nach oben

Journal of Classification

Erschienen in:

18.03.2022

Batch Self-Organizing Maps for Distributional Data with an Automatic Weighting of Variables and Components

verfasst von: Francisco de A. T. de Carvalho, Antonio Irpino, Rosanna Verde, Antonio Balzanella

Erschienen in: Journal of Classification | Ausgabe 2/2022

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This paper deals with a batch self organizing map algorithm for data described by distributional-valued variables (DBSOM). Such variables are characterized to take as values probability or frequency distributions on numeric support. According to the nature of the data, the loss function is based on the L₂ Wasserstein distance, that is one of the most used metrics to compare distributions in the context of distributional data analysis. Besides, to consider the different contributions of the variables, four adaptive versions of the DBSOM algorithm are proposed. Relevance weights are automatically learned, one for each distributional-valued variable, in an additional step of the algorithm. Since the L₂ Wasserstein metric allows a decomposition of the distance into two components, one related to the means and one related to the size and shape of the distributions, relevance weights are automatically learned for each of the two components to emphasize the importance of the different characteristics, related to the moments of the distributions, on the distance value. The proposed algorithms are corroborated by applications on real distributional-valued data sets.

Vorheriger Artikel On Assessments of Agreement Between Fuzzy Partitions

Nächster Artikel Complex Principal Component Analysis: Theory and Geometrical Aspects

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nur mit Berechtigung zugänglich

We remark that g_mj is a distributional data because the corresponding quantile function Q_mj is a weighted average quantile function. For further details see Irpino and Verde (2015)

It is available at https://github.com/Airpino/ADBSOM

See the ?? for the proof.

https://archive.ics.uci.edu/ml/datasets/daily+and+sports+activities

https://cran.r-project.org/package=HistDAWass

Altun, K, Barshan, B, & Tunçel, O (2010). Comparative study on classifying human activities with miniature inertial and magnetic sensors. Pattern Recognition, 43(10), 3605–3620.CrossRef

Badran, F, Yacoub, M, & Thiria, S (2005). Self-organizing maps and unsupervised classification. In G Dreyfus (Ed.) Neural Networks: methodology and applications (pp. 379–442). Singapore: Springer.

Bao, C, Peng, H, He, D, & Wang, J (2018). Adaptive fuzzy c-means clustering algorithm for interval data type based on interval-dividing technique. Pattern Analysis and Applications, 21, 803–812.MathSciNetCrossRef

Barshan, B, & Yuksek, M C (2014). Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. The Computer Journal, 57(11), 1649–1667.CrossRef

Barshan, B, & Yurtman, A (2016). Investigating inter-subject and inter-activity variations in activity recognition using wearable motion sensors. The Computer Journal, 59(9), 1345–1362.CrossRef

Bock, H H (2002). Clustering algorithms and Kohonen maps for symbolic data. J Jpn Soc Comp Statist, 15, 1–13.CrossRef

Bock, H H, & Diday, E. (2000). Analysis of symbolic data exploratory methods for extracting statistical information from complex data. Berlin: Springer.MATH

Cabanes, G, Bennani, Y, Destenay, R, & Hardy, A (2013). A new topological clustering algorithm for interval data. Pattern Recognition, 46, 3030–3039.CrossRef

Cabanes, G, Bennani, Y, Verde, R, & Irpino, A. (2021). On the use of Wasserstein metric in topological clustering of distributional data. https://arxiv.org/abs/2109.04301.

Campello, R J G B, & Hruschka, E R (2006). A fuzzy extension of the silhouette width criterion for cluster analysis. Fuzzy Sets and Systems, 157(21), 2858–2875.MathSciNetCrossRef

de Carvalho, F A T, & De Souza, R M C R (2010). Unsupervised pattern recognition models for mixed feature–type symbolic data. Pattern Recognition Letters, 31, 430–443.CrossRef

de Carvalho, F A T, & Lechevallier, Y (2009). Partitional clustering algorithms for symbolic interval data based on single adaptive distances. Pattern Recognition, 42(7), 1223–1236.CrossRef

de Carvalho, FAT, Irpino, A, & Verde, R. (2015). Fuzzy clustering of distribution-valued data using an adaptive L₂ Wasserstein distance. In: 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp. 1–8). https://doi.org/10.1109/FUZZ-IEEE.2015.7337847.

de Carvalho, F A T, Bertrand, P, & Simões, E C (2016). Batch SOM algorithms for interval-valued data with automatic weighting of the variables. Neurocomputing, 182, 66–81.CrossRef

Diday, E, & Govaert, G (1977). Classification automatique avec distances adaptatives. RAIRO Informatique Computer Science, 11(4), 329–349.MathSciNetMATH

Diday, E, & Simon, J C (1976). Clustering analysis. In K Fu (Ed.) Digital pattern classification (pp. 47–94). Berlin: Springer.

D’Urso, P, & Giovanni, L D (2011). Midpoint radius self-organizing maps for interval-valued data with telecommunications application. Applied Soft Computing, 11, 3877–3886.CrossRef

Friedman, J H, & Meulman, J J (2004). Clustering objects on subsets of attributes. Journal of the Royal Statistical Society: Serie B, 66, 815–849.MathSciNetCrossRef

Gibbs, A L, & Su, F E (2002). On choosing and bounding probability metrics. International Statistical Review, 70(3), 419–435.CrossRef

Hajjar, C, & Hamdan, H (2011a). Self-organizing map based on city-block distance for interval-valued data. In Complex Systems Design and Management - CSDM, (Vol. 2011 pp. 281–292).

Hajjar, C, & Hamdan, H (2011b). Self-organizing map based on Hausdorff distance for interval-valued data. In IEEE International Conference on Systems, Man, and Cybernetics - SMC, (Vol. 2011 pp. 1747–1752).

Hajjar, C, & Hamdan, H (2011c). Self-organizing map based on l2 distance for interval-valued data. In 6th IEEE International Symposium on Applied Computational Intelligence and Informatics - SACI, (Vol. 2011 pp. 317–322).

Hajjar, C, & Hamdan, H (2013). Interval data clustering using self-organizing maps based on adaptive mahalanobis distances. Neural Networks, 46, 124–132.CrossRef

Huang, J Z, Ng, M K, Rong, H, & Li, Z (2005). Automated variable weighting in k-means type clustering. IEEE Trans Pattern Anal Mach Intell, 27(5), 657–668.CrossRef

Hubert, L, & Arabie, P (1985). Comparing partitions. Journal of Classification, 2(1), 193–218.CrossRef

Hulse, D, Gregory, S, & Baker, J. (2002). Willamette River Basin: Trajectories of environmental and ecological change. Oregon State University Press. http://www.fsl.orst.edu/pnwerc/wrb/Atlas_web_compressed/PDFtoc.html.

Irpino, A. (2018). HistDAWass: Histogram data analysis using Wasserstein distance. R package version 1.0.1.

Irpino, A, & Romano, E. (2007). Optimal histogram representation of large data sets: Fisher vs piecewise linear approximation. Revue des Nouvelles Technologies de l’Information RNTI-E-9, 99–110.

Irpino, A, & Verde, R (2006). A new Wasserstein based distance for the hierarchical clustering of histogram symbolic data. In B Vea (Ed.) Data Science and Classification (pp. 185–192). Berlin: Springer.

Irpino, A, & Verde, R (2015). Basic statistics for distributional symbolic variables: A new metric-based approach. Advances in Data Analysis and Classification, 9(2), 143–175.MathSciNetCrossRef

Irpino, A, Verde, R, & de Carvalho, F A T (2014). Dynamic clustering of histogram data based on adaptive squared Wasserstein distances. Expert Systems with Applications, 41(7), 3351–3366.CrossRef

Irpino, A, Verde, R, & de Carvalho, F A T (2017). Fuzzy clustering of distributional data with automatic weighting of variable components. Information Sciences, 406-407, 248–268.MathSciNetCrossRef

Kim, J, & Billard, L (2011). A polythetic clustering process and cluster validity indexes for histogram-valued objects. Computational Statistics and Data Analysis, 55(7), 2250–2262.MathSciNetCrossRef

Kim, J, & Billard, L (2013). Dissimilarity measures for histogram-valued observations. Communications in Statistics - Theory and Methods, 42(2), 283–303.MathSciNetCrossRef

Kiviluoto, K (1996). Topology preservation in self-organizing maps. In IEEE International Conference on Neural Networks, 1996. https://doi.org/10.1109/ICNN.1996.548907, (Vol. 1 pp. 294–299).

Kohonen, T. (1995). Self-organizing maps. New York: Springer.CrossRef

Kohonen, T (2013). Essentials of the self-organizing map. Neural Networks, 37(1), 52–65.CrossRef

Kohonen, T. (2014). MATLAB Implementations and Applications of the Self-Organizing Map. Helsinki: Unigrafia Oy.

Korenjak-Černe, S, & Batagelj, V. (2002). Symbolic data analysis approach to clustering large datasets, (pp. 319–327). Berlin: Springer.

Manning, C, Raghavan, P, & Schütze, H. (2008). Introduction to information retrieval. New York: Cambridge University Press.CrossRef

Meila, M (2007). Comparing clusterings – an information based distance. Journal of Multivariate Analysis, 98(5), 873–895.MathSciNetCrossRef

Milligan, G W, & Cooper, M C (1988). A study of standardization of variables in cluster analysis. Journal of Classification, 5(2), 181–204. https://doi.org/10.1007/BF01897163.MathSciNetCrossRef

Modha, D S, & Spangler, W S (2003). Feature weighting in k-means clustering. Machine Learning, 52(3), 217–237.CrossRef

Mount, N J, & Weaver, D (2011). Self-organizing maps and boundary effects: Quantifying the benefits of torus wrapping for mapping som trajectories. Pattern Analysis and Applications, 14(2), 139–148.MathSciNetCrossRef

Rousseeuw, P J (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65.CrossRef

Rüshendorff, L. (2001). Wasserstein metric. In Encyclopedia of Mathematics. Springer.

Terada, T, & Yadohisa, H (2010). Non-hierarchical clustering for distribution-valued data. In Y Lechevallier G Saporta (Eds.) Proceedings of COMPSTAT, (Vol. 2010 pp. 1653–1660). Berlin: Springer.

Verde, R, & Irpino, A (2008a). Comparing histogram data using a Mahalanobis-Wasserstein distance. In P Brito (Ed.) Proceedings of COMPSTAT 2008, Compstat, (Vol. 2008 pp. 77–89). Heidelberg: Springer.

Verde, R, & Irpino, A (2008b). Dynamic clustering of histogram data: Using the right metric. In B Pea (Ed.) Selected contributions in data analysis and classification (pp. 123–134). Berlin: Springer.

Verde, R, & Irpino, A. (2018). Multiple factor analysis of distributional data. Statistica Applicata: Italin Journal of applied statistics. To appear.MATH

Verde, R, Irpino, A, & Lechevallier, Y (2006). Dynamic clustering of histograms using Wasserstein metric. In A Rizzi M Vichi (Eds.) Proceedings of COMPSTAT 2006, Compstat, (Vol. 2006 pp. 869–876). Heidelberg: Physica Verlag.

Vesanto, J, Himberg, J, Alhoniemi, E, & Parhankangas, J. (1999). Self-organizing map in matlab: the som toolbox. In Inproceedings of the Matlab DSP Conference (pp. 35–40).

Vrac, M, Billard, L, Diday, E, & Chedin, A (2012). Copula analysis of mixture models. Computational Statistics, 27, 427–457.MathSciNetCrossRef

Zhang, L, Bing, Z, & Zhang, L (2015). A hybrid clustering algorithm based on missing attribute interval estimation for incomplete data. Pattern Analysis and Applications, 18, 377–384.MathSciNetCrossRef

Titel: Batch Self-Organizing Maps for Distributional Data with an Automatic Weighting of Variables and Components
verfasst von: Francisco de A. T. de Carvalho
Antonio Irpino
Rosanna Verde
Antonio Balzanella
Publikationsdatum: 18.03.2022
Verlag: Springer US
Erschienen in: Journal of Classification / Ausgabe 2/2022
Print ISSN: 0176-4268
Elektronische ISSN: 1432-1343
DOI: https://doi.org/10.1007/s00357-022-09411-1

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Weitere Artikel der Ausgabe 2/2022

Complex Principal Component Analysis: Theory and Geometrical Aspects

Ordinal Trees and Random Forests: Score-Free Recursive Partitioning and Improved Ensembles

Erratum to: The Spatial Representation of Consumer Dispersion Patterns via a New Multi-level Latent Class Methodology

The Spatial Representation of Consumer Dispersion Patterns via a New Multi-level Latent Class Methodology

On Assessments of Agreement Between Fuzzy Partitions

Editorial: Journal of Classification Vol. 39-2

Premium Partner