clustering Query Show help

Autori sa v príspevku zaoberajú problematikou klasifikácie skupín atletických disciplín ovplyvňuj-úcich športovú výkonnosť sedemboja žien. Na identifikáciu skupín boli využité ukazovatele najlepšíchsvetových výkonov sedemboja nad 6200 bodov podľa dostupných údajov z IAAF (N = 172). Z klasifi-kačných metód zhlukovania boli použité hierarchické modely ako Average linkage (Between & Within- group), Single Linkage - Nearest neigbor, Complete Linkage - Farthest neigbor, Centroid linkage,Median clustering, Ward ́s method.Všetkých sedem zhlukových metód sa zhodlo v dvoch skupinách zhlukov a v obsahu disciplínv 2. klastry [200 m, skok od diaľky, 800 m, 100 m prekážok, skok do výšky] [vrh guľou, hod oštepom].Test stability so štruktúrou zhlukov sedemboja na úrovni 2. klastra je 100 %. Najvyššiu stabilitu42,86 % javí vnútorná hierarchia disciplín [200 m, Skok do diaľky, 100 m prekážok, Skok do výšky,800 m] [Vrh guľou, Hod oštepom].Hierarchické modely umožnili identifikovať skupiny atletických disciplíny ovplyvňujúce športovývýkon v sedemboji žien. Poznanie štruktúry športového výkonu prispieva k zefektívneniu tréningovéhoprocesu a určeniu viacbojárskej typológie pretekárok svetovej výkonnosti.

Authors deals with the problematics of group classification of athletics disciplines, which influence thesports performance in the women's heptathlon. For the group identification, the indicators of the bestworld's performance in heptathlon above the 6200 points according to the data from IAAF (N = 172)were used. From the classification methods of clustering the hierarchical models as the Average linkage(Between & Within-group), Single Linkage - Nearest neighbor, Complete Linkage - Farthest neighbor,Centroid linkage, Median clustering, and Ward ́s method were used.All seven clustering methods agreed in two groups of clusters and in the content of disciplines in2 clusters [200 meters, Long jump, 800 meters, 100 meters hurdles, High jump] [Shot put, Javelinthrow]. The stability test with the cluster structure of heptathlon in the level of the second cluster is100 %. The highest stability, 42,86 %, shows the internal hierarchy of disciplines [200 meters, Longjump, 100 meters hurdles, High jump, 800 meters] [Shot put, Javelin throw].Hierarchical models allow identifying groups of athletics disciplines that influence the sports perfor-mance in women's heptathlon. Understanding the structure of sports performance contributes to thestreamlining the training process and determining the combined events typology of world performanceathletes.

Article

Empirical evidence of the applicability of functional clustering through gene expression classification

Here, we objectively analyze the applicability of functional clustering for the identification of groups ...

IEEE/ACM transactions on computational biology and bioinformatics. 2012 ; 9 (3) : 788-98.

IEEE/ACM Trans Comput Biol Bioinform
ISSN 1557-9964
Medvik
Source

The availability of a great range of prior biological knowledge about the roles and functions of genes and gene-gene interactions allows us to simplify the analysis of gene expression data to make it more robust, compact, and interpretable. Here, we objectively analyze the applicability of functional clustering for the identification of groups of functionally related genes. The analysis is performed in terms of gene expression classification and uses predictive accuracy as an unbiased performance measure. Features of biological samples that originally corresponded to genes are replaced by features that correspond to the centroids of the gene clusters and are then used for classifier learning. Using 10 benchmark data sets, we demonstrate that functional clustering significantly outperforms random clustering without biological relevance. We also show that functional clustering performs comparably to gene expression clustering, which groups genes according to the similarity of their expression profiles. Finally, the suitability of functional clustering as a feature extraction technique is evaluated and discussed.

Article

Learning Markov Random Walks for robust subspace clustering and estimation

Markov Random Walks (MRW) has proven to be an effective way to understand spectral clustering and embedding ...

Neural networks. 2014 ; 59 (-) : 1-15.

Neural Netw
ISSN 1879-2782
Medvik
Source

Markov Random Walks (MRW) has proven to be an effective way to understand spectral clustering and embedding. However, due to less global structural measure, conventional MRW (e.g., the Gaussian kernel MRW) cannot be applied to handle data points drawn from a mixture of subspaces. In this paper, we introduce a regularized MRW learning model, using a low-rank penalty to constrain the global subspace structure, for subspace clustering and estimation. In our framework, both the local pairwise similarity and the global subspace structure can be learnt from the transition probabilities of MRW. We prove that under some suitable conditions, our proposed local/global criteria can exactly capture the multiple subspace structure and learn a low-dimensional embedding for the data, in which giving the true segmentation of subspaces. To improve robustness in real situations, we also propose an extension of the MRW learning model based on integrating transition matrix learning and error correction in a unified framework. Experimental results on both synthetic data and real applications demonstrate that our proposed MRW learning model and its robust extension outperform the state-of-the-art subspace clustering methods.

MeSH
Algorithms MeSH
Emotions physiology MeSH
Humans MeSH
Limbic System physiology MeSH
Models, Neurological MeSH
Neural Networks, Computer * MeSH
Pattern Recognition, Automated methods MeSH
Cluster Analysis MeSH
Models, Theoretical MeSH
Learning MeSH
Artificial Intelligence MeSH
Animals MeSH
Check Tag
Humans MeSH
Animals MeSH
Publication type
Journal Article MeSH
Research Support, Non-U.S. Gov't MeSH
Review MeSH

Collections

Published

Filters

clustering Query Show help

clustering Query Show help

Refine by MeSH