually beneficial to show inner workings and detailed information regarding the data mining modules? If so, to which costs?
In NOVA, we focused on the interpretability challenge, investigating which level of information abstraction is necessary for effective problem solving tasks. Empirical studies with experts from the partner companies, Combitech AB (network security and logistics) and Takara Bio Europe AB (gene regulatory systems) were carried out.
The project was a collaboration between the University of Skövde, Combitech AB and Takara Bio Europe AB. The Knowledge Foundation, industrial partners and the University of Skövde funded the project during 2015–2017.
Human-machine interaction for distributed decision-making
The project will study distributed decision-making for advanced decision support for tactical air unit cooperation in future aircraft platforms with focus on:
Human-machine interaction (HMI: How should distributed decision support be interacted with and displayed? What information will be distributed over platforms and how should that be displayed and controlled? Sharing of displayed information?
Tactical support with situation analysis: How should threats be analyzed, based on parameters such as proximity, kinematics, identity and ability to act? Based on situation analysis, suggest ownership and group actions regarding maneuvering and the use of sensors. How should information de distributed within a tactical air unit to optimize situation analysis?
The Swedish Governmental Agency for Innovation Systems (VINNOVA) is funding the project with 7.3 million SEK over 4 years within the National Avionics Research Program (research grant NFFP6-2013-01201). Aeronautics (Saab AB) provides an equal amount and the University of Skövde provides another 1 million SEK, with a total funding of 15.5 million SEK during 2013–2018.
Information and Data Science (IDS)
The project Information and Data Science (IDS) focuses on developing and evaluating methods for advanced data analysis for various types of data such as measurement- and text data.
More specifically, the project focuses on methods for identifying different types of patterns in the data, e.g., clusters, and capture how these patterns evolve over time. Methods from the research area of deep learning and different types of statistical methods will be studied. The project has two main scenarios for evaluation: (1) trend analysis based on text data, and (2) analysis of data in the area of "sports analytics", more specifically data collected from golf swings. Within the project we will also explore different methods to visually explore the identified patterns from the data.
DataFlow – Finding patterns in new data flows
Swedish metal industry has access to huge amounts of data, from internal databases, sensors and simulations as well as from external data collected from the Web, magazines, scientific publication databases, and future reports etc. There's also the ability to connect to more informal data streams such as forums and blogs. Today, technology can collect, process and merge all this internal and external data to find patterns that previously could not be seen. So-called information fusion provides a new perspective on big data and can make significant contributions to the industry to understand their business by combining, looking at, and understanding several different data flows.
This project will show how the metal industry can use the latest digital technology and data analysis methods to transform their data flows into information flows. The project will provide companies of the innovation area with concrete examples of how a data-driven approach can develop their businesses, and make it easier for Swedish data competence to initiate projects with the industry by showing them what kinds of data streams the businesses generate.
DataFlow is a collaboration with Outokumpu Stainless AB, Jernkontoret and Advectas AB, and is funded by the Swedish Governmental Agency for Innovation Systems(VINNOVA) during April 2017–March 2018 with 1.9 million SEK, of which SAIL receives 1.5 million SEK.