J
Johan Himberg
Researcher at Nokia
Publications - 31
Citations - 4562
Johan Himberg is an academic researcher from Nokia. The author has contributed to research in topics: Mobile device & Context (language use). The author has an hindex of 23, co-authored 31 publications receiving 4307 citations. Previous affiliations of Johan Himberg include Helsinki University of Technology.
Papers
More filters
Journal ArticleDOI
Validating the independent components of neuroimaging time series via clustering and visualization.
TL;DR: In experiments with magnetoencephalographic and functional magnetic resonance imaging data, the method was able to show that expected components are reliable; furthermore, it pointed out components whose interpretation was not obvious but whose reliability should incite the experimenter to investigate the underlying technical or physical phenomena.
Self-organizing map in Matlab: the SOM Toolbox
TL;DR: The SOM Toolbox is an implementation of the SOM and its visualization in the Matlab 5 computing environment and its performance in terms of computational load is evaluated and compared to a corresponding Cprogram.
Journal ArticleDOI
Independent component analysis of fMRI group studies by self-organizing clustering
Fabrizio Esposito,Tommaso Scarabino,Aapo Hyvärinen,Johan Himberg,Elia Formisano,Silvia Comani,Gioacchino Tedeschi,Rainer Goebel,Erich Seifritz,Francesco Di Salle,Francesco Di Salle +10 more
TL;DR: This work exploits the application of similarity measures and a related visual tool to study the natural self-organizing clustering of many independent components from multiple individual data sets in the subject space and exploits commonalities across multiple subject-specific patterns for blind group and subgroup pattern extraction and selection.
Proceedings ArticleDOI
Recognizing human motion with multiple acceleration sensors
TL;DR: In this paper experiments with acceleration sensors are described for human activity recognition of a wearable device user and the use of principal component analysis and independent component analysis with a wavelet transform is tested for feature generation.