| DatabionicSwarm-package {DatabionicSwarm} | R Documentation |
Swarm Intelligence for Self-Organized Clustering
Description
Algorithms implementing populations of agents that interact with one another and sense their environment may exhibit emergent behavior such as self-organization and swarm intelligence. Here, a swarm system called Databionic swarm (DBS) is introduced which was published in Thrun, M.C., Ultsch A.: "Swarm Intelligence for Self-Organized Clustering" (2020), Artificial Intelligence, <DOI:10.1016/j.artint.2020.103237>. DBS is able to adapt itself to structures of high-dimensional data such as natural clusters characterized by distance and/or density based structures in the data space. The first module is the parameter-free projection method called Pswarm (Pswarm()), which exploits the concepts of self-organization and emergence, game theory, swarm intelligence and symmetry considerations. The second module is the parameter-free high-dimensional data visualization technique, which generates projected points on the topographic map with hypsometric tints defined by the generalized U-matrix (GeneratePswarmVisualization()). The third module is the clustering method itself with non-critical parameters (DBSclustering()). Clustering can be verified by the visualization and vice versa. The term DBS refers to the method as a whole. It enables even a non-professional in the field of data mining to apply its algorithms for visualization and/or clustering to data sets with completely different structures drawn from diverse research fields. The comparison to common projection methods can be found in the book of Thrun, M.C.: "Projection Based Clustering through Self-Organization and Swarm Intelligence" (2018) <DOI:10.1007/978-3-658-20540-9>.
Details
For a brief introduction to DatabionicSwarm please see the vignette Short Intro to the Databionic Swarm (DBS). The license is CC BY-NC-SA 4.0.
Index of help topics:
DBSclustering Databonic swarm clustering (DBS)
DatabionicSwarm-package
Swarm Intelligence for Self-Organized
Clustering
DefaultColorSequence Default color sequence for plots
Delaunay4Points Adjacency matrix of the delaunay graph for
BestMatches of Points
Delta3DWeightsC Intern function
DijkstraSSSP Internal function: Dijkstra SSSP
GeneratePswarmVisualization
Generates the Umatrix for Pswarm algorithm
Hepta Hepta is part of the Fundamental Clustering
Problem Suit (FCPS) [Thrun/Ultsch, 2020].
Lsun3D Lsun3D is part of the Fundamental Clustering
Problem Suit (FCPS) [Thrun/Ultsch, 2020].
ProjectedPoints2Grid Transforms ProjectedPoints to a grid
Pswarm A Swarm of Databots based on polar coordinates
(Polar Swarm).
PswarmCurrentRadiusC2botsPositive
intern function, do not use yourself
RelativeDifference Relative Difference
ShortestGraphPathsC Shortest GraphPaths = geodesic distances
UniquePoints Unique Points
findPossiblePositionsCsingle
Intern function, do not use yourself
getCartesianCoordinates
Intern function: Transformation of Databot
indizes to coordinates
getUmatrix4Projection depricated! see GeneralizedUmatrix()
Generalisierte U-Matrix fuer
Projektionsverfahren
plotSwarm Intern function for plotting during the Pswarm
annealing process
rDistanceToroidCsingle
Intern function for 'Pswarm'
sESOM4BMUs Intern function: Simplified Emergent
Self-Organizing Map
setGridSize Sets the grid size for the Pswarm algorithm
setPolarGrid Intern function: Sets the polar grid
setRmin Intern function: Estimates the minimal radius
for the Databot scent
setdiffMatrix setdiffMatrix shortens Matrix2Curt by those
rows that are in both matrices.
trainstepC Internal function for sESOM
Note
For interactive Island Generation of a generalized Umatrix
see interactiveGeneralizedUmatrixIsland function in the package ProjectionBasedClustering.
If you want to verifiy your clustering result externally, you can use Heatmap or SilhouettePlot of the CRAN package DataVisualizations.
Author(s)
Michal Thrun
Maintainer: Michael Thrun <m.thrun@gmx.net>
References
[Thrun/Ultsch, 2021] Thrun, M. C., and Ultsch, A.: Swarm Intelligence for Self-Organized Clustering, Artificial Intelligence, Vol. 290, pp. 103237, doi:10.1016/j.artint.2020.103237, 2021.
[Thrun/Ultsch, 2021] Thrun, M. C., & Ultsch, A.: Swarm Intelligence for Self-Organized Clustering (Extended Abstract), in Bessiere, C. (Ed.), 29th International Joint Conference on Artificial Intelligence (IJCAI), Vol. IJCAI-20, pp. 5125–5129, doi:10.24963/ijcai.2020/720, Yokohama, Japan, Jan., 2021.
[Thrun/Ultsch, 2020] Thrun, M. C., & Ultsch, A.: Uncovering High-Dimensional Structures of Projections from Dimensionality Reduction Methods, MethodsX, Vol. 7, pp. 101093, DOI doi:10.1016/j.mex.2020.101093, 2020.
[Thrun, 2018] Thrun, M. C.: Projection Based Clustering through Self-Organization and Swarm Intelligence, doctoral dissertation 2017, Springer, Heidelberg, ISBN: 978-3-658-20539-3, doi:10.1007/978-3-658-20540-9, 2018.
[Ultsch/Thrun, 2017] Ultsch, A., & Thrun, M. C.: Credible Visualizations for Planar Projections, in Cottrell, M. (Ed.), 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization (WSOM), IEEE Xplore, France, 2017.
[Thrun et al., 2016] Thrun, M. C., Lerch, F., Loetsch, J., & Ultsch, A.: Visualization and 3D Printing of Multivariate Data of Biomarkers, in Skala, V. (Ed.), International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), Vol. 24, Plzen, http://wscg.zcu.cz/wscg2016/short/A43-full.pdf, 2016.
Successfully used in
[Thrun et al., 2018] Thrun, M. C., Breuer, L., & Ultsch, A. : Knowledge discovery from low-frequency stream nitrate concentrations: hydrology and biology contributions, Proc. European Conference on Data Analysis (ECDA), pp. 46-47, Paderborn, Germany, 2018.
[Weyer-Menkhoff et al., 2018] Weyer-Menkhoff, I., Thrun, M. C., & Loetsch, J.: Machine-learned analysis of quantitative sensory testing responses to noxious cold stimulation in healthy subjects, European Journal of Pain, Vol. 22(5), pp. 862-874, DOI doi:10.1002/ejp.1173, 2018.
[Kringel et al., 2018] Kringel, D., Geisslinger, G., Resch, E., Oertel, B. G., Thrun, M. C., Heinemann, S., & Loetsch, J. : Machine-learned analysis of the association of next-generation sequencing based human TRPV1 and TRPA1 genotypes with the sensitivity to heat stimuli and topically applied capsaicin, Pain, Vol. 159 (7 ), pp. 1366-1381, DOI doi:10.1097/j.pain.0000000000001222, 2018
[Thrun, 2019] Thrun, M. C.: : Cluster Analysis of Per Capita Gross Domestic Products, Entrepreneurial Business and Economics Review (EBER), Vol. 7(1), pp. 217-231, DOI: doi:10.15678/EBER.2019.070113, 2019.
[Lopez-Garcia et al., 2020] Lopez-Garcia, P., Argote, D. L., & Thrun, M. C.: Projection-based Classification of Chemical Groups and Provenance Analysis of Archaeological Materials, IEEE Access, Vol. 8, pp. 152439-152451, DOI doi:10.1109/ACCESS.2020.3016244, 2020.
Examples
data('Lsun3D')
##2d projection, without instant visualization of steps
#Alternative I:
#DistanceMatrix hast to be defined by the user.
InputDistances=as.matrix(dist(Lsun3D$Data))
projection=Pswarm(InputDistances)
#2d projection, with instant visualization
## Not run:
#Alternative II: DataMatrix, Distance is Euclidean per default
projection=Pswarm(Lsun3D$Data,Cls=Lsun3D$Cls,PlotIt=T)
## End(Not run)
#
##Computation of Generalized Umatrix
# If Non Euclidean Distances are used, Please Use \code{MDS}
# from the ProjectionBasedClustering package with the correct OutputDimension
# to generate a new DataMatrix from the distances (see SheppardDiagram
# or KruskalStress)
genUmatrixList=GeneratePswarmVisualization(Data = Lsun3D$Data,
projection$ProjectedPoints,projection$LC)
## Visualizuation of GenerelizedUmatrix,
# Estimation of the Number of Clusters=Number of valleys
library(GeneralizedUmatrix)#install if not installed
GeneralizedUmatrix::plotTopographicMap(genUmatrixList$Umatrix,genUmatrixList$Bestmatches)
## Automatic Clustering
# number of Cluster from dendrogram (PlotIt=TRUE) or visualization
Cls=DBSclustering(k=3, Lsun3D$Data,
genUmatrixList$Bestmatches, genUmatrixList$LC,PlotIt=FALSE)
# Verification, often its better to mark Outliers manually
GeneralizedUmatrix::plotTopographicMap(genUmatrixList$Umatrix,genUmatrixList$Bestmatches,Cls)
## Not run:
# To generate the 3D landscape in the shape of an island
# from the toroidal topograpic map visualization
# you may cut your island interactivly around high mountain ranges
Imx = ProjectionBasedClustering::interactiveGeneralizedUmatrixIsland(genUmatrixList$Umatrix,
genUmatrixList$Bestmatches,Cls)
GeneralizedUmatrix::plotTopographicMap(genUmatrixList$Umatrix,
genUmatrixList$Bestmatches, Cls=Cls,Imx = Imx)
## End(Not run)
## Not run:
library(ProjectionBasedClustering)#install if not installed
Cls2=ProjectionBasedClustering::interactiveClustering(genUmatrixList$Umatrix,
genUmatrixList$Bestmatches, Cls)
## End(Not run)