Aalto Good Life Lab
Aalto Good Life Lab
Computational Science
This research area is at the intersection of computer science and the sciences, developing bespoke, theoretically grounded algorithms and models with performance guarantees for the computational modelling and analysis of systems and data across biosciences, chemistry, physics, earth sciences, medicine, network science, and the humanities. The work is pursued in close collaboration with leading national and international experts to ensure scientific relevance and methodological rigour.
Research Area Leaders
Indre Žliobaitė
Research Area Leader
Harri Lähdesmäki
Research Area Deputy Leader
People
Talayeh Aledavood
behavioral sensing, digital traces, digital phenotyping, mental health and wellbeing, data science
Johannes Arend
Spatial Audio, Psychoacoustics, Hearing Science, Virtual Acoustics, Perception, XR, VR, AR
Petter Holme
computational social science, AI and society
Aapo Hyvärinen
Machine learning, computational neuroscience
Mikko Kivelä
network science, computational social science
Arto Klami
Machine learning, AI, Bayesian statistics, AI-assisted research
Maarit Korpi-Lagg
High-performance computing; distributed computing; scientific computing; astroinformatics
Kjell Lemström
Computational musicology, algorithms, learning analytics
Janne Lindqvist
human-computer interaction, HCI, good life, well-being
Riku Linna
Dynamical systems, complex systems, computer simulation, machine learning, system identification, system forecasting
Michael Mathioudakis
efficient ML and data analysis, algorithms
Simon Puglisi
Algorithms; Data Structures; Genomics; Data Compression; Pattern Matching
Juho Rousu
molecular machine learning, computational biomedicine
Alexandru Tomescu
bioinformatics, pangenomics, graph algorithms, graph decompositions, parameterized algorithms
Martha Zaidan
Artificial Intelligence, Environmental Sciences, Engineering Systems
Indrė Žliobaitė
data science, complex systems, evolution
Research Groups
Algorithmic Data Science
The goal of our group is to develop efficient and easily manageable data science systems and use them for novel applications. Towards this end, we conduct research at all stages of data science, from data management and processing to model inference and applied data analysis.
Content-based retrieval and analysis of harmony and other music structures (C-BRAHMS)
The C-BRAHMS research group aims at designing and developing efficient methods for computational musicology problems. In particular, it focuses on three computational musicology areas: 1) music pattern matching and detection, 2) automated music generation with the help of human computer interaction, and 3) score following with the help of the first area of this project, optical music recognition and audio transcription. The project develops cutting edge technology and algorithms to these areas and aim to make significant strides in these intertwined fields. Our initiative stands at the intersection of advanced computer science and the legacy of musicology, music composition and performance. It aims to push the boundaries on how music is created, engineered, and interacted with in the future.
Data Science and Evolution
The data science and evolution group employs data science to build an understanding about the evolutionary processes in nature and society and about their causal mechanisms. The group’s present research focuses on methods for better interpreting and modelling fossil records and past conditions.
DigiTraces Lab
Our mission is to develop new methodologies and tools to quantify people’s behavior and turn these traces into insights about their mental and physical health and well-being. To this end, we run privacy-aware studies to collect digital traces from individuals and populations. These data may come from personal devices such as smartphones and fitness trackers or online traces such as web browser activity or social media. We develop new computational methods, stemming from different domains, from statistical and machine learning to natural language processing and large language models, depending on the needs of each project and the application domain.
Graph Algorithms and Bioinformatics
Our research is focused on graph algorithms, from both a theoretical perspective, and a practical perspective motivated by real-world problems in Bioinformatics, such as genome sequencing technologies.
We also study related algorithmic topics, such as combinatorial optimization, enumeration algorithms, string algorithms. Our main application area is Bioinformatics, where we work on various assembly problems of high-throughput sequencing data, pan-genomics, protein evolution.
High-performance computing Lab (HPCLab)
Our research group develops and utilises high-performance and data intensive computing (HPC) methods and applications for heterogeneous NUMA-architectures.
Our spearhead area is astroinformatics, namely methods and tools for simulating and analysing data from complex (astro)physical systems, such as turbulent fluids, the Sun, and interstellar matter in galaxies. The developed methods include simulation tools accelerated with graphics processing units, and data-analysis tools employing machine learning
Kernel Methods, Pattern Analysis and Computational Biology (KEPACO)
The KEPACO group develops machine learning methods, models and tools for data science, in particular computational metabolomics. The methodological backbone of the group is formed by kernel methods and regularized learning. The group particularly focusses in learning with multiple and structured targets, multiple views and ensembles. Applications of interest include metabolomics, biomedicine, pharmacology and synthetic biology.
Natural Computation
The group seeks to understand, model, and program naturally occurring or nature-inspired self-organising processes. The current main focus is on DNA and RNA self-assembly, but related areas of interest are e.g. algorithms for swarm robotics and programmable matter, control of distributed sensor networks, and stochastic optimisation methods for complex energy landscapes.
Multi-source probabilistic inference
The Multi-source Probabilistic Inference (MUPI) research group studies statistical machine learning and artificial intelligence. We develop new methods and algorithms for coping with uncertainty in artificial intelligence, focusing in particular on approximate Bayesian inference of probabilistic programs. We also solve interesting practical problems across multiple application fields, developing machine learning techniques in particular for setups with limited amount of training examples.
Intelligent enviRonmental mOnitoring and aNalytics (IRON)
IRON is a research group within the Institute for Atmospheric and Earth System Research (INAR) and the Department of Computer Science (CS) at the University of Helsinki. The group is led by Martha Arbayani Zaidan (Academy Research Fellow and Data Scientist). The group focuses on the use of modern AI technologies to tackle some computational and monitoring issues in environmental sciences and related disciplines. Stay informed about current research and projects, activities, and collaboration.
Technical Psychoacoustics
The Technical Psychoacoustics research group works at the intersection of technical developments in virtual acoustics and spatial audio, the perceptual evaluation of these technologies, and their application in hearing science.