The doctoral dissertation in the field of Computer Science will be examined at the Faculty of Science, Forestry and Technology, Joensuu campus.
What is the topic of your doctoral research? Why is it important to study the topic?
My doctoral research investigates how artificial intelligence (AI) can make more reliable and efficient decisions when faced with complex real-world data. As AI becomes increasingly used in healthcare, industry, and everyday technologies, it must be able to recognise not only common patterns but also unusual events that may be important.
Such events can indicate diseases, equipment faults, security threats, or other critical situations. As the volume of data continues to grow, there is a need for intelligent systems that can help people identify important information accurately and efficiently. This research contributes to the development of AI systems that can better support decision-making in situations where reliability matters.
What are the key findings or observations of your doctoral research?
The research shows that AI can become more reliable by paying greater attention to unusual or difficult-to-detect patterns within data. While these patterns are often rare, they frequently contain the most valuable information. The work introduces new approaches that improve how AI identifies meaningful patterns and distinguishes them from noise. The findings demonstrate that better results can be achieved not simply by building larger models, but by developing smarter ways of analysing data.
The research also shows how these ideas can be applied to healthcare, where reliable detection of important signals can support medical decision-making. More broadly, the findings contribute to the development of AI systems that are more accurate, efficient, and dependable in real-world environments.
How can the results of your doctoral research be utilised in practice?
The results can be applied in any field where important information is hidden within large amounts of data. In healthcare, the methods may help identify signs of disease and support healthcare professionals in analysing patient information. In industry, they can help detect faults before failures occur, improving safety and reducing costs.
The findings are also relevant to areas such as cybersecurity, finance, environmental monitoring, and smart technologies, where early detection of important events can improve decision-making and efficiency.
What are the key research methods and materials used in your doctoral research?
The research combined theoretical studies, method development, and experimental evaluation. It began by identifying challenges that limit the reliability of current AI systems when dealing with complex data.
New approaches were developed and tested using real-world datasets. Their performance was compared with existing methods to evaluate both effectiveness and practical usefulness. By combining ideas from artificial intelligence, data analysis, and signal processing, the research aimed to develop solutions that are both scientifically rigorous and relevant to real-world applications.
The doctoral dissertation of Sylwan Rahardja, MMED, entitled Improving reliability and efficiency in machine learning under complex data distributions will be examined at the Faculty of Science, Forestry and Technology, Joensuu campus. The opponent will be University Lecturer Henri Hansen, Tampere University, and the custos will be Professor Pasi Fränti, University of Eastern Finland. Language of the public defence is English.
- Public examination
- Dissertation (PDF)
- Photo (coming)
