Research projects

My research group is at the University of Helsinki.

(We are always looking for good people, please contact me if interested!)

Interactive Artificial Intelligence for Driving R&D (ongoing)

Our goal is a new generation of AI methodology that can drive a disruptive wave in the Finnish technology industry. The project develops AI software for white-box AI that better understands its users, making AI accessible to in-house domain experts, and improving efficiency and success rate.

The project is funded by the Technology Industries of Finland Centennial Foundation for the period of 2019-2021. The project is a collaboration with seven professors from Aalto University and University of Helsinki (including me), the principal investigator being Prof. Samuel Kaski. See the announcement (in Finnish) at

Finnish Center for Artificial Intelligence (ongoing)

We are members of the Finnish Center for Artificial Intelligence (FCAI).

FCAI is a joint venture by University of Helsinki, Aalto University, and VTT Technical Research Centre of Finland. It is funded in part by the Academy of Finland for the periods of 2019-2022 (funded) and 2023-2026 (planned).

Structure from randomization (ended)

The objective of the project is to develop and apply statistically sound randomization methods to be used to find complex patterns from the data and that can be used in conjunction with the state-of-the art machine learning and data mining methods. By randomization we mean here a process by which we can create a controlled perturbation of the data. These perturbations can be used in statistical significance testing and to make the machine learning algorithms transparent and to explore the model space of machine learning algorithms. In this project we apply on data sets that are of relevance for work life.

Structure from randomization is an Academy Project in the ICT 2023 programme, funded by the Academy of Finland, during 2018-2019.

Human-guided data analysis (ended)

The current methods and processes of data analysis give the knowledge workers, who are rarely experts in data analysis, only a limited means to explore large heterogeneous data sets. We further develop and study the recently introduced formulation of the explorative data analysis task in terms of statistical significance testing and constraints to null hypothesis to develop novel methods of data analysis that are optimised for the use with humans and that can be controlled by the humans. The project has two use cases that are used to demonstrate the methods, namely analysis of scientific data sets collected at the Finnish Institute of Occupational Health and a prototype system by which medical doctors to analyse and study patient data.

Human-guided data analysis is an Academy Project funded by the Academy of Finland for the period of 2015-2019. The project has a web site at

Revolution of Knowledge Work (ended)

In this project study information seeking and sense making methods in knowledge work. The features of knowledge work are nowadays part of increasing number of occupations, also outside the expert domain.

For some examples please take a look on how we can adapt information seeking on the basis of psychophysiological measurements (video), and please read our white paper about the trends of knowledge work and needs for knowledge work tools (pdf).

Revolution of Knowledge Work was a large strategic research opening, funded by Tekes for the period of 2013-2017. The project consortium consisted of Helsinki Institute for Information Technology HIIT, which coordinated the project, and the Finnish Institute of Occupational Health where I was at the time of the project. The project has a web site at

Smarter glasses (ended)

The main objective of the project is to create Smarter glasses – an inexpensive open source mobile system that accurately tracks the gaze and the mental state of the user. The glasses are designed to be used in the context of the Internet of Things (IoT) but are naturally useful for other purposes as well. The aim is to infer user-based outputs relevant from the IoT perspective – such as attention, intention, activity, arousal, vigilance, and cognitive load – and provide these in a reduced form for use with low-powered IoT receiver devices so that the user experience of various smart devices can be improved. Smarter glasses offers a scientifically novel way for studying user interaction, especially within the IoT framework. Also, there are no previous studies in psychology that investigate the synchronization of feedback to eye movements and actions.

Smarter glasses was an Academy Project in the ICT 2023 programme at the Finnish Institute of Occupational Health where I was at the time of the project, funded by the Academy of Finland, during 2015-2016. We coordinated the research consortium, which consists of us and the Visual Cognition Research Group at the University of Helsinki.