SimulaMets research projects are both internally and externally financed. We collaborate with universities both in Norway and in other countries, as well as with industry.
FFC: Female Football Centre
The Department of Holistic Systems at SimulaMet is collaborating with UiT - The Arctic University of Norway and Forzasys AS on the Female Football Centre (FFC), funded by the Tromsø Research Foundation.
The main goal of the centre is to gain new and fundamental insights into what affects the performance and overall health of female elite football players. A general objective is to devise novel methodologies for epidemiological research that might impact research fields in both sports and medicine. In particular, we aim to develop a non-invasive, privacy-preserving technology that enables us to continuously quantify and monitor athlete behavior where we derive analytic insights from different perspectives (e.g., biomechanics, sports-specific science, medicine, coaches, and athletes).
In the current gold standards for epidemiology, observational prospective cohort studies include that cohort subjects are followed in detail over a longer period. This is an error-prone and tedious task that has for a long time been carried out using pen and paper, and later doing a manual, tedious analysis. Making this entire process easier is the main responsibility of the researchers from the Department of Holistic Systems at SimulaMet.
In cooperation with UiT and Forzasys AS, SimulaMet has earlier developed and used an automatic performance monitoring system for athletes used by both national and elite series soccer teams. The goal is to quantify and develop accurate analysis technologies that enable a personalized assessment and performance development of elite athletes.
The automatic performance monitoring system collects athletes’ subjective parameters, like training load, wellness, injury, and illness, using a small questionnaire-app running on their mobile phones, and the data is transferred to a cloud-based backend system. Then, from a trainer-portal, the data can be automatically visualized for both individual players and team overviews.
In FFC, the objective is to extend the system further to include female-specific parameters and introduce more automatic analysis using, for example, machine learning. We will host and develop the system for all the teams participating in the project, and we will initiate automatic analyses that might be able to predict future overuse injuries or to help maybe to find the best development process of a player or a team.
Svein Arne Pettersen (head of research at the School of sports sciences, UiT) is the centre leader, and he has collaborated with the researchers at SimulaMet for a long time.
Read more about the new Female Football Centre (FFC)
FFC is funded by Tromsø Research Foundation.
TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion
Data mining holds the promise to improve our understanding of dynamics of complex systems such as the human brain and human metabolome (i.e., the complete set of small biochemical compounds in the human body) by discovering the underlying patterns, i.e., subsystems, in data collected from these systems. However, discovering those patterns and understanding their evolution in time is a challenging task. The complexity of the systems requires collection of both time-evolving and static data from multiple sources using different technologies recording the behavior of the system from complementary viewpoints, and there is a lack of data mining methods that can find the hidden patterns in such complex data.
The goal of this multidisciplinary project is to develop novel data mining techniques to jointly analyze static and dynamic data sets to discover underlying patterns, understand temporal dynamics of those patterns, and capture early signs of future outcomes. We will introduce a scalable and constrained data fusion framework that can jointly factorize heterogeneous data in the form of matrices and multi-way arrays, by incorporating temporal as well as domain-specific constraints.
These methods will be motivated by a real, challenging system: the human metabolome, and used to jointly analyze static genetic information and longitudinal metabolomics data to discover interpretable patterns, i.e., subsystems corresponding to metabolic networks (networks of metabolites acting together), with the ultimate goal of understanding their role in the transition from healthy to diseased states. The project will play a significant role in terms of developing the data mining tools needed to extract meaningful information from the surge of data, referred to as "personal data clouds" being collected in predictive medicine studies, where participants give blood samples regularly to track their health status and will be alerted of early signs of diseases.
Funding Source
Research Council of Norway, IKTPLUSS (2020-2023)
Novo Nordisk Foundation, Exploratory Interdisciplinary Synergy Grant (2020-2022)
Partners
COPSAC (Danish Pediatric Asthma Center)
University of Copenhagen
University of Amsterdam
Publications for TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion
Journal Article
Characterizing human postprandial metabolic response using multiway data analysis
bioRxiv (2023).Status: Submitted
Characterizing human postprandial metabolic response using multiway data analysis
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Journal Article |
| Year of Publication | 2023 |
| Journal | bioRxiv |
| Publisher | biorxiv |
| DOI | 10.1101/2023.08.31.555521 |
Analyzing postprandial metabolomics data using multiway models: A simulation study
bioRxiv (2023).Status: Submitted
Analyzing postprandial metabolomics data using multiway models: A simulation study
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Journal Article |
| Year of Publication | 2023 |
| Journal | bioRxiv |
| Publisher | bioRxiv |
| URL | https://www.biorxiv.org/content/10.1101/2022.12.19.521154v2 |
| DOI | 10.1101/2022.12.19.521154 |
Proceedings, refereed
A Time-aware Tensor Decomposition for Tracking Evolving Patterns
In MLSP'23: IEEE International Workshop on Machine Learning for Signal Processing. IEEE, 2023.Status: Accepted
A Time-aware Tensor Decomposition for Tracking Evolving Patterns
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2023 |
| Conference Name | MLSP'23: IEEE International Workshop on Machine Learning for Signal Processing |
| Publisher | IEEE |
PARAFAC2-based coupled Matrix and Tensor Factorizations
In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023.Status: Published
PARAFAC2-based coupled Matrix and Tensor Factorizations
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2023 |
| Conference Name | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Pagination | 1-5 |
| Publisher | IEEE |
| DOI | 10.1109/ICASSP49357.2023.10094562 |
Talks, invited
Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
In Acceleration and Extrapolation Methods, ICERM, Brown University, 2023.Status: Published
Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Talks, invited |
| Year of Publication | 2023 |
| Location of Talk | Acceleration and Extrapolation Methods, ICERM, Brown University |
| URL | https://icerm.brown.edu/topical_workshops/tw-23-aem/ |
Extracting Insights from Complex Data: Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
In IPAM Workshop on Explainable AI for the Sciences: Towards Novel Insights, 2023.Status: Published
Extracting Insights from Complex Data: Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Talks, invited |
| Year of Publication | 2023 |
| Location of Talk | IPAM Workshop on Explainable AI for the Sciences: Towards Novel Insights |
| URL | http://www.ipam.ucla.edu/abstract/?tid=18155&pcode=XAI2023 |
Journal Article
Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness
IEEE Signal Processing Magazine 39, no. 4 (2022): 8-24.Status: Published
Reproducibility in Matrix and Tensor Decompositions: Focus on Model Match, Interpretability, and Uniqueness
| Afilliation | Machine Learning |
| Project(s) | TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion, Department of Data Science and Knowledge Discovery |
| Publication Type | Journal Article |
| Year of Publication | 2022 |
| Journal | IEEE Signal Processing Magazine |
| Volume | 39 |
| Issue | 4 |
| Pagination | 8-24 |
| Date Published | 06/2022 |
| Publisher | IEEE |
| DOI | 10.1109/MSP.2022.3163870 |
Tracing Evolving Networks using Tensor Factorizations vs. ICA-based Approaches
Frontiers in Neuroscience 16 (2022).Status: Published
Tracing Evolving Networks using Tensor Factorizations vs. ICA-based Approaches
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Journal Article |
| Year of Publication | 2022 |
| Journal | Frontiers in Neuroscience |
| Volume | 16 |
| Date Published | 04/2022 |
| Publisher | Frontiers |
| URL | https://www.frontiersin.org/article/10.3389/fnins.2022.861402 |
| DOI | 10.3389/fnins.2022.861402 |
An AO-ADMM approach to constraining PARAFAC2 on all modes
SIAM Journal on Mathematics of Data Science 4 (2022): 1191-1222.Status: Published
An AO-ADMM approach to constraining PARAFAC2 on all modes
Analyzing multi-way measurements with variations across one mode of the dataset is a challenge in various fields including data mining, neuroscience and chemometrics. For example, measurements may evolve over time or have unaligned time profiles. The PARAFAC2 model has been successfully used to analyze such data by allowing the underlying factor matrices in one mode (i.e., the evolving mode) to change across slices. The traditional approach to fit a PARAFAC2 model is to use an alternating least squares-based algorithm, which handles the constant cross-product constraint of the PARAFAC2 model by implicitly estimating the evolving factor matrices. This approach makes imposing regularization on these factor matrices challenging. There is currently no algorithm to flexibly impose such regularization with general penalty functions and hard constraints. In order to address this challenge and to avoid the implicit estimation, in this paper, we propose an algorithm for fitting PARAFAC2 based on alternating optimization with the alternating direction method of multipliers (AO-ADMM). With numerical experiments on simulated data, we show that the proposed PARAFAC2 AO-ADMM approach allows for flexible constraints, recovers the underlying patterns accurately, and is computationally efficient compared to the state-of-the-art. We also apply our model to a real-world chromatography dataset, and show that constraining the evolving mode improves the interpretability of the extracted patterns.
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Journal Article |
| Year of Publication | 2022 |
| Journal | SIAM Journal on Mathematics of Data Science |
| Volume | 4 |
| Number | 3 |
| Pagination | 1191-1222 |
| Publisher | SIAM |
| Place Published | SIAM Journal on Mathematics of Data Science |
| DOI | 10.1137/21M1450033 |
Exploring Dynamic Metabolomics Data With Multiway Data Analysis: a Simulation Study
BMC Bioinformatics 23 (2022).Status: Published
Exploring Dynamic Metabolomics Data With Multiway Data Analysis: a Simulation Study
Background: Analysis of dynamic metabolomics data holds the promise to improve our understanding of underlying mechanisms in metabolism. For example, it may detect changes in metabolism due to the onset of a disease. Dynamic or time-resolved metabolomics data can be arranged as a three-way array with entries organized according to a subjects mode, a metabolites mode and a time mode. While such time-evolving multiway data sets are increasingly collected, revealing the underlying mechanisms and their dynamics from such data remains challenging. For such data, one of the complexities is the presence of a superposition of several sources of variation: induced variation (due to experimental conditions or inborn errors), individual variation, and measurement error. Multiway data analysis (also known as tensor factorizations) has been successfully used in data mining to find the underlying patterns in multiway data. In this paper, we study the use of multiway data analysis to reveal the underlying patterns and dynamics in time-resolved metabolomics data.
Results: We focus on simulated data arising from different dynamic models of increasing complexity, i.e., a simple linear system, a yeast glycolysis model, and a human cholesterol model. We generate data with induced variation as well as individual variation. Systematic experiments are performed to demonstrate the advantages and limitations of multiway data analysis in analyzing such dynamic metabolomics data and their capacity to disentangle the different sources of variations. We choose to use simulations since we want to understand the capability of multiway data analysis methods which is facilitated by knowing the ground truth.
Conclusion: Our numerical experiments demonstrate that despite the increasing complexity of the studied dynamic metabolic models, tensor factorization methods CANDECOMP/PARAFAC(CP) and Parallel Profiles with Linear Dependences (Paralind) can disentangle the sources of variations and thereby reveal the underlying mechanisms and their dynamics.
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , TrACEr: Time-Aware ConstrainEd Multimodal Data Fusion |
| Publication Type | Journal Article |
| Year of Publication | 2022 |
| Journal | BMC Bioinformatics |
| Volume | 23 |
| Number | Article 31 |
| Date Published | 2022 |
| Publisher | Springer |
| DOI | 10.1186/s12859-021-04550-5 |
DeCipher
Cancer is a significant cause of morbidity and mortality worldwide. In Norway alone, there are more than 33,000 new cancer patients each year, and 11,000 cancer-associated deaths in 2017. A large proportion of these incidents are preventable. For example, a mass-screening program against cervical cancer established in the Nordic countries has demonstrated a reduction in morbidity and mortality almost by 80 %. Despite this success, it remains a significant challenge to improve the screening program, such as minimize over screening and undertreatment and hence reduce expenditure in a broad public health perspective.
Current knowledge about the disease, together with a wealth of available data and modern technologies, can offer far better-personalized prevention, by deriving an individual-based time till the next screening. Existing automatic decision support systems for cervical cancer prevention are, however, extremely conservative as they are mostly limited to identifying patients who are overdue for their next routine screening, without providing any personalized recommendations for follow-ups.
By intelligent use of existing registries and health data, DeCipher aims to develop a data-driven framework to provide a personalized time-varying risk assessment for cancer initiation and identify subgroups of individuals and factors leading to similar disease progression. By unveiling structure hidden in the data, we will develop novel theoretically grounded machine learning methods for the analysis of large-scale registry and health data.
DeCipher consists of an excellent multidisciplinary research team from diverse fields such as machine learning, data mining, screening programs, and epidemiology. Available to screening programs, clinicians, and individuals in the population, the DeCipher results will allow for an improvement of an individual’s preventive cancer healthcare while reducing the cost of screening programs.
SimulaMet’s Role
SimulaMet will play a central role in the development of machine learning algorithms for longitudinal screening data analysis. Moreover, as the coordinator, SimulaMet is responsible for overall project management and dissemination activities.
Funding source
Research Council of Norway, IKTPLUSS
All partners
Cancer Registry Norway
Karolinska University Hospital, Sweden
Lawrence Livermore National Lab, USA
Coordinator
SimulaMet
Publications for DeCipher
Journal Article
Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
WIREs Data Mining and Knowledge Discovery 13 (2023).Status: Published
Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , DeCipher |
| Publication Type | Journal Article |
| Year of Publication | 2023 |
| Journal | WIREs Data Mining and Knowledge Discovery |
| Volume | 13 |
| Number | e1494 |
| Publisher | Wiley |
| DOI | 10.1002/widm.1494 |
Proceedings, refereed
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
In Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development. Springer, 2022.Status: Published
Phenotyping of cervical cancer risk groups via generalized low-rank models using medical questionnaires
| Afilliation | Machine Learning |
| Project(s) | DeCipher, Department of Data Science and Knowledge Discovery |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2022 |
| Conference Name | Norwegian AI Symposium: Nordic Artificial Intelligence Research and Development |
| Pagination | 94--110 |
| Publisher | Springer |
| DOI | 10.1007/978-3-031-17030-0_8 |
Talks, contributed
Mono- and multi-infection patterns of HPV and the risk of cervical intraepithelial neoplasia
In ANCR Symposium, the Faroe Islands. ANCR Symposium, 2022.Status: Published
Mono- and multi-infection patterns of HPV and the risk of cervical intraepithelial neoplasia
| Afilliation | Machine Learning |
| Project(s) | DeCipher |
| Publication Type | Talks, contributed |
| Year of Publication | 2022 |
| Location of Talk | ANCR Symposium, the Faroe Islands |
| Publisher | ANCR Symposium |
Talks, contributed
Generalized Low-Rank Models for Phenotyping Cervical Cancer Risk Groups using Medical Questionnaires
In Stavanger, Norway, 2021.Status: Published
Generalized Low-Rank Models for Phenotyping Cervical Cancer Risk Groups using Medical Questionnaires
| Afilliation | Machine Learning |
| Project(s) | Department of Data Science and Knowledge Discovery , DeCipher |
| Publication Type | Talks, contributed |
| Year of Publication | 2021 |
| Location of Talk | Stavanger, Norway |
UPSKILL
An incomplete mapping of the skills of a given individual, combined with insufficient insight into a company's actual need for competence, give rise to quite a few challenges. For instance, it may lead to hiring the wrong candidates, lack of insight into the best path for personal development and challenges when deciding relevant content for courses, learning material and for continued education.
UPSKILL will introduce a global platform for professional networking. The platform will connect individuals, companies and learning providers, and offer automatic methods for identification, mapping, and development of skills and abilities.
The project will result in new methods for representing the skills of an individual, mapping a company's need for competence, as well as new methods for matching available skills and abilities with the actual need for
competence. The methods will be self-learning, applicable for commercial use and independent of industry.
As a result, the UPSKILL platform will lead to simplified and less expensive hiring and restructuring processes, reduced risk of hiring wrong candidates, free competence guidance for individuals, and content recommendation for learning providers. The platform will be launched in Europe and Southeast Asia after project completion.
Simula’s Role
Simula plays a central role in designing and developing data-driven algorithms for the automatic and unbiased hiring process, identification of individual’s competence profile from available data sources, and development of matching algorithms for potential employees and employers. The developed methods will form a solid foundation for the UPSKILL platform.
Funding source
Research Council of Norway, BIA
All partners
Simula Metropolitan Center for Digital Engineering
Oslo Metropolitan University
University of South-Eastern Norway
Coordinator
Conexus AS