Sofie Lövdal
YOU?
Author Swipe
View article: IRMA: Machine learning-based harmonization of $$^{18}$$F-FDG PET brain scans in multi-center studies
IRMA: Machine learning-based harmonization of $$^{18}$$F-FDG PET brain scans in multi-center studies Open
Purpose Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias. Methods We demonstrate the use of the …
View article: IRMA: Machine learning-based harmonization of 18F-FDG PET brain scans in multi-center studies
IRMA: Machine learning-based harmonization of 18F-FDG PET brain scans in multi-center studies Open
Purpose: Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias. Methods: We demonstrate the use of th…
View article: Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)$^2$MA-GLVQ
Mitigating the Bias in Data for Fairness Using an Advanced Generalized Learning Vector Quantization Approach -- FA(IR)$^2$MA-GLVQ Open
We propose a bias detection and mitigating scheme for data in the context of classification tasks based on learning vector quantizers (LVQ) as classifier. For this purpose generalized LVQ endowed with an advanced matrix adaptation scheme i…
View article: Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces
Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces Open
We introduce and investigate the iterated application of Generalized Matrix Learning Vector Quantization for the analysis of feature relevances in classification problems, as well as for the construction of class-discriminative subspaces. …
View article: Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces
Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces Open
We introduce and investigate the iterated application of Generalized Matrix Learning Vector Quantizaton for the analysis of feature relevances in classification problems, as well as for the construction of class-discriminative subspaces. T…
View article: <i>Gaia</i> DR3 view of dynamical substructure in the stellar halo near the Sun
<i>Gaia</i> DR3 view of dynamical substructure in the stellar halo near the Sun Open
Context. Debris from past merger events is expected and also known, to some extent, to populate the stellar halo near the Sun. Aims. We aim to identify and characterise such merger debris using Gaia DR3 data supplemented with metallicity a…
View article: Improved Interpretation of Feature Relevances: Iterated Relevance Matrix Analysis (IRMA)
Improved Interpretation of Feature Relevances: Iterated Relevance Matrix Analysis (IRMA) Open
We introduce and investigate the iterated application of Generalized Matrix Relevance Learning for the analysis of feature relevances in classification problems.The suggested Iterated Relevance Matrix Analysis (IRMA), identifies a linear s…
View article: The Gaia DR3 view of dynamical substructure in the stellar halo near the Sun
The Gaia DR3 view of dynamical substructure in the stellar halo near the Sun Open
The debris from past merger events is expected and, to some extent, known to populate the stellar halo near the Sun. We aim to identify and characterise such merger debris using Gaia DR3 data supplemented by metallicity and chemical abunda…
View article: Substructure in the stellar halo near the Sun
Substructure in the stellar halo near the Sun Open
Context. Merger debris is expected to populate the stellar haloes of galaxies. In the case of the Milky Way, this debris should be apparent as clumps in a space defined by the orbital integrals of motion of the stars. Aims. Our aim is to d…
View article: Substructure in the stellar halo near the Sun
Substructure in the stellar halo near the Sun Open
Context. In an accompanying paper, we present a data-driven method for clustering in ‘integrals of motion’ space and apply it to a large sample of nearby halo stars with 6D phase-space information. The algorithm identified a large number o…
View article: Substructure in the stellar halo near the Sun. I. Data-driven clustering in Integrals of Motion space
Substructure in the stellar halo near the Sun. I. Data-driven clustering in Integrals of Motion space Open
Aims: Develop a data-driven and statistically based method for finding such clumps in Integrals of Motion space for nearby halo stars and evaluating their significance robustly. Methods: We use data from Gaia EDR3 extended with radial velo…
View article: Substructure in the stellar halo near the Sun. II. Characterisation of independent structures
Substructure in the stellar halo near the Sun. II. Characterisation of independent structures Open
In Lövdal et al, we presented a data-driven method for clustering in Integrals of Motion space and applied it to a large sample of nearby halo stars with 6D phase-space information. We identified a large number of clusters, many of which c…
View article: Injury Prediction in Competitive Runners With Machine Learning
Injury Prediction in Competitive Runners With Machine Learning Open
Purpose : Staying injury free is a major factor for success in sports. Although injuries are difficult to forecast, novel technologies and data-science applications could provide important insights. Our purpose was to use machine learning …
View article: Replication Data for: Injury Prediction In Competitive Runners With Machine Learning
Replication Data for: Injury Prediction In Competitive Runners With Machine Learning Open
The data set consists of a detailed training log from a Dutch high-level running team over a period of seven years (2012-2019). We included the middle and long distance runners of the team, that is, those competing on distances between the…