update

Author: snoweye

ChangeLog

@@ -1,4 +1,4 @@
-2014-05-24: Ver. 0.1-7
+2014-05-31: Ver. 0.1-7
   * Migrate to MS-MPI.
 
 2014-02-02: Ver. 0.1-6

DESCRIPTION

@@ -1,11 +1,12 @@
 Package: pmclust
 Version: 0.1-7
-Date: 2014-05-24
+Date: 2014-05-31
 Title: Parallel Model-Based Clustering
 Authors@R: c(person("Wei-Chen", "Chen", role = c("aut", "cre"), email =
         "[email protected]"), person("George", "Ostrouchov", role = "aut"))
-Depends: R (>= 3.0.0), methods, rlecuyer, pbdMPI (>= 0.2-3), MASS
-Enhances: MixSim, pbdSLAP, pbdBASE, pbdDMAT
+Depends: R (>= 3.0.0), methods, rlecuyer, pbdMPI (>= 0.2-4), MASS
+Enhances: MixSim, pbdSLAP (>= 0.1-9), pbdBASE (>= 0.3-0), pbdDMAT (>=
+        0.3-0)
 LazyLoad: yes
 LazyData: yes
 Description: The pmclust aims to utilize model-based clustering (unsupervised)
@@ -24,7 +25,7 @@ URL: http://r-pbd.org/
 BugReports: http://group.r-pbd.org/
 MailingList: Please send questions and comments regarding pbdR to
         [email protected]
-Packaged: 2014-02-02 22:05:31 UTC; snoweye
+Packaged: 2014-05-24 20:19:44 UTC; snoweye
 Author: Wei-Chen Chen [aut, cre],
   George Ostrouchov [aut]
 Maintainer: Wei-Chen Chen <[email protected]>

inst/doc/pmclust-guide.pdf

@@ -195,7 +195,7 @@
 \begin{Command}
 mpiexec -np 4 Rscript -e "demo(ex_MixSim,'pmclust',ask=F,echo=F)"
 \end{Command}
-More performance comparison can be found in~\citet{Chen2012a}.
+More performance comparison can be found in~\citet{Chen2013}.
 
 Further, \code{X.spmd} may be replaced by \code{X.dmat} in a \code{ddmatrix}
 format (block-cyclic) for larger datasets and gaining performance

vignettes/pmclust-include/02-example.tex

@@ -4,7 +4,7 @@
 
 Five algorithms are implemented in this packages including:
 EM~\citep{Dempster1977}, AECM~\citep{Meng1997}, APECM~\citep{Chen2011},
-APECMa~\citep{Chen2012a}, and K-means~\citep{Lloyd1982}.
+APECMa~\citep{Chen2013}, and K-means~\citep{Lloyd1982}.
 The EM-like algorithms (EM, AECM, APECM, and APECMa) are for model-based
 clusterings~\citep{Fraley2002},
 while K-means is a distance based clustering algorithm.

vignettes/pmclust-include/03-algorithm.tex

@@ -28,7 +28,7 @@
 So, the better algorithm such as APECM-like algorithms can provide
 less iterations to convergence and obtain results more efficiently.
 
-The ideas of parallelization can be found in~\citet{Chen2012a},
+The ideas of parallelization can be found in~\citet{Chen2013},
 and the similar idea can benefit other statistical methods when
 applied to large datasets.
 See more SPMD examples on the website

vignettes/pmclust-include/04-discussion.tex

@@ -5,16 +5,16 @@ @MISC{Chen2012pmclustpackage
   note = {R Package},
   url = {http://cran.r-project.org/package=pmclust}
 }
-@ARTICLE{Chen2012a,
+@ARTICLE{Chen2013,
   author = {Chen, W.-C. and Ostrouchov, G. and Pugmire, D. and
             Prabhat, M. and Wehner, M.},
   title = {A Parallel EM Algorithm for Model-Based Clustering with
           Application to Explore Large Spatio-Temporal Data},
   journal = {Technometrics},
   year = {2013},
-  volume = {},
-  pages = {},
-  note = {(revision)},
+  volume = {55},
+  issue = {4},
+  pages = {513-523},
   long_journal = {Technometrics}
 }
 @ARTICLE{Chen2011,